# real-time face tracking

A computer-vision technique for detecting faces and facial features in video and tracking detected faces across successive frames.

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

## FVScore: Specification-Driven Neuro-Symbolic Video Evaluation

DevFeed: [FVScore: Specification-Driven Neuro-Symbolic Video Evaluation](<https://devfeed.tech/articles/fvscore-specification-driven-neuro-symbolic-video-evaluation-140065.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22673>)

Author: Do Xuan Long, Long T. Le, Yiwen Song, Min-Yen Kan, Tomas Pfister, Yale Song

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

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

Topics: [real-time face tracking](<https://devfeed.tech/topics/real-time-face-tracking.md>), [Interactive AI Systems](<https://devfeed.tech/topics/interactive-ai-systems.md>), [open-llm-leaderboard](<https://devfeed.tech/topics/open-llm-leaderboard.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [correlation](<https://devfeed.tech/tags/correlation.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [grounded](<https://devfeed.tech/tags/grounded.md>), [logic](<https://devfeed.tech/tags/logic.md>), [operators](<https://devfeed.tech/tags/operators.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [report](<https://devfeed.tech/tags/report.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

FVSCORE evaluates generated videos by translating prompt requirements and implicit physical, temporal, and cross-modal constraints into propositions, grounding them with specialized perceptual tools, and assessing confidence traces with soft temporal operators inspired by Linear Temporal Logic. Significance-Aware Calibration filters for perceptually significant violations before producing reports tied to timestamps and evidence. The abstract reports stronger correlation with human judgments than holistic and agent-based evaluators across public and complex multi-event benchmarks, alongside interpretable feedback; it provides no specific performance figures.

### Source excerpt

arXiv:2611.22673v1 Announce Type: cross Abstract: We introduce Faithfulness Video Score (FVSCORE), a neuro-symbolic framework for specification-driven video generation evaluation. Existing evaluators rely on holistic MLLM judgments or vision-language metrics, yet aligning their scores with human judgments and tracing them to specific temporal violations remain open challenges. FVSCORE addresses these limitations by compiling each video into explicit propositions capturing prompt requirements and implicit propositions capturing unstated physical, temporal, and cross-modal constraints. It grounds each proposition using specialized perceptual tools and evaluates the resulting confidence traces with soft temporal operators inspired by Linear Temporal Logic. A Significance-Aware Calibration step then aligns verification with human perception by retaining only perceptually significant violations before producing a timestamp- and evidence-grounded report. We conduct extensive experiments across public and complex multi-event benchmarks with the strongest video models to date, demonstrating that FVSCORE outperforms holistic and agent-based evaluators in human correlation while providing highly accurate and interpretable feedback.

## Big Brains, Tiny Board: Pupavision, an Agentic Physical AI Instrument for Monitoring Drosophila Pupariation and Lifecycle Transitions

DevFeed: [Big Brains, Tiny Board: Pupavision, an Agentic Physical AI Instrument for Monitoring Drosophila Pupariation and Lifecycle Transitions](<https://devfeed.tech/articles/big-brains-tiny-board-pupavision-an-agentic-physical-ai-instrument-for-monitoring-drosophila-pupariation-and-lifecycle-transitions-139968.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22136>)

Author: Joel Sadler, Daniel Graham, Melanie Worley

Published: 2026-11-18T05:00:00Z

Content type: news

Language: en

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

Topics: [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [recording](<https://devfeed.tech/topics/recording.md>), [real-time face tracking](<https://devfeed.tech/topics/real-time-face-tracking.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [biology](<https://devfeed.tech/tags/biology.md>), [blueprint](<https://devfeed.tech/tags/blueprint.md>), [board](<https://devfeed.tech/tags/board.md>), [camera](<https://devfeed.tech/tags/camera.md>), [capture](<https://devfeed.tech/tags/capture.md>), [case-study](<https://devfeed.tech/tags/case-study.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [data](<https://devfeed.tech/tags/data.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [design](<https://devfeed.tech/tags/design.md>), [lifecycle](<https://devfeed.tech/tags/lifecycle.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [physical-ai](<https://devfeed.tech/tags/physical-ai.md>), [tiny](<https://devfeed.tech/tags/tiny.md>)

