basilevh/tcow
Tracking through Containers and Occluders in the Wild (CVPR 2023) - Official Implementation
This project helps video analysts and computer vision researchers accurately track specific objects in video footage, even when they are temporarily hidden or move behind other objects like containers. You provide video clips and an initial mask highlighting the object to track, and it outputs precise segmentations of that object across all frames. This is ideal for those studying object motion, analyzing crowded scenes, or evaluating the effectiveness of object tracking systems.
No commits in the last 6 months.
Use this if you need to reliably follow objects through complex video scenes where occlusions (like objects moving behind a box or another person) are common.
Not ideal if you primarily need to detect objects or classify actions, rather than tracking specific instances of objects across frames.
Stars
40
Forks
4
Language
Python
License
MIT
Category
Last pushed
Jun 07, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/basilevh/tcow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
roboflow/rf-detr
[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture...
stereolabs/zed-sdk
⚡️The spatial perception framework for rapidly building smart robots and spaces
mikel-brostrom/boxmot
BoxMOT: Pluggable SOTA multi-object tracking modules with support for axis-aligned and oriented...
RizwanMunawar/yolov7-object-tracking
YOLOv7 Object Tracking Using PyTorch, OpenCV and Sort Tracking
google-deepmind/tapnet
Tracking Any Point (TAP)