Skip to content

Latest commit

 

History

History
199 lines (122 loc) · 9.33 KB

README.md

File metadata and controls

199 lines (122 loc) · 9.33 KB
Raw

StrongSORT with OSNet for YoloV5, YoloV7, YoloV8 (Counter)


# Official YOLOv5
CI CPU testing
Open In Colab
# Official YOLOv7

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

PWC Hugging Face Spaces Open In Colab arxiv.org

Ultralytics CI Ultralytics Code Coverage YOLOv8 Citation Docker Pulls
Run on Gradient Open In Colab Open In Kaggle

Ultralytics YOLOv8 is a cutting-edge, state-of-the-art (SOTA) model that builds upon the success of previous YOLO versions and introduces new features and improvements to further boost performance and flexibility. YOLOv8 is designed to be fast, accurate, and easy to use, making it an excellent choice for a wide range of object detection and tracking, instance segmentation, image classification and pose estimation tasks.

Introduction

This repository contains a highly configurable two-stage-tracker that adjusts to different deployment scenarios. The detections generated by YOLOv5, YOLOv7, YOLOv8 a family of object detection architectures and models pretrained on the COCO dataset, are passed to StrongSORT which combines motion and appearance information based on OSNet in order to tracks the objects. It can track any object that your Yolov5 model was trained to detect.

Before you run the tracker

  1. Clone the repository recursively:

git clone --recurse-submodules https://github.com/bharath5673/StrongSORT-YOLO.git

If you already cloned and forgot to use --recurse-submodules you can run git submodule update --init

  1. Make sure that you fulfill all the requirements: Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install, run:

pip install -r requirements.txt

Tracking sources

Tracking can be run on most video formats

Select object detectors and ReID model

Yolov5

There is a clear trade-off between model inference speed and accuracy. In order to make it possible to fulfill your inference speed/accuracy needs you can select a Yolov5 family model for automatic download

$ python track_v5.py --source 0 --yolo-weights weights/yolov5n.pt --img 640
                                            yolov5s.pt
                                            yolov5m.pt
                                            yolov5l.pt 
                                            yolov5x.pt --img 1280
                                            ...

Yolov7

There is a clear trade-off between model inference speed and accuracy. In order to make it possible to fulfill your inference speed/accuracy needs you can select a Yolov5 family model for automatic download

$ python track_v7.py --source 0 --yolo-weights weights/yolov7-tiny.pt --img 640
                                            yolov7.pt
                                            yolov7x.pt 
                                            yolov7-w6.pt 
                                            yolov7-e6.pt 
                                            yolov7-d6.pt 
                                            yolov7-e6e.pt
                                            ...

StrongSORT

The above applies to StrongSORT models as well. Choose a ReID model based on your needs from this ReID model zoo

$ python track_v*.py --source 0 --strong-sort-weights osnet_x0_25_market1501.pt
                                                   osnet_x0_5_market1501.pt
                                                   osnet_x0_75_msmt17.pt
                                                   osnet_x1_0_msmt17.pt
                                                   ...

Filter tracked classes

By default the tracker tracks all MS COCO classes.

If you only want to track persons I recommend you to get these weights for increased performance

python track_v*.py --source 0 --yolo-weights weights/v*.pt --classes 0  # tracks persons, only

If you want to track a subset of the MS COCO classes, add their corresponding index after the classes flag

python track_v*.py --source 0 --yolo-weights  weights/v*.pt --classes 16 17  # tracks cats and dogs, only

Counter

counter

get realtime counts of every tracking objects without any rois or any line interctions

$ python track_v*.py --source test.mp4 -yolo-weights weights/v*.pt --save-txt --count --show-vid

Draw Object Trajectory 

$ python track_v*.py --source test.mp4 -yolo-weights weights/v*.pt --save-txt --count --show-vid --draw

Here is a list of all the possible objects that a Yolov5 model trained on MS COCO can detect. Notice that the indexing for the classes in this repo starts at zero.

MOT compliant results

Can be saved to your experiment folder runs/track/<yolo_model>_<deep_sort_model>/ by

python track_v*.py --source ... --save-txt

YoloV8 (Counter)

V8 counter

## recommended conda env python=3.10
## conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia
## pip install ultralytics
$ python track_v8.py --source 0 1 vid1.mp4 vid2.mp4 --track --count

Acknowledgements

Expand