### AI overview

Pupavision separates reliable image capture from agent assistance: a deterministic service records one frame every ten minutes, while a coding agent running on a single-board Linux computer helps capture images, repairs code errors, and checks the experiment daily. The agent's model operates in the cloud, but its harness runs on the device; if recording stops, the researcher receives a mobile alert. The roughly $45-$75 instrument completed a 26-day fly-incubator pilot with about 3,580 frames, including 11 days when the agent was logged out and capture continued. A 51-hour outage informed the layered design. Researchers then traced selected pupae backward from a late reference image to produce per-vial pupariation curves. This is an early pilot: assay accuracy still needs validation against expert-labeled data, and real-time computer vision is future work.

### Source excerpt

arXiv:2611.22136v1 Announce Type: new Abstract: Many biology experiments are limited by the availability and ease of use of instruments that monitor and record them. For example, the timing of pupariation in the fruit fly Drosophila melanogaster, a widely used model organism, can provide biologically relevant information about growth regulation and is often recorded manually. Here, we present Pupavision, a small physical AI instrument built from a single-board Linux computer and a day/night camera for roughly 45 to 75 US dollars in parts. The key idea is that a frontier coding agent runs its agentic harness directly on the tiny board. The model thinks in the cloud, but the agent works on the device. The agent assists image capture, writes code to repair errors, and checks the experiment every day to keep raw data capture reliable. If recording stops, the researcher gets a ping on their mobile phone. A simple deterministic capture service records one image every ten minutes and never depends on the agent. We report a 26-day pilot in a fly incubator (about 3,580 frames), including eleven days in which the agent was logged out and capture continued, and a 51-hour outage whose cause led to the layered design. A researcher-in-the-loop workflow then produces per-vial pupariation curves by tracing selected pupae backward in time from a late reference frame. Future work will validate the assay for lifecycle tracking accuracy against expert-labeled data and expand real-time computer vision analysis. Pupavision offers a blueprint for do-it-yourself agentic instruments that put frontier intelligence on a tiny board, with deterministic code underneath. We present this as an early case study from a pilot lab deployment and contribute lessons learned toward a future where scientific domain experts are empowered by DIY agentic hardware.

## CoraLive: Ultra-Low-Power Underwater Vision for Long-term Coral Reef Monitoring

DevFeed: [CoraLive: Ultra-Low-Power Underwater Vision for Long-term Coral Reef Monitoring](<https://devfeed.tech/articles/coralive-ultra-low-power-underwater-vision-for-long-term-coral-reef-monitoring-107620.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.39472>)

Author: Sitong Shen, Chenshu Wu

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [recording](<https://devfeed.tech/topics/recording.md>), [real-time face tracking](<https://devfeed.tech/topics/real-time-face-tracking.md>), [VENTUNO Q](<https://devfeed.tech/topics/ventuno-q.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [battery](<https://devfeed.tech/tags/battery.md>), [board](<https://devfeed.tech/tags/board.md>), [camera](<https://devfeed.tech/tags/camera.md>), [co-design](<https://devfeed.tech/tags/co-design.md>), [content](<https://devfeed.tech/tags/content.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [coral](<https://devfeed.tech/tags/coral.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [custom](<https://devfeed.tech/tags/custom.md>), [daily](<https://devfeed.tech/tags/daily.md>), [data](<https://devfeed.tech/tags/data.md>), [days](<https://devfeed.tech/tags/days.md>), [low-power](<https://devfeed.tech/tags/low-power.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [power](<https://devfeed.tech/tags/power.md>), [reef](<https://devfeed.tech/tags/reef.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

CoraLive targets long-term coral reef monitoring by shifting reconstruction and segmentation from an underwater camera to offline shore-side processing. Its dual-rate sensing pairs frequent low-resolution frames with sparse high-fidelity samples, while content-adaptive updates store compact task-specific data instead of raw video. In a custom STM32U575-based dual-camera prototype, this approach reduced daily storage by 4.51x and average power by 7.78x versus raw recording, extending reported battery life from 20.4 to 159.5 days while retaining high-accuracy segmentation and reconstruction. The abstract also reports validation in a real-world underwater deployment.

