UniAD
ByteTrack
| UniAD | ByteTrack | |
|---|---|---|
| 1 | 6 | |
| 2,879 | 4,281 | |
| 5.8% | - | |
| 7.1 | 0.0 | |
| about 2 months ago | 10 days ago | |
| Python | Python | |
| Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
UniAD
-
Goal-oriented Autonomous Driving (Open Source!)
Code: https://github.com/OpenDriveLab/UniAD (to be released soon)
ByteTrack
-
Multi Object Tracking from moving camera
Thanks for the suggestion! Unfortunately, unitrack code doesn't support custom data evaluation. I've found Bytetrack to be useful for my current task.
- Object tracking in videos?
- ByteTrack: Multi-Object Tracking by Associating Every Detection Box
-
ByteDance Proposes An Impressive Multi-Object Tracking Architecture
Code for https://arxiv.org/abs/2110.06864 found: https://github.com/ifzhang/ByteTrack
Quick 5 Min Read | Paper | Github
- [R] ByteTrack: Multi-Object Tracking by Associating Every Detection Box
What are some alternatives?
PaddleDetection - Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
multi-object-tracker - Multi-object trackers in Python
M2I - M2I is a simple but effective joint motion prediction framework through marginal and conditional predictions by exploiting the factorized relations between interacting agents.
FastMOT - High-performance multiple object tracking based on YOLO, Deep SORT, and KLT 🚀
FairMOT - [IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking
classy-sort-yolov5 - Ready-to-use realtime multi-object tracker that works for any object category. YOLOv5 + SORT implementation.
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.
yolo_tracking - BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models
iou-tracker - Python implementation of the IOU Tracker
multi_object_tracking - Multi-object tracking of water fleas from video. Detects dark blotches on light background, performs multi-object association, tracks them with Kalman filters.
zero-shot-object-tracking - Object tracking implemented with the Roboflow Inference API, DeepSort, and OpenAI CLIP.
Ray - Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.