# OpenCV

OpenCV is an open-source computer vision library with over 2,500 algorithms and interfaces for C++, Python, and Java.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Digitization of Analogue Gauges using Computer Vision

DevFeed: [Digitization of Analogue Gauges using Computer Vision](<https://devfeed.tech/articles/digitization-of-analogue-gauges-using-computer-vision-145647.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26262>)

Author: Erico Kayumba Mutonkole, Olasupo Ajayi, Omowunmi Isafiade

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [image recognition](<https://devfeed.tech/topics/image-recognition.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>)

Tags: [automation](<https://devfeed.tech/tags/automation.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [gauge](<https://devfeed.tech/tags/gauge.md>), [manufacturing](<https://devfeed.tech/tags/manufacturing.md>), [opencv](<https://devfeed.tech/tags/opencv.md>), [residual](<https://devfeed.tech/tags/residual.md>), [web-scraping](<https://devfeed.tech/tags/web-scraping.md>)

### AI overview

The study reports that OpenCV with ResNet18 achieved 97.3% accuracy in reading analogue pressure gauges, compared with 64.4% for OpenCV with VGG19 and 63.8% for OpenCV with Scikit-Image. The comparison used 1,848 gauge images covering 0-10 BAR, assembled through web scraping, synthetic generation, and augmentation. These results favor the ResNet18 approach within the reported evaluation; the supplied abstract does not describe deployment performance.

### Source excerpt

arXiv:2611.26262v1 Announce Type: cross Abstract: Analogue gauges remain prevalent in manufacturing industries for measuring physical quantities, yet manual monitoring by operators introduces human error and operational inefficiency. This research developed and evaluated an automated gauge reading system using computer vision and deep learning techniques. Three hybrid approaches were implemented and compared: OpenCV with Scikit-Image (traditional computer vision), OpenCV with ResNet18, and OpenCV with VGG19 (deep learning approaches). A comprehensive dataset of 1,848 pressure gauge images (0-10 BAR range) was curated through web scraping, synthetic generation, and augmentation techniques. The experimental results demonstrate that ResNet18 significantly outperforms the alternatives, achieving an accuracy of 97.3%, compared to VGG19's 64.4% and Scikit-Image's 63.8%. The study validates the effectiveness of residual learning architectures for industrial gauge digitization, providing a robust foundation for Industry 5.0 automation applications.

## OpenCV 5.1 Brings More AVX-512 Optimizations, Other Improvements

DevFeed: [OpenCV 5.1 Brings More AVX-512 Optimizations, Other Improvements](<https://devfeed.tech/articles/opencv-5-1-brings-more-avx-512-optimizations-other-improvements-120976.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/OpenCV-5.1-Released>)

Author: Michael Larabel

Published: 2026-11-06T10:36:58Z

Content type: release

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [OpenCV](<https://devfeed.tech/topics/opencv.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [ai](<https://devfeed.tech/tags/ai.md>), [avx](<https://devfeed.tech/tags/avx.md>), [bug-fixes](<https://devfeed.tech/tags/bug-fixes.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [cudnn](<https://devfeed.tech/tags/cudnn.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [dnn](<https://devfeed.tech/tags/dnn.md>), [github](<https://devfeed.tech/tags/github.md>), [java](<https://devfeed.tech/tags/java.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [opencv](<https://devfeed.tech/tags/opencv.md>), [opengl](<https://devfeed.tech/tags/opengl.md>), [optimizations](<https://devfeed.tech/tags/optimizations.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [python](<https://devfeed.tech/tags/python.md>), [risc-v](<https://devfeed.tech/tags/risc-v.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>)

### AI overview

OpenCV 5.1 adds AVX-512 and other SIMD optimizations, AVX-VNNI improvements, expanded FP8 support, and new RISC-V RVV vector kernels. It removes the classic DNN engine, retaining the newer engine introduced in OpenCV 5.0, and includes NVIDIA CUDA and cuDNN improvements. Other listed changes include an OpenGL 3D visualizer for meshes, point clouds, RGB-D frames, and camera trajectories; improved Java, JavaScript, and Python bindings; and hundreds of bug fixes.

### Source excerpt

OpenCV 5.0 debuted back in June with a rewritten DNN engine and many other exciting improvements for this widely-used computer vision (CV) library. Out today is OpenCV 5.1 with tons of fixes and other incremental improvements to this important code...

## Detecting parcels at the front door with a camera, OpenCV and Home Assistant

DevFeed: [Detecting parcels at the front door with a camera, OpenCV and Home Assistant](<https://devfeed.tech/articles/detecting-parcels-at-the-front-door-with-a-camera-opencv-and-home-assistant-117105.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/11/04/detecting-parcels-at-the-front-door-with-a-camera-opencv-and-home-assistant/>)

Author: Anne Barela

Published: 2026-11-04T15:53:18Z

Content type: article

Language: en

Sources: [Adafruit Industries](<https://devfeed.tech/sources/adafruit-industries-makers-hackers-artists-designers-and-engineers.md>)

Topics: [OpenCV](<https://devfeed.tech/topics/opencv.md>), [Home Assistant](<https://devfeed.tech/topics/home-assistant.md>), [webcam](<https://devfeed.tech/topics/webcam.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [arduino](<https://devfeed.tech/tags/arduino.md>), [bluetooth](<https://devfeed.tech/tags/bluetooth.md>), [camera](<https://devfeed.tech/tags/camera.md>), [electronics](<https://devfeed.tech/tags/electronics.md>), [esp32](<https://devfeed.tech/tags/esp32.md>), [home-assistant](<https://devfeed.tech/tags/home-assistant.md>), [opencv](<https://devfeed.tech/tags/opencv.md>), [projects](<https://devfeed.tech/tags/projects.md>), [python](<https://devfeed.tech/tags/python.md>), [reverse-engineering](<https://devfeed.tech/tags/reverse-engineering.md>)

### AI overview

A Python service uses OpenCV to check for parcels on the front step and notify Home Assistant. A StackyFi ESP32 camera serves a 1280 x 1024 JPEG on request rather than streaming; the service takes a snapshot every three seconds and compares a cropped area with an empty-step reference. It checks structural, luminance and colour changes to reduce false triggers from clouds, shadows and white-balance drift, then waits for a change to remain still for 45 seconds before reporting a parcel. Testing lowered the trigger threshold from 8% to 3% after a small box produced a 6.5% change. The excerpt does not provide setup code or configuration details.