### Source excerpt

arXiv:2610.39472v1 Announce Type: new Abstract: Effective coral reef protection and restoration demands continuous, long-term underwater monitoring. However, current solutions largely rely on fragmented, manual labor and costly infrastructure, or are severely limited by constrained battery lifespans. In this paper, we present CoraLive, an ultra-low-power underwater camera system for long-term, continuous coral reef monitoring. CoraLive presents a decoupled underwater-shore co-design that minimizes on-board computation and storage, offloading heavy reconstruction and segmentation tasks to offline shore-side processing. To achieve this, CoraLive introduces a dual-rate sensing scheme combining frequent low-resolution frames with sparse high-fidelity samples and a content-adaptive update mechanism that extracts and stores only compact, task-specific data, eliminating the need to save raw video frames. We implement CoraLive on a custom STM32U575-based dual-camera prototype with device-level computation and storage optimization. Compared with raw recording, CoraLive reduces daily storage by $4.51\times$ and average power by $7.78\times$, extending battery lifetime from 20.4 to 159.5~days while retaining high-accuracy segmentation and reconstruction. Further validated in a real-world underwater deployment, we envision CoraLive as a pioneering step for ubiquitous long-term coral reef underwater monitoring.

## Multi-Ratio Video Resizing for Mobile Feed and Marketing

DevFeed: [Multi-Ratio Video Resizing for Mobile Feed and Marketing](<https://devfeed.tech/articles/multi-ratio-video-resizing-for-mobile-feed-and-marketing-101176.md>)

Original publisher: [Read original article](<https://netflixtechblog.com/multi-ratio-video-resizing-for-mobile-feed-and-marketing-2e6b42810f49?source=rss----2615bd06b42e---4>)

Author: Netflix Technology Blog

Published: 2026-10-26T16:01:02Z

Content type: article

Language: en

Sources: [Netflix](<https://devfeed.tech/sources/netflix-techblog-medium.md>)

Topics: [Image](<https://devfeed.tech/topics/image.md>), [Video Analytics](<https://devfeed.tech/topics/video-analytics.md>), [real-time face tracking](<https://devfeed.tech/topics/real-time-face-tracking.md>), [Tool](<https://devfeed.tech/topics/tool.md>)

Tags: [app](<https://devfeed.tech/tags/app.md>), [automated](<https://devfeed.tech/tags/automated.md>), [camera](<https://devfeed.tech/tags/camera.md>), [catalog](<https://devfeed.tech/tags/catalog.md>), [content](<https://devfeed.tech/tags/content.md>), [crop](<https://devfeed.tech/tags/crop.md>), [device](<https://devfeed.tech/tags/device.md>), [external](<https://devfeed.tech/tags/external.md>), [filmmaking](<https://devfeed.tech/tags/filmmaking.md>), [formats](<https://devfeed.tech/tags/formats.md>), [generate](<https://devfeed.tech/tags/generate.md>), [marketing](<https://devfeed.tech/tags/marketing.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [production](<https://devfeed.tech/tags/production.md>), [quality](<https://devfeed.tech/tags/quality.md>), [ratio](<https://devfeed.tech/tags/ratio.md>), [scale](<https://devfeed.tech/tags/scale.md>), [simple](<https://devfeed.tech/tags/simple.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

Netflix describes an automated video reframing pipeline for creating 9:16, 4:5, and 1:1 crops from 16:9 footage in one pass. It detects shots and can split conversations into speaker-focused sub-shots using face detection and LipFlap; it then ranks focus regions using faces, visual saliency, active-speaker status, relative size, and shot-level understanding. To avoid shaky frame-by-frame tracking, it holds a static crop for small movements and smooths a dynamic tracking window when focus moves significantly. Editors can review and adjust crops in the internal Clips tool, or export XML framing parameters to external editors such as Adobe Premiere. Netflix reports better performance than Premiere's Auto Reframe on a curated internal evaluation set; no metrics are provided in the supplied text.

