#5555th of 56 in Image and video
yolov5-deepsort-inference
YOLOv5 detection plus DeepSort tracking for counting vehicles and pedestrians
- Stars
- 1.5k
- License
- GPL-3.0
- Last commit
- Mar 2026
- Language
- Python
1,451 on 21 Apr 20261,480 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Python project that runs YOLOv5 detection and DeepSort tracking on video to track people, cars and trucks. It wraps both in a `Detector` class whose `feedCap` call returns an annotated frame, and `demo.py` runs the example. Custom YOLOv5 weights can be placed in the `weights` folder. The README points to a newer YOLOv11 version as the latest.
Who it is for: Computer vision developers adding vehicle or pedestrian tracking to video
Strengths
- Wrapped `Detector` class with a single `feedCap` call returns an annotated frame
- Custom-trained YOLOv5 weights can be used by placing them in `weights/`
- Includes DeepSort re-ID tracking, not only per-frame detection
- Short setup: `pip install -r requirements.txt` then `python demo.py`
Weaknesses
- Detection filter is hardcoded to person, car and truck labels
- Author points to a newer YOLOv11-DeepSort repository as the latest version
- GPL-3.0 license limits use in closed-source products
- README is in Chinese; no tests or benchmarks listed
What it needs
- GPU optional
- Needs PyTorch, YOLOv5 (ultralytics), DeepSort
- Models: YOLOv5 .pt weights (default yolov5m.pt)
Quick answers
Is yolov5-deepsort-inference open source?
Yes. Its code is on GitHub under the GPL-3.0 license.
Does yolov5-deepsort-inference need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Image and video
See all 56| Rank | Project | Score |
|---|---|---|
| 1 | frigateLocal NVR with realtime object detection for IP cameras | 92 out of 100 |
| 2 | MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles | 88 out of 100 |
| 3 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 86 out of 100 |
| #4 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 85 out of 100 |
| #5 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 85 out of 100 |