### Source excerpt

Delivery drivers often leave a parcel on the step and drive off without knocking, so a box can sit outside for hours. The Brian Dorey Tech Blog covers a small setup that watches the front step and sends a Home Assistant notification when something shows up. The camera is a StackyFi ESP32 board with a [...]

## Covariance-aware Scoring: A Geometric Correction for Vision-Language Test-Time Adaptation

DevFeed: [Covariance-aware Scoring: A Geometric Correction for Vision-Language Test-Time Adaptation](<https://devfeed.tech/articles/covariance-aware-scoring-a-geometric-correction-for-vision-language-test-time-adaptation-114327.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.00024>)

Author: Lakpa Tamang, Saman Forouzandeh, Kamal Berahmand, Wei Shao, Hamid Beigy, Mahdi Jalili

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [vlm](<https://devfeed.tech/topics/vlm.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>)

Tags: [ambient](<https://devfeed.tech/tags/ambient.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [bayes](<https://devfeed.tech/tags/bayes.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [caching](<https://devfeed.tech/tags/caching.md>), [clip](<https://devfeed.tech/tags/clip.md>), [cosine](<https://devfeed.tech/tags/cosine.md>), [covariance](<https://devfeed.tech/tags/covariance.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [feature](<https://devfeed.tech/tags/feature.md>), [features](<https://devfeed.tech/tags/features.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [language](<https://devfeed.tech/tags/language.md>), [linear](<https://devfeed.tech/tags/linear.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [online](<https://devfeed.tech/tags/online.md>), [prototype](<https://devfeed.tech/tags/prototype.md>), [test](<https://devfeed.tech/tags/test.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

CARe addresses a limitation of cosine-based test-time adaptation (TTA): under anisotropic feature distributions, high-variance directions can dominate scores without being discriminative. It replaces ambient embedding geometry with Mahalanobis geometry induced by the target feature second moment. Under a shared-covariance Gaussian model, the resulting decision direction matches the Bayes-optimal linear discriminant; ambient-space scoring is the isotropic special case. The abstract reports higher adaptation accuracy than base cosine scoring on standard and fine-grained distribution-shift benchmarks across two backbones. Gains are largest for datasets with the greatest feature anisotropy and vanish as features approach isotropy.

### Source excerpt

arXiv:2611.00024v1 Announce Type: cross Abstract: Test-time adaptation (TTA) enables vision--language models such as CLIP to adapt to distribution shifts without labels or access to source data. Existing methods adapt through feature caching, prototype estimation, or the online accumulation of feature statistics, but most ultimately score a test feature against a class representative in the ambient embedding space, typically through cosine similarity. We identify this shared decision rule as a limitation under anisotropic feature distributions, which means when a small number of directions account for a large fraction of feature variance, the score can be dominated by high-variance directions that are not necessarily discriminative. In light of this, we propose CARe, a covariance-aware scoring for TTA that replaces the ambient geometry with a Mahalanobis geometry induced by the target feature second moment. Theoretically, we show that under a shared-covariance Gaussian model the covariance-aware decision direction coincides with that of the Bayes-optimal linear discriminant, with ambient-space scoring as the isotropic special case, and establish that the potential benefit of covariance-aware scoring grows with feature anisotropy. Empirically, we show that CARe improves adaptation accuracy over its base cosine scoring on both standard and fine-grained distribution-shift benchmarks across two backbones. Consistent with our analysis, the gains are largest on datasets whose features are most anisotropic and vanish as the features approach isotropy.

## Raspberry Pi Halloween Wise Cracking skull

DevFeed: [Raspberry Pi Halloween Wise Cracking skull](<https://devfeed.tech/articles/raspberry-pi-halloween-wise-cracking-skull-109251.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/10/30/raspberry-pi-halloween-wise-cracking-skull/>)

Author: Ben

Published: 2026-10-30T20:11:15Z

Content type: article

Language: en

Sources: [Adafruit Industries](<https://devfeed.tech/sources/adafruit-industries-makers-hackers-artists-designers-and-engineers.md>)

Topics: [Raspberry Pi](<https://devfeed.tech/topics/raspberry-pi.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>)