### Source excerpt

Serdar Cellat, Yuchen Xie, Bernadette Marcu, Blaid Burgess, Cody Jarrett, Carlos Pereira, Qing Shi, Samuel Carvajal, Manuel Pamplona, Dorothy Jung, Feiko Ritsema, Benjamin Klein, Alex Woo, Eugene Lok, Anna Pulido, Rebecka Swe, Sanford Holsapple, Ranjith Kumar Shetty IntroductionClips in the Netflix mobile app. At Netflix, a crucial part of our mission is ensuring our content looks stunning on any device. Vertical formats are increasingly important for Netflix, as we have 1.2B followers across our social media accounts, and have recently rolled out Clips, our vertical video feed in the Netflix mobile app. Traditionally, creating vertical assets meant editors and producers manually reframed horizontal videos in editing tools, a process that doesn't scale as our catalog and use cases grow. To support both our in-app feed and external marketing campaigns at scale, we built an automated multi-ratio video cropping system, tightly integrated into our internal production tools, that can generate high-quality vertical and other aspect-ratio variants with minimal manual effort. Our Video Resizing Approach Converting cinematic 16:9 footage into mobile-friendly aspect ratios takes more than a simple center crop. Filmmaking often involves dynamic character blocking and complex camera movement. We need an intelligent "virtual camera" that can follow the key action, respond to how each scene is composed, and produce crops that feel as intentional as the original shot. We address this challenge by framing video resizing as a tracking and temporal optimization problem. Our pipeline processes each asset in three main stages, designed to produce 9:16, 4:5, and 1:1 crops in a single pass, without incurring additional computational overhead. An overview of the three-stage process converting horizontal footage into mobile aspect ratios.Shot Detection and Splitting First, we segment the video into atomic shots using a neural-network-based shot boundary detector. In many cases, shots conta

## SORT vs DeepSORT vs ByteTrack vs OC-SORT: Which Tracking Algorithm Should You Use?

DevFeed: [SORT vs DeepSORT vs ByteTrack vs OC-SORT: Which Tracking Algorithm Should You Use?](<https://devfeed.tech/articles/sort-vs-deepsort-vs-bytetrack-vs-oc-sort-which-tracking-algorithm-should-you-use-90275.md>)

Original publisher: [Read original article](<https://roboflow.com/blog/sort-vs-deepsort-vs-bytetrack-vs-oc-sort>)

Author: Dikshant Shah

Published: 2026-10-19T18:10:57Z

Content type: tutorial

Language: en

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

Topics: [real-time face tracking](<https://devfeed.tech/topics/real-time-face-tracking.md>), [distributed algorithm](<https://devfeed.tech/topics/distributed-algorithm.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-assistants](<https://devfeed.tech/tags/ai-coding-assistants.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [api](<https://devfeed.tech/tags/api.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [object-tracking](<https://devfeed.tech/tags/object-tracking.md>), [speed](<https://devfeed.tech/tags/speed.md>), [tracking](<https://devfeed.tech/tags/tracking.md>)

### AI overview

This tutorial compares SORT, DeepSORT, ByteTrack, and OC-SORT for multi-object tracking in computer vision. It explains their tracking approaches and tradeoffs, then describes how to compare them in Roboflow Workflows and deploy a selected pipeline to cloud or local devices.

### Source excerpt

SORT vs DeepSORT vs ByteTrack vs OC-SORT: pick the right tracker for occlusion, crowds, or speed, then test trackers on your video in Roboflow.

