open-mmlab / mmtracking
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
☆3,642Updated last year
Alternatives and similar repositories for mmtracking:
Users that are interested in mmtracking are comparing it to the libraries listed below
- [ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box☆5,050Updated 8 months ago
- Simultaneous object detection and tracking using center points.☆2,404Updated 8 months ago
- [IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking☆4,071Updated last year
- Scaled-YOLOv4: Scaling Cross Stage Partial Network☆2,027Updated 3 months ago
- Object detection, 3D detection, and pose estimation using center point detection:☆7,356Updated last year
- NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone…☆5,853Updated 6 months ago
- 🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥☆3,126Updated last year
- PyTorch ,ONNX and TensorRT implementation of YOLOv4☆4,503Updated 8 months ago
- The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.☆1,291Updated 2 years ago
- Joint Detection and Embedding for fast multi-object tracking☆2,407Updated 3 years ago
- YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documenta…☆9,637Updated 3 months ago
- MOT using deepsort and yolov3 with pytorch☆2,871Updated 7 months ago
- BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models☆6,950Updated this week
- PyTorch implementation of YOLOv4