Tags: [adafruit-learn-guide](<https://devfeed.tech/tags/adafruit-learn-guide.md>), [adafruit-learning-system](<https://devfeed.tech/tags/adafruit-learning-system.md>), [als](<https://devfeed.tech/tags/als.md>), [build](<https://devfeed.tech/tags/build.md>), [detection](<https://devfeed.tech/tags/detection.md>), [electronic-halloween](<https://devfeed.tech/tags/electronic-halloween.md>), [halloween](<https://devfeed.tech/tags/halloween.md>), [mc](<https://devfeed.tech/tags/mc.md>), [opencv](<https://devfeed.tech/tags/opencv.md>), [party](<https://devfeed.tech/tags/party.md>), [person-detection](<https://devfeed.tech/tags/person-detection.md>), [pi](<https://devfeed.tech/tags/pi.md>), [pi-5](<https://devfeed.tech/tags/pi-5.md>), [picture](<https://devfeed.tech/tags/picture.md>), [project](<https://devfeed.tech/tags/project.md>), [python](<https://devfeed.tech/tags/python.md>), [raspberry](<https://devfeed.tech/tags/raspberry.md>), [raspberry-pi](<https://devfeed.tech/tags/raspberry-pi.md>), [raspberry-pi-5](<https://devfeed.tech/tags/raspberry-pi-5.md>), [script](<https://devfeed.tech/tags/script.md>), [skull](<https://devfeed.tech/tags/skull.md>), [speaker](<https://devfeed.tech/tags/speaker.md>), [uses](<https://devfeed.tech/tags/uses.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

A Raspberry Pi 5 costume detector turns a Halloween encounter into a spoken joke: OpenCV detects a person, the NoIR PiCamera captures an image, and the image is sent to Claude with a request for a kind-hearted, corny dad joke about the costume. Piper converts the returned joke to speech, which plays through a speaker connected to a speaker bonnet. The excerpt does not provide build instructions or implementation details beyond this workflow.

### Source excerpt

Raspberry Pi Halloween Costume Detector Build a wise cracking skull to MC your Halloween costume party. This project uses a Raspberry Pi 5 paired with a NoIR PiCamera and speaker bonnet. The Pi runs a Python script with OpenCV person detection. When a person crosses paths with the skull, a picture is sent [...]

## Runpod Partners With OpenCV to Empower the Next Gen of AI Builders

DevFeed: [Runpod Partners With OpenCV to Empower the Next Gen of AI Builders](<https://devfeed.tech/articles/runpod-partners-with-opencv-to-empower-the-next-gen-of-ai-builders-94582.md>)

Original publisher: [Read original article](<https://www.runpod.io/blog/runpod-opencv-partnership>)

Author: Brendan McKeag

Published: 2026-10-22T02:42:59Z

Content type: article

Language: en

Sources: [Runpod Blog.](<https://devfeed.tech/sources/runpod-blog.md>)

Topics: [OpenCV](<https://devfeed.tech/topics/opencv.md>), [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-careers](<https://devfeed.tech/tags/ai-careers.md>), [ai-development](<https://devfeed.tech/tags/ai-development.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [api](<https://devfeed.tech/tags/api.md>), [applications](<https://devfeed.tech/tags/applications.md>), [cloud-compute](<https://devfeed.tech/tags/cloud-compute.md>), [cloud-computing](<https://devfeed.tech/tags/cloud-computing.md>), [community](<https://devfeed.tech/tags/community.md>), [compute](<https://devfeed.tech/tags/compute.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [consulting](<https://devfeed.tech/tags/consulting.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [free](<https://devfeed.tech/tags/free.md>), [future](<https://devfeed.tech/tags/future.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [opencv](<https://devfeed.tech/tags/opencv.md>), [partnership](<https://devfeed.tech/tags/partnership.md>), [students](<https://devfeed.tech/tags/students.md>)

### AI overview

Runpod says its partnership with OpenCV will give students access to GPU cloud computing for learning and building computer vision and AI projects. The article presents the partnership as a way to lower the hardware barrier for students who cannot afford high-end GPUs, such as A100s. Runpod says it will provide on-demand GPUs, serverless compute for AI training and inference, and API endpoints for language, image recognition, and speech recognition models. It describes these resources as helping students create, train, and test models and work with larger models and more complex projects. The supplied text does not specify eligibility, access procedures, or the amount or duration of free compute.

### Source excerpt

Runpod has teamed up with OpenCV to provide free GPU access for students building the future of computer vision. Learn how the partnership works and who.

## Computer Vision: SIFT algorithm (Scale Invariant Feature Transform)

DevFeed: [Computer Vision: SIFT algorithm (Scale Invariant Feature Transform)](<https://devfeed.tech/articles/computer-vision-sift-algorithm-scale-invariant-feature-transform-64969.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/computer-vision-sift-algorithm-scale-invariant-feature-transform/>)

Author: Slava Efimov

Published: 2026-10-05T14:18:00Z

Content type: tutorial

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>), [object-detection](<https://devfeed.tech/topics/object-detection.md>)

Tags: [3d-reconstruction](<https://devfeed.tech/tags/3d-reconstruction.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [editor-s-picks](<https://devfeed.tech/tags/editor-s-picks.md>), [invariant](<https://devfeed.tech/tags/invariant.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>)

### AI overview

The tutorial explains how SIFT detects scale- and rotation-invariant image keypoints, builds gradient-based descriptors, and matches features across images. It covers the Difference of Gaussians scale space, filtering weak points, descriptor comparison, and OpenCV usage, then illustrates applications including image matching, object detection, stitching, and 3D reconstruction workflows.

### Source excerpt

Elegant object matching from several viewpoints The post Computer Vision: SIFT algorithm (Scale Invariant Feature Transform) appeared first on Towards Data Science.