## Elorian AI's Glimpse now available on AI Gateway

DevFeed: [Elorian AI's Glimpse now available on AI Gateway](<https://devfeed.tech/articles/elorian-ai-s-glimpse-now-available-on-ai-gateway-89222.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/elorian-ai-glimpse-now-available-on-ai-gateway>)

Author: Zachary Chen

Published: 2026-10-16T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [real-time face tracking](<https://devfeed.tech/topics/real-time-face-tracking.md>), [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [api](<https://devfeed.tech/tags/api.md>), [bring-your-own-key](<https://devfeed.tech/tags/bring-your-own-key.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cli](<https://devfeed.tech/tags/cli.md>), [codex](<https://devfeed.tech/tags/codex.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [data-retention](<https://devfeed.tech/tags/data-retention.md>), [failover](<https://devfeed.tech/tags/failover.md>), [optimizations](<https://devfeed.tech/tags/optimizations.md>), [performance](<https://devfeed.tech/tags/performance.md>), [retries](<https://devfeed.tech/tags/retries.md>), [train](<https://devfeed.tech/tags/train.md>), [vercel](<https://devfeed.tech/tags/vercel.md>)

### AI overview

Elorian's Glimpse visual reasoning model is now available through Vercel AI Gateway. It accepts images and video, can revisit visual evidence to track objects and interpret motion, and supports applications such as chart analysis, video captioning, counting, and robotics data annotation. The release also shows how to call the model with the AI SDK and describes gateway features including usage and cost tracking, retries, failover, reporting, and API key budgets.

### Source excerpt

Glimpse from Elorian is now available on AI Gateway. The visual reasoning model accepts images and video to follow objects through motion, interpret spatial relationships, and connect an action to its physical consequences. Glimpse can return to visual evidence as it works: zooming into a detail, revisiting a short interval of video, or tracking the same feature across frames. This allows the model to support use cases like scientific chart analysis, video captioning, visual counting, and robotics data annotation. Some examples include checking a train's motion to determine whether it is slowing down, keeping objects distinct through camera movement, and labeling completed actions in robot footage. Use elorian/glimpse as the model name: With AI SDK 7, you can send a video as a file part. Replace the placeholder URL with a public or signed HTTPS URL for your video: To configure AI Gateway in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Try Glimpse in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. Read more

## Surveillance Company Tells Cops It Wants to Add Facial Recognition to Flock Cameras

DevFeed: [Surveillance Company Tells Cops It Wants to Add Facial Recognition to Flock Cameras](<https://devfeed.tech/articles/surveillance-company-tells-cops-it-wants-to-add-facial-recognition-to-flock-cameras-64538.md>)

Original publisher: [Read original article](<https://yro.slashdot.org/story/26/10/03/0545254/surveillance-company-tells-cops-it-wants-to-add-facial-recognition-to-flock-cameras>)

Author: EditorDavid

Published: 2026-10-04T00:21:00Z

Content type: news

Language: en

Sources: [Slashdot](<https://devfeed.tech/sources/slashdot.md>)

Topics: [Facial recognition](<https://devfeed.tech/topics/facial-recognition.md>), [real-time face tracking](<https://devfeed.tech/topics/real-time-face-tracking.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [facial-recognition](<https://devfeed.tech/tags/facial-recognition.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [security](<https://devfeed.tech/tags/security.md>), [surveillance](<https://devfeed.tech/tags/surveillance.md>)

### AI overview

VIDIZMO promotes adding facial recognition and other analysis to footage from Flock cameras, although it has not yet built the advertised export integration or begun processing that footage. Its CEO says the company would like to integrate with Flock, and VIDIZMO also describes demographic analysis for marketing based on people's race or age.

### Source excerpt

404 Media reports: "We will not add facial recognition to our devices," Flock CEO Garrett Langley said in a recent video. But other, third-party companies are telling cops that they are willing to add facial recognition to data gathered by Flock cameras in order to "close that gap." A company called VIDIZMO is advertising the capability to export footage from FlockOS to its own platforms that do facial recognition, behavior prediction, and racial and gender analysis on live camera feeds. VIDIZMO is a several decades-old video analysis and database company that has started offering facial recognition technology to cops within the last six months. In a May email to Johnson City, Tennessee, deputy police chief Michael Adams, a salesperson from VIDIZMO wrote that the company's product could do facial recognition on both Flock and Axon [body-worn camera] data in "one searchable platform...." VIDIZMO's CEO, Nadeem Khan, told 404 Media on a video call that the company has not yet started running facial recognition tech on footage from Flock cameras, and that it has not actually built the specific tool that would export data from Flock's system to its own platform (though the company advertises this capability online, and the company already sells other facial recognition products). But Khan said VIDIZMO "would love to do the integration," and that he believes facial recognition "is the way the world is going, the way the world will have to be," and that he thinks Flock should offer the capability itself in a way that "balances privacy, security, and the freedom that we enjoy in this country." The article notes that VIDIZMO says on its website, "You can identify individuals from seven races: White, Black, Indian, East Asian, Southeast Asian, Middle Eastern, and Latino Hispanic." VIDIZMO adds that stores or cities can also then do "demographic analysis" for marketing purposes by determining the races or ages of people showing up.... Read more of this story at Slashdot.

