In this project, we build a real-time object detection model with a modified YOLO neural network. As generalized from natural pictures to other domains, this algorithm outperforms other techniques. As compared with other algorithms, this algorithm is easy to implement and a much more efficient, and the fastest algorithm to use in real-time. Also, the YOLO algorithm is trained on a complete image in predicting boundaries which predict the fewer false positive in background areas.
In a working directory of your choice, run pip env python3 -m venv <ENV_NAME>
, then source <ENV_NAME>/bin/activate
. Finally, install packages using:
>>> pip install -r requirements.txt
