bertinetto/siamese-fc
Arbitrary object tracking at 50-100 FPS with Fully Convolutional Siamese networks.
This project helps you accurately track a specific object across video frames, even if it moves or changes slightly. You input a video sequence and a selected target object, and the system outputs the precise location of that object in subsequent frames. It's designed for researchers or practitioners working with video analysis who need to follow dynamic elements.
629 stars. No commits in the last 6 months.
Use this if you need to identify and follow a particular item or subject in real-time video, for tasks like surveillance or behavioral analysis.
Not ideal if you are looking for a completely out-of-the-box solution that doesn't require familiarity with Matlab or deep learning concepts.
Stars
629
Forks
219
Language
MATLAB
License
MIT
Category
Last pushed
May 16, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/bertinetto/siamese-fc"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
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)