## Building an AI-powered multimodal compliance monitor: From training to tracking to chat

DevFeed: [Building an AI-powered multimodal compliance monitor: From training to tracking to chat](<https://devfeed.tech/articles/building-an-ai-powered-multimodal-compliance-monitor-from-training-to-tracking-to-chat-62446.md>)

Original publisher: [Read original article](<https://www.redhat.com/en/blog/building-ai-powered-multimodal-compliance-monitor-training-tracking-chat>)

Author: Ganesh Murthy

Published: 2026-09-30T00:00:00Z

Content type: tutorial

Language: en

Sources: [Red Hat Blog](<https://devfeed.tech/sources/red-hat-blog.md>)

Topics: [ai security](<https://devfeed.tech/topics/ai-security.md>), [real-time face tracking](<https://devfeed.tech/topics/real-time-face-tracking.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Advanced AI workflows](<https://devfeed.tech/topics/advanced-ai-workflows.md>), [ML model versioning](<https://devfeed.tech/topics/ml-model-versioning.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [database](<https://devfeed.tech/tags/database.md>), [database-schema](<https://devfeed.tech/tags/database-schema.md>), [labeling](<https://devfeed.tech/tags/labeling.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [tracking](<https://devfeed.tech/tags/tracking.md>)

### AI overview

This Red Hat OpenShift AI quickstart walks through an AI monitoring application that combines computer vision and large language models. It covers training custom object detection models, real-time tracking of people and equipment, storing observations in a flexible JSONB database, and querying monitoring data through natural-language chat and dashboards.

### Source excerpt

Organizations face a persistent challenge maintaining workplace safety, security, asset tracking, and operational compliance across facilities with multiple video feeds. Manual monitoring is resource-intensive, inherently reactive, and often misses critical events or patterns indicating safety risks. A single safety officer watching a bank of screens can't reliably track whether every worker on a busy factory floor is wearing their hardhat, vest, and mask--let alone recall compliance trends from last week.This project tackles that problem with a complete, end-to-end AI monitoring system combi

## Gaze Detection and Gaze Tracking Explained

DevFeed: [Gaze Detection and Gaze Tracking Explained](<https://devfeed.tech/articles/gaze-detection-and-gaze-tracking-explained-64087.md>)

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

Author: Dikshant Shah

Published: 2026-09-08T21:36:35Z

Content type: tutorial

Language: en

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

Topics: [real-time face tracking](<https://devfeed.tech/topics/real-time-face-tracking.md>), [webcam face tracking](<https://devfeed.tech/topics/webcam-face-tracking.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>), [human computer interaction](<https://devfeed.tech/topics/human-computer-interaction.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [detection](<https://devfeed.tech/tags/detection.md>), [tracking](<https://devfeed.tech/tags/tracking.md>)

### AI overview

This tutorial explains gaze detection and gaze tracking, then walks through a video pipeline that combines face detection, face tracking, detection stabilization, and L2CS-Net gaze estimation. It uses Roboflow Workflows and Inference, with Python code to process video frames, smooth gaze predictions, and generate a visualization.

### Source excerpt

Gaze tracking explained, plus a working pipeline: detect faces with SAM 3, track them with OC-SORT, and estimate gaze with L2CS-Net in Roboflow.

## Gaze Detection and Gaze Tracking Explained

DevFeed: [Gaze Detection and Gaze Tracking Explained](<https://devfeed.tech/articles/gaze-detection-and-gaze-tracking-explained-49810.md>)

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

Author: Dikshant Shah

Published: 2026-09-08T21:36:35Z

Content type: tutorial

Language: en

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

Topics: [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [human computer interaction](<https://devfeed.tech/topics/human-computer-interaction.md>), [real-time face tracking](<https://devfeed.tech/topics/real-time-face-tracking.md>), [facial landmarks](<https://devfeed.tech/topics/facial-landmarks.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [cameras](<https://devfeed.tech/tags/cameras.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [detection](<https://devfeed.tech/tags/detection.md>), [facial-landmarks](<https://devfeed.tech/tags/facial-landmarks.md>), [guide](<https://devfeed.tech/tags/guide.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [inference](<https://devfeed.tech/tags/inference.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [tracking](<https://devfeed.tech/tags/tracking.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

This guide explains gaze detection and gaze tracking with computer vision, including how systems use eye position, iris orientation, head pose, facial landmarks, and eye movement to estimate visual attention. It also describes a gaze-tracking pipeline built with Roboflow tools.

### Source excerpt

Gaze tracking explained, plus a working pipeline: detect faces with SAM 3, track them with OC-SORT, and estimate gaze with L2CS-Net in Roboflow.

## How to Build an AI Basketball Shot Evaluator

DevFeed: [How to Build an AI Basketball Shot Evaluator](<https://devfeed.tech/articles/how-to-build-an-ai-basketball-shot-evaluator-64096.md>)

Original publisher: [Read original article](<https://roboflow.com/blog/how-to-build-an-ai-basketball-shot-evaluator>)

Author: Aarnav Shah

Published: 2026-08-14T11:38:13Z

Content type: tutorial

Language: en

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

Topics: [real-time face tracking](<https://devfeed.tech/topics/real-time-face-tracking.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

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

### AI overview

A tutorial builds a local basketball shot tracker using an RF-DETR object detector and keypoint model to record shot outcomes and mechanics. It explains rim-based camera calibration, shot-release detection, handling occlusion with ball physics, and a local web interface for reviewing results.

### Source excerpt

Build a local basketball shot tracker using an RF-DETR detector and zero-shot keypoint tracking. Learn how to calibrate distance from the rim, detect shot release with pose data, handle net occlusions using physics, and render live mechanics overlays onto your video.

## Engineering Real-Time Animated Profile Pictures

DevFeed: [Engineering Real-Time Animated Profile Pictures](<https://devfeed.tech/articles/engineering-real-time-animated-profile-pictures-38367.md>)

Original publisher: [Read original article](<https://cyrilmottier.com/posts/2025/engineering-real-time-animated-profile-pictures/>)

Author: Cyril Mottier

Published: 2025-02-16T13:21:47Z

Content type: article

Language: en

Sources: [Cyril Mottier Blog](<https://devfeed.tech/sources/cyril-mottier-blog.md>)

Topics: [real-time face tracking](<https://devfeed.tech/topics/real-time-face-tracking.md>), [Playback](<https://devfeed.tech/topics/playback.md>), [data](<https://devfeed.tech/topics/data.md>), [Cache](<https://devfeed.tech/topics/cache.md>)

Tags: [article](<https://devfeed.tech/tags/article.md>), [caching](<https://devfeed.tech/tags/caching.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [playback](<https://devfeed.tech/tags/playback.md>), [real-time](<https://devfeed.tech/tags/real-time.md>)

### AI overview

This engineering article explains how amo apps implement transparent animated profile pictures called "Your Face." It covers recording with real-time face detection and selfie fragmentation, encoding the original video and mask in H.265, and queue-based playback that applies the mask and cycles decoded frames for back-and-forth real-time animation. The system has run on Android and iOS for over a year.

### Source excerpt

This article was initially published as a thread of posts on X. For the sake of readability and long-term availability, it is now available here as a single-page article. Post 1 In the amo apps, profile pictures are done a bit differently. You record "Your Face", a transparent animated boomerang-like cutout. It feels more personal. You see your friends come to life on-screen, not through overly curated or filtered camera roll photos.