## Transcoding UTF-8 to UTF-16 with replacement at gigabytes per second

DevFeed: [Transcoding UTF-8 to UTF-16 with replacement at gigabytes per second](<https://devfeed.tech/articles/transcoding-utf-8-to-utf-16-with-replacement-at-gigabytes-per-second-62841.md>)

Original publisher: [Read original article](<https://lemire.me/blog/2026/09/30/transcoding-utf-8-to-utf-16-with-replacement-at-gigabytes-per-second/>)

Author: Daniel Lemire

Published: 2026-09-30T12:33:27Z

Content type: article

Language: en

Sources: [Daniel Lemire](<https://devfeed.tech/sources/daniel-lemire.md>)

Topics: [Encoding](<https://devfeed.tech/topics/encoding.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>)

Tags: [c-sharp](<https://devfeed.tech/tags/c-sharp.md>), [compiler](<https://devfeed.tech/tags/compiler.md>), [engine](<https://devfeed.tech/tags/engine.md>), [gcc](<https://devfeed.tech/tags/gcc.md>), [icelake](<https://devfeed.tech/tags/icelake.md>), [java](<https://devfeed.tech/tags/java.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [validation](<https://devfeed.tech/tags/validation.md>), [xeon](<https://devfeed.tech/tags/xeon.md>)

### AI overview

The simdutf library adds a function for transcoding invalid UTF-8 input to UTF-16, replacing ill-formed sequences with U+FFFD. The method first validates the input and records error offsets, then transcodes the valid spans. In a reported test on one Xeon Gold 6548N core, simdutf reached 7.0 GB/s on valid input, compared with 1.7 GB/s for a scalar decoder.

### Source excerpt

Our software represents strings using the UTF-16 or the UTF-8 formats. Most text on the web is UTF-8, but Java, C# or JavaScript represents the strings as UTF-16 to the programmer. Sometimes we need to transcode (convert) strings. Your browser probably uses the simdutf library for validating or transcoding. It is part of the widely ... Continue reading Transcoding UTF-8 to UTF-16 with replacement at gigabytes per second

## Photo Scrubber -- local face blur & metadata removal

DevFeed: [Photo Scrubber -- local face blur & metadata removal](<https://devfeed.tech/articles/photo-scrubber-local-face-blur-metadata-removal-62925.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Sep/29/photo-scrubber/>)

Author: Simon Willison

Published: 2026-09-29T16:45:27Z

Content type: article

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [webcam face tracking](<https://devfeed.tech/topics/webcam-face-tracking.md>), [facial landmarks](<https://devfeed.tech/topics/facial-landmarks.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>)

Tags: [automatically](<https://devfeed.tech/tags/automatically.md>), [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [gpt-6](<https://devfeed.tech/tags/gpt-6.md>), [gpt-6-astra](<https://devfeed.tech/tags/gpt-6-astra.md>), [local](<https://devfeed.tech/tags/local.md>), [mediapipe](<https://devfeed.tech/tags/mediapipe.md>), [photo](<https://devfeed.tech/tags/photo.md>), [photography](<https://devfeed.tech/tags/photography.md>), [photography-25](<https://devfeed.tech/tags/photography-25.md>), [tools](<https://devfeed.tech/tags/tools.md>), [tools-79](<https://devfeed.tech/tags/tools-79.md>), [vision](<https://devfeed.tech/tags/vision.md>), [webassembly](<https://devfeed.tech/tags/webassembly.md>)

### AI overview

The author describes an experimental local tool that detects and blurs identifiable faces in photographs. It uses Google's MediaPipe C++ library compiled to WebAssembly and the BlazeFace face detection model.

### Source excerpt

Tool: Photo Scrubber -- local face blur & metadata removal I took a photograph of some protesters, then thought about how I don't like sharing photographs of strangers with identifiable faces. I had GPT-6 Astra build this experimental tool that would identify faces and automatically blur them out. It uses Google's MediaPipe C++ library, compiled to WebAssembly via @mediapipe/tasks-vision, plus the BlazeFace face detection model. Tags: photography, tools

## This Tiny SBC Lets You Swap Interface Modules for Voice, Vision or Sensing

DevFeed: [This Tiny SBC Lets You Swap Interface Modules for Voice, Vision or Sensing](<https://devfeed.tech/articles/this-tiny-sbc-lets-you-swap-interface-modules-for-voice-vision-or-sensing-59827.md>)

Original publisher: [Read original article](<https://feed.itsfoss.com/link/24361/17473150/vicharak-axon-lite>)

Author: Abhishek Prakash

Published: 2026-09-25T07:32:45Z

Content type: article

Language: en

Sources: [It's FOSS](<https://devfeed.tech/sources/it-s-foss.md>)

Topics: [OpenCV](<https://devfeed.tech/topics/opencv.md>), [Python](<https://devfeed.tech/topics/python.md>), [Networking hardware](<https://devfeed.tech/topics/networking-hardware.md>), [hdmi](<https://devfeed.tech/topics/hdmi.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [add-ons](<https://devfeed.tech/tags/add-ons.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-data](<https://devfeed.tech/tags/ai-data.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-vision](<https://devfeed.tech/tags/ai-vision.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [axon](<https://devfeed.tech/tags/axon.md>), [gadgets](<https://devfeed.tech/tags/gadgets.md>), [interface](<https://devfeed.tech/tags/interface.md>), [modules](<https://devfeed.tech/tags/modules.md>), [news](<https://devfeed.tech/tags/news.md>), [npu](<https://devfeed.tech/tags/npu.md>), [rk3576](<https://devfeed.tech/tags/rk3576.md>), [rockchip](<https://devfeed.tech/tags/rockchip.md>), [sbc](<https://devfeed.tech/tags/sbc.md>), [sensing](<https://devfeed.tech/tags/sensing.md>), [this](<https://devfeed.tech/tags/this.md>), [tiny](<https://devfeed.tech/tags/tiny.md>), [vision](<https://devfeed.tech/tags/vision.md>), [voice](<https://devfeed.tech/tags/voice.md>)

### AI overview

Vicharak's Axon-Lite is a small Linux-first SBC built around a Rockchip RK3576, with a listed 6 TOPS NPU, LPDDR5, flexible storage, Wi-Fi 6, Gigabit Ethernet and a Raspberry Pi-compatible 40-pin header. Its main distinction is swappable interface modules for voice processing, smart sensing, AI data, or vision, plus board-to-board expansion. The excerpt also describes camera and display connections and a Debian-style environment with common development and AI tools. A key limitation is that the modular connector may be proprietary, making expansions dependent on Vicharak's module lineup. The 4 GB and 8 GB models are listed for preorder at INR 15,930 and INR 18,299, with shipping expected in January 2027; shipping and customs charges may apply.

