mmtracking
mmpose
| mmtracking | mmpose | |
|---|---|---|
| 7 | 31 | |
| 3,382 | 5,025 | |
| 1.6% | 2.8% | |
| 1.5 | 8.0 | |
| 8 months ago | 9 days ago | |
| Python | Python | |
| Apache License 2.0 | Apache License 2.0 |
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.
mmtracking
-
Tracking sets of Keypoints by Person
I suggest to try the top down approach with the https://openmmlab.com/ open source package. The openmmlab provides multiple algorithms, datasets and pretrained models for various computer vision tasks. Start with mmpose video demo that integrates detection and pose estimation. You can add later tracking with https://github.com/open-mmlab/mmtracking to track the poses in time.
-
MMDeploy: Deploy All the Algorithms of OpenMMLab
MMTracking: OpenMMLab video perception toolbox and benchmark.
- [P]We have supported Quasi-Dense Similarity Learning for Multiple Object Tracking.
- [p]We have supported Quasi-Dense Similarity Learning for Multiple Object Tracking
- MMTracking have supported Quasi-Dense Similarity Learning for Multiple Object Tracking.
- MMTracking Supports Quasi-Dense Similarity Learning for Multiple Object Tracking
-
Help combining custom detector (yolo) with a tracker.
Implementations exist, like https://github.com/open-mmlab/mmtracking
mmpose
-
RTMPose: The All-In-One Real-time Pose Estimation Solution for R&D
RTMPose-m achieves 75.8% AP on COCO with 90+ FPS on an Intel i7-11700 CPU and 430+ FPS on an NVIDIA GTX 1660 Ti GPU, and RTMPose-l achieves 67.0% AP on COCO-WholeBody with 130+ FPS.
-
MMDeploy: Deploy All the Algorithms of OpenMMLab
MMPose: OpenMMLab pose estimation toolbox and benchmark.
-
Model conversion from Pytorch to Tf using Onnx.
I downloaded pytorch2onnx.py from mmPose tools. It's big, but the top half is imports and input arguments. Line 125, I hard-coded my (image) input size. I ran it on my .pth model file, and out pop'd an onnx file.
-
Finetuning Openpose for custom dataset
They have a specific repo called mmpose: https://github.com/open-mmlab/mmpose
-
State of the art 2D body pose estimation [Discussion]
I would start with mmpose. It's basically a curated list of the best models ready to go.
-
[P] Object detection framework : Detectron2 VS MMDetection
The [MMLab key point detection](https://github.com/open-mmlab/mmpose) is in a separate repo from detection.
-
[D] Searching for open source pose estimation solution similar to open pose ?
One option is mmPose. They have a bunch of 2D/3D models implemented and support different skeleton structures.
-
Human Pose Estimation Recommendation
This library is pretty good. It has implementations for a number of pose estimators. I think Darkpose is the best one from memory
-
Human pose classification problem.
Check out https://github.com/open-mmlab/mmpose I think they have guides for new datasets
What are some alternatives?
ByteTrack - [ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box
openpose - OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
FastMOT - High-performance multiple object tracking based on YOLO, Deep SORT, and KLT 🚀
openpifpaf - Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
PaddleDetection - Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
AlphaPose - Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
norfair - Lightweight Python library for adding real-time multi-object tracking to any detector.
mmaction2 - OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
Yolov7_StrongSORT_OSNet - Real-time multi-camera multi-object tracker using YOLOv7 and StrongSORT with OSNet
deep-high-resolution-net.pytorch - The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"
mmyolo - OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.
AdelaiDet - AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.