mpatacchiola/deepgaze

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1880 stars · 480 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Deepgaze is a Python computer vision library for human-computer interaction built on OpenCV and TensorFlow. It provides CNN-based head pose and gaze direction estimation, face detection, skin/color detection, motion detection and tracking, and saliency map generation.

Use cases

• estimate head pose from camera images with a CNN
• detect where a person is looking (gaze direction estimation)
• detect faces in video frames
• detect skin regions in images via histogram backprojection
• detect and track motion in video with a particle filter
• compute saliency maps to find visually salient regions
• classify images using histogram intersection

When to choose

• you need head pose or gaze estimation in Python with OpenCV/TensorFlow
• you are building human-computer interaction or robotics attention systems
• you want classic CV techniques like skin detection, motion detection, and particle-filter tracking in one library

When to avoid

• you need actively developed state-of-the-art models or GPU-optimized inference
• you need real-time performance on embedded hardware
• you are not working in Python or cannot use the pinned OpenCV/TensorFlow versions

Facets

library · maturity maintenance

computer-vision image-processing machine-learning deep-learning computer-vision machine-learning robotics python cross-platform head-pose-estimation gaze-estimation face-detection skin-detection motion-detection motion-tracking saliency-map particle-filter opencv tensorflow cnn human-computer-interaction

Member repositories

For agents

markdown · JSON · MCP: product_card(name="mpatacchiola/deepgaze")