### Source excerpt

Vicharak's Axon-Lite packs a Rockchip RK3576, a 6 TOPS NPU and swappable modules into a tiny SBC.

## Sobel Edge Detection in Computer Vision

DevFeed: [Sobel Edge Detection in Computer Vision](<https://devfeed.tech/articles/sobel-edge-detection-in-computer-vision-64114.md>)

Original publisher: [Read original article](<https://roboflow.com/blog/sobel-edge-detection-in-computer-vision>)

Author: Dikshant Shah

Published: 2026-09-22T12:21:33Z

Content type: tutorial

Language: en

Sources: [Roboflow](<https://devfeed.tech/sources/roboflow-blog.md>)

Topics: [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>)

Tags: [code](<https://devfeed.tech/tags/code.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [how-to](<https://devfeed.tech/tags/how-to.md>)

### AI overview

This tutorial explains Sobel edge detection, including its horizontal and vertical 3x3 kernels, gradient magnitude and direction, strengths and limitations, and differences from Canny. It shows how to build and deploy a Sobel workflow using Roboflow Workflows, including a custom Python block with OpenCV.

### Source excerpt

Learn how Sobel edge detection finds edges with two 3x3 kernels, how it compares to Canny, and how to run it on images and video in Roboflow.

## Laplacian Edge Detection in Computer Vision

DevFeed: [Laplacian Edge Detection in Computer Vision](<https://devfeed.tech/articles/laplacian-edge-detection-in-computer-vision-64101.md>)

Original publisher: [Read original article](<https://roboflow.com/blog/laplacian-edge-detection>)

Author: Dikshant Shah

Published: 2026-09-17T18:01:00Z

Content type: tutorial

Language: en

Sources: [Roboflow](<https://devfeed.tech/sources/roboflow-blog.md>)

Topics: [Image processing](<https://devfeed.tech/topics/image-processing.md>), [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>)

Tags: [application-development](<https://devfeed.tech/tags/application-development.md>), [build](<https://devfeed.tech/tags/build.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [deploy](<https://devfeed.tech/tags/deploy.md>)

### AI overview

This tutorial explains Laplacian edge detection, including its use of second-order intensity changes, Gaussian smoothing, zero crossings, and thresholding. It compares Laplacian detection with Sobel and Canny, then shows how to build, test, and deploy an edge detection workflow with Roboflow, including Python code for a custom block.

### Source excerpt

Learn how Laplacian edge detection works, compare it with Sobel and Canny, and build and deploy an edge detection pipeline with Roboflow Workflows.

## Canny Edge Detection in Computer Vision

DevFeed: [Canny Edge Detection in Computer Vision](<https://devfeed.tech/articles/canny-edge-detection-in-computer-vision-64081.md>)

Original publisher: [Read original article](<https://roboflow.com/blog/canny-edge-detection>)

Author: Dikshant Shah

Published: 2026-09-15T18:03:46Z

Content type: tutorial

Language: en

Sources: [Roboflow](<https://devfeed.tech/sources/roboflow-blog.md>)

Topics: [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [object-detection](<https://devfeed.tech/topics/object-detection.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [api](<https://devfeed.tech/tags/api.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [data](<https://devfeed.tech/tags/data.md>), [edge](<https://devfeed.tech/tags/edge.md>)

### AI overview

This tutorial explains Canny edge detection, covering noise reduction, gradient calculation, non-maximum suppression, double thresholding, and hysteresis. It shows how to build an image and video workflow in Roboflow Workflows, including a Python block, adjustable thresholds, and deployment options.

### Source excerpt

Canny edge detection in five steps (blur, gradients, NMS, thresholds, hysteresis), plus a Roboflow Workflow that runs it on images and video.

## How to Measure Volume with Computer Vision

DevFeed: [How to Measure Volume with Computer Vision](<https://devfeed.tech/articles/how-to-measure-volume-with-computer-vision-64099.md>)

Original publisher: [Read original article](<https://roboflow.com/blog/how-to-measure-volume-with-computer-vision>)

Author: Timothy M

Published: 2026-08-24T20:24:07Z

Content type: tutorial

Language: en

Sources: [Roboflow](<https://devfeed.tech/sources/roboflow-blog.md>)

Topics: [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [object-detection](<https://devfeed.tech/topics/object-detection.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [python](<https://devfeed.tech/tags/python.md>), [tutorial](<https://devfeed.tech/tags/tutorial.md>)

### AI overview

The tutorial explains how computer vision can estimate object volume by segmenting an object, calibrating pixel measurements to real-world units, and supplying the third dimension from known height, shape, depth data, or container fill level. Its Roboflow Workflows example uses SAM 3, a 5 x 5 cm calibration marker, mask area measurement, and custom Python code to calculate a rectangular box's external and internal dimensions and volumes.

### Source excerpt

Learn how to measure box volume with computer vision using Roboflow Workflows. This tutorial uses SAM 3 segmentation, a 5 x 5 cm calibration marker, Mask Area Measurement, and Custom Python to convert pixels into physical dimensions and calculate external and internal box volume.

## Best Edge Devices for Computer Vision

DevFeed: [Best Edge Devices for Computer Vision](<https://devfeed.tech/articles/best-edge-devices-for-computer-vision-64076.md>)

Original publisher: [Read original article](<https://roboflow.com/blog/best-edge-devices-for-computer-vision>)

Author: Timothy M

Published: 2026-08-14T16:52:00Z

Content type: tutorial

Language: en

Sources: [Roboflow](<https://devfeed.tech/sources/roboflow-blog.md>)

Topics: [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [Jetson](<https://devfeed.tech/topics/jetson.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>), [DeepStream](<https://devfeed.tech/topics/deepstream.md>), [LiteRT](<https://devfeed.tech/topics/litert.md>), [pc](<https://devfeed.tech/topics/pc.md>), [DuckDB](<https://devfeed.tech/topics/duckdb.md>)

Tags: [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [edge](<https://devfeed.tech/tags/edge.md>), [efficiently](<https://devfeed.tech/tags/efficiently.md>), [fps](<https://devfeed.tech/tags/fps.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [inference](<https://devfeed.tech/tags/inference.md>), [jetson](<https://devfeed.tech/tags/jetson.md>), [performance](<https://devfeed.tech/tags/performance.md>)

### AI overview

A practical guide to selecting edge hardware for computer vision workloads. It compares Jetson devices, industrial PCs, and Raspberry Pi, and explains how camera count, model size, frame rate, latency, and the full video pipeline affect performance. It also outlines deploying and benchmarking a vision application with Roboflow Inference.

### Source excerpt

Explore the best edge devices for computer vision, from NVIDIA Jetson and Raspberry Pi to industrial PCs and Roboflow AI1. Learn how FPS, model size, camera count, and GPU acceleration affect performance, and how Roboflow Inference helps deploy vision models efficiently at the edge.

## Hand-Eye Calibration for Robot Vision with RF-DETR

DevFeed: [Hand-Eye Calibration for Robot Vision with RF-DETR](<https://devfeed.tech/articles/hand-eye-calibration-for-robot-vision-with-rf-detr-64093.md>)

Original publisher: [Read original article](<https://roboflow.com/blog/hand-eye-calibration>)

Author: Mostafa Ibrahim

Published: 2026-08-10T22:08:00Z

Content type: tutorial

Language: en

Sources: [Roboflow](<https://devfeed.tech/sources/roboflow-blog.md>)

Topics: [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>), [object-detection](<https://devfeed.tech/topics/object-detection.md>), [Isaac Sim](<https://devfeed.tech/topics/isaac-sim.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [camera](<https://devfeed.tech/tags/camera.md>), [confidence-score](<https://devfeed.tech/tags/confidence-score.md>), [detection](<https://devfeed.tech/tags/detection.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [model](<https://devfeed.tech/tags/model.md>), [robot](<https://devfeed.tech/tags/robot.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

The tutorial shows how to calibrate the transform between a robot-mounted camera and gripper, detect a target with RF-DETR, and map its position from camera coordinates to robot-base coordinates. Its example uses fixed test transforms and a depth value of 1.0 meter to check the workflow calculations; a real setup would use calibrated transforms and RGB-D depth.

### Source excerpt

Learn how to map camera detections into robot coordinates using hand-eye calibration, so a vision-guided robot can locate targets and use those positions for accurate picking and motion tasks.

## Gemini CLI Vision Extension Adds Webcam Capture, ASL, and Image and Video Generation

DevFeed: [Gemini CLI Vision Extension Adds Webcam Capture, ASL, and Image and Video Generation](<https://devfeed.tech/articles/geminicli-vision-extension-65969.md>)

Original publisher: [Read original article](<https://github.com/automateyournetwork/GeminiCLI_Vision_Extension>)

Published: 2025-09-06T12:00:00Z

Content type: tutorial

Language: en

Sources: [Automate Your Network](<https://devfeed.tech/sources/automate-your-network.md>)

Topics: [Extension](<https://devfeed.tech/topics/extension.md>), [webcam face tracking](<https://devfeed.tech/topics/webcam-face-tracking.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-image-generation](<https://devfeed.tech/tags/ai-image-generation.md>), [ai-video](<https://devfeed.tech/tags/ai-video.md>), [gemini-cli](<https://devfeed.tech/tags/gemini-cli.md>), [project](<https://devfeed.tech/tags/project.md>), [webcam](<https://devfeed.tech/tags/webcam.md>)

### AI overview

The Gemini CLI Vision Extension connects webcams, tethered phones, and static images to Gemini's multimodal tools. Its slash commands support camera discovery and capture, ASL interpretation, image generation with Gemini 2.5 Flash Image, and video generation with Veo.

### Source excerpt

An Extension for Gemini-CLI that enables Webcam access including single frame capture and American Sign Language (ASL) modes

## Gemini CLI slash commands for webcam access through Vision MCP

DevFeed: [Gemini CLI slash commands for webcam access through Vision MCP](<https://devfeed.tech/articles/geminicli-slash-vision-65965.md>)

Original publisher: [Read original article](<https://github.com/automateyournetwork/GeminiCLI_Slash_Vision>)

Published: 2025-09-04T12:00:00Z

Content type: tutorial

Language: en

Sources: [Automate Your Network](<https://devfeed.tech/sources/automate-your-network.md>)

Topics: [webcam face tracking](<https://devfeed.tech/topics/webcam-face-tracking.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>)

Tags: [gemini-cli](<https://devfeed.tech/tags/gemini-cli.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [project](<https://devfeed.tech/tags/project.md>), [webcam](<https://devfeed.tech/tags/webcam.md>)

### AI overview

The document describes custom Gemini CLI slash commands that use Vision MCP to enable webcam access, with a clone command and a Python MCP server configuration.

### Source excerpt

Custom Slash Commands that use Vision MCP to enable webcam access

## Converting Vertex-Colored Meshes to Textured Meshes

DevFeed: [Converting Vertex-Colored Meshes to Textured Meshes](<https://devfeed.tech/articles/converting-vertex-colored-meshes-to-textured-meshes-7551.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/vertex-colored-to-textured-mesh>)

Author: Dylan Ebert

Published: 2024-09-30T00:00:00Z

Content type: tutorial

Language: en

Sources: [Hugging Face](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [Library](<https://devfeed.tech/topics/library.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>), [NumPy](<https://devfeed.tech/topics/numpy.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [code](<https://devfeed.tech/tags/code.md>), [image-processing](<https://devfeed.tech/tags/image-processing.md>), [library](<https://devfeed.tech/tags/library.md>), [mesh](<https://devfeed.tech/tags/mesh.md>), [tutorial](<https://devfeed.tech/tags/tutorial.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

A tutorial explaining how to convert vertex-colored meshes into UV-mapped, textured meshes. It presents a quick solution using the InstantTexture library and a detailed implementation based on UV generation, vertex-color remapping, barycentric interpolation, and texture-buffer filling.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.

## Tensorflow on edge, or - Building a "smart" security camera with a Raspberry Pi

DevFeed: [Tensorflow on edge, or - Building a "smart" security camera with a Raspberry Pi](<https://devfeed.tech/articles/tensorflow-on-edge-or-building-a-smart-security-camera-with-a-raspberry-pi-41482.md>)

Original publisher: [Read original article](<https://chollinger.com/blog/2019/12/tensorflow-on-edge-or-building-a-smart-security-camera-with-a-raspberry-pi/>)

Author: Christian Hollinger

Published: 2019-12-09T00:00:00Z

Content type: tutorial

Language: en

Sources: [Christian Hollinger](<https://devfeed.tech/sources/christian-hollinger.md>)

Topics: [Tensorflow](<https://devfeed.tech/topics/tensorflow.md>), [object-detection](<https://devfeed.tech/topics/object-detection.md>), [Raspberry Pi](<https://devfeed.tech/topics/raspberry-pi.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [webcam](<https://devfeed.tech/topics/webcam.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>), [API](<https://devfeed.tech/topics/api.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [big-data](<https://devfeed.tech/tags/big-data.md>), [cameras](<https://devfeed.tech/tags/cameras.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [devices](<https://devfeed.tech/tags/devices.md>), [linux](<https://devfeed.tech/tags/linux.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [maker](<https://devfeed.tech/tags/maker.md>), [object-detection](<https://devfeed.tech/tags/object-detection.md>), [pi](<https://devfeed.tech/tags/pi.md>), [programming](<https://devfeed.tech/tags/programming.md>), [python](<https://devfeed.tech/tags/python.md>), [raspberry](<https://devfeed.tech/tags/raspberry.md>), [raspberry-pi](<https://devfeed.tech/tags/raspberry-pi.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [security](<https://devfeed.tech/tags/security.md>), [software](<https://devfeed.tech/tags/software.md>), [systems](<https://devfeed.tech/tags/systems.md>), [tensorflow](<https://devfeed.tech/tags/tensorflow.md>), [video](<https://devfeed.tech/tags/video.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

A tutorial describes building a Raspberry Pi 4 security camera that uses TensorFlow Object Detection and OpenCV to detect people in real time from video streams without motion sensors or cloud deployment.

### Source excerpt

The amount of time my outdoor cameras are being set off by light, wind, cars, or anything other than a human is insane. Overly cautious security cameras might be a feature, but an annoying one at that...

## How we wrote chicken egg counter on a Raspberry PI

DevFeed: [How we wrote chicken egg counter on a Raspberry PI](<https://devfeed.tech/articles/how-we-wrote-chicken-egg-counter-on-a-raspberry-pi-20853.md>)

Original publisher: [Read original article](<https://ivanursul.com/counting-eggs-in-opencv>)

Author: Ivan Ursul

Published: 2018-10-03T09:23:24Z

Content type: tutorial

Language: en

Sources: [Ivan Ursul](<https://devfeed.tech/sources/ivan-ursul.md>)

Topics: [Raspberry Pi](<https://devfeed.tech/topics/raspberry-pi.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>), [webcam](<https://devfeed.tech/topics/webcam.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [Database](<https://devfeed.tech/topics/database.md>)

Tags: [camera](<https://devfeed.tech/tags/camera.md>), [image-recognition](<https://devfeed.tech/tags/image-recognition.md>), [java](<https://devfeed.tech/tags/java.md>), [linux](<https://devfeed.tech/tags/linux.md>), [migrations](<https://devfeed.tech/tags/migrations.md>), [mongodb](<https://devfeed.tech/tags/mongodb.md>), [network](<https://devfeed.tech/tags/network.md>), [raspberry-pi](<https://devfeed.tech/tags/raspberry-pi.md>), [stream](<https://devfeed.tech/tags/stream.md>), [webcam](<https://devfeed.tech/tags/webcam.md>)

### AI overview

A project account describing the design of a Raspberry Pi application that uses a webcam and OpenCV-based image recognition to count chicken eggs on a factory conveyor and send the count to a database. It discusses tracking eggs across camera frames and preprocessing images to identify contours and ellipses.

### Source excerpt

How it started Besides my main work on Upwork I quite often pick different projets. So I found a project, where I had to write a program for recognizing chicken eggs on a factory stream line. Customer wanted to install the application on computer with web camera, put this camera at a top of stream line and the application had to calculate eggs and send them to the DB. He also wanted to run this program on a cheap computer. The quality of the network in the factory isn't stable, so the program had to be resilient to outstand the network issues. There was enough challenges for me, so I decided to participate on this project.

## Animated line drawings with OpenCV

DevFeed: [Animated line drawings with OpenCV](<https://devfeed.tech/articles/animated-line-drawings-with-opencv-21653.md>)

Original publisher: [Read original article](<https://www.windytan.com/2017/12/animated-line-drawings-with-opencv.html>)

Author: Oona Räisänen (noreply@blogger.com)

Published: 2017-12-30T12:15:00Z

Content type: tutorial

Language: en

Sources: [Oona Räisänen](<https://devfeed.tech/sources/oona-raisanen.md>)

Topics: [OpenCV](<https://devfeed.tech/topics/opencv.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [image effects](<https://devfeed.tech/topics/image-effects.md>), [generative art](<https://devfeed.tech/topics/generative-art.md>)

Tags: [animations](<https://devfeed.tech/tags/animations.md>), [art](<https://devfeed.tech/tags/art.md>), [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [cmake](<https://devfeed.tech/tags/cmake.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [drawing](<https://devfeed.tech/tags/drawing.md>), [graphics](<https://devfeed.tech/tags/graphics.md>), [image](<https://devfeed.tech/tags/image.md>), [matrix](<https://devfeed.tech/tags/matrix.md>), [music](<https://devfeed.tech/tags/music.md>), [opencv](<https://devfeed.tech/tags/opencv.md>), [pixel](<https://devfeed.tech/tags/pixel.md>), [plotting](<https://devfeed.tech/tags/plotting.md>), [programming](<https://devfeed.tech/tags/programming.md>)

### AI overview

The excerpt shows how to use OpenCV's C++ drawing tools to create pixel-level animations and save them as video. A minimal CMake project links OpenCV, and a zero-initialized 1920x1080 `cv::Mat` provides a black canvas. The example builds animated concentric rings with rotating spokes; antialiased subpixel positions are represented by multiplying coordinates by 8 and using a three-bit shift. To give the graphics a vector-display glow, the author applies Gaussian blur, noting that convolution is CPU-intensive and that blur calculation consumed much of the rendering time. The excerpt ends mid-discussion, so it does not establish the full rendering or video-writing workflow.

### Source excerpt

OpenCV is a pretty versatile C++ computer vision library. Because I use it every day it has also become my go-to tool for creating simple animations at pixel level, for fun, and saving them as video files. This is not one of its core functions but happens to be possible using its GUI drawing tools. Below we'll take a look at some video art I wrote for a music project. It goes a bit further than just line drawings but the rest is pretty much just flavouring. As you'll see, creating images in OpenCV has a lot in common with how you would work with layers and filters in an image editor like GIMP or Photoshop. Setting it up It doesn't take a lot of boilerplate to initialize an OpenCV project. Here's my minimal CMakeLists.txt: cmake_minimum_required (VERSION 2.8) project (marmalade) find_package (OpenCV REQUIRED) add_executable (marmalade marmalade.cc) target_link_libraries (marmalade ${OpenCV_LIBS}) I also like to set compiler flags to enforce the C++11 standard, but this is not necessary. In the main .cc file I have: #include "opencv2/imgproc/imgproc.hpp" #include "opencv2/highgui/highgui.hpp" Now you can build the project by just typing cmake . && make in the terminal. Basic shapes First, we'll need an empty canvas. It will be a matrix (cv::Mat) with three unsigned char channels for RGB at Full HD resolution: const cv::Size video_size(1920, 1080); cv::Mat mat_frame = cv::Mat::zeros(video_size, CV_8UC3); This will also initialize everything to zero, i.e. black. Now we can draw our graphics! I had an initial idea of an endless cascade of concentric rings each rotating at a different speed. There might be color and brightness variations as well but otherwise it would stay static the whole time. You can't see a circle's rotation around its center, so we'll add some features to them as well, maybe some kind of bars or spokes. A simplified render method for a ring would look like this: void Ring::RenderTo(cv::Mat& mat_output) const { cv::circle(mat_output, 8 * center_, 8 *

## OMSCS CS6476 (Computer Vision) Review and Tips

DevFeed: [OMSCS CS6476 (Computer Vision) Review and Tips](<https://devfeed.tech/articles/omscs-cs6476-computer-vision-review-and-tips-46505.md>)

Original publisher: [Read original article](<https://eugeneyan.com//writing/omscs-cs6476-computer-vision/>)

Author: Eugene Yan

Published: 2017-05-15T00:00:00Z

Content type: opinion

Language: en

Sources: [Eugene Yan](<https://devfeed.tech/sources/eugene-yan.md>)

Topics: [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [NumPy](<https://devfeed.tech/topics/numpy.md>), [OpenCV](<https://devfeed.tech/topics/opencv.md>), [Python](<https://devfeed.tech/topics/python.md>), [Algorithms](<https://devfeed.tech/topics/algorithms.md>)

Tags: [code](<https://devfeed.tech/tags/code.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [deeplearning](<https://devfeed.tech/tags/deeplearning.md>), [learning](<https://devfeed.tech/tags/learning.md>), [omscs](<https://devfeed.tech/tags/omscs.md>), [python](<https://devfeed.tech/tags/python.md>), [review](<https://devfeed.tech/tags/review.md>), [tips](<https://devfeed.tech/tags/tips.md>)

### AI overview

A review of Georgia Tech OMSCS CS6476 Computer Vision, covering its mathematical foundations, computer vision algorithms, NumPy and OpenCV exercises, and assignments involving implementation, experimentation, and parameter tuning.

### Source excerpt

OMSCS CS6476 Computer Vision - Performing computer vision tasks with ONLY numpy.