DragonFive/opencv_TLD
TLD：tracking-learning-detection 跟踪算法
This project helps operations engineers or anyone working with video footage to automatically track a specific, unknown object over long periods. You provide an initial video frame with a bounding box around the object of interest, and the system outputs a continuous bounding box around that object, even if it briefly disappears or changes appearance due to lighting or occlusion. This is ideal for tasks like security monitoring, sports analysis, or autonomous vehicle perception where consistent object tracking is crucial.
No commits in the last 6 months.
Use this if you need to reliably track a designated, arbitrary object within a video stream for extended durations, even when it undergoes visual changes or temporary occlusions.
Not ideal if you need to identify or categorize specific types of objects (like 'cars' or 'people') rather than just tracking a singular, pre-defined target.
Stars
49
Forks
27
Language
C++
License
GPL-3.0
Category
Last pushed
Mar 10, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/DragonFive/opencv_TLD"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
IBM/MAX-Object-Detector
Localize and identify multiple objects in a single image.
LSH9832/edgeyolo
an edge-real-time anchor-free object detector with decent performance
stephanecharette/DarkMark
Marking up images for use with Darknet.
amdegroot/ssd.pytorch
A PyTorch Implementation of Single Shot MultiBox Detector
aditya-vora/FCHD-Fully-Convolutional-Head-Detector
Code for FCHD - A fast and accurate head detector