melodiepupu / seq_nms_yolo

This project combines YOLOv2 and seq-nms to realise real time video detection.

Seq_nms_YOLO

Membres: Yunyun SUN, Yutong YAN, Sixiang XU, Heng ZHANG

---

Introduction

This project combines YOLOv2(reference) and seq-nms(reference) to realise real time video detection.

Steps

1. make the project;
2. Download yolo.weights and tiny-yolo.weights by running wget https://pjreddie.com/media/files/yolo.weights and wget https://pjreddie.com/media/files/tiny-yolo-voc.weights;
3. Copy a video file to the video folder, for example, input.mp4;
4. In the video folder, run python video2img.py -i input.mp4 and then python get_pkllist.py;
5. Return to root floder and run python yolo_seqnms.py to generate output images in video/output;
6. If you want to reconstruct a video from these output images, you can go to the video folder and run python img2video.py -i output

And you will see detection results in video/output

Reference

This project copies lots of code from darknet , Seq-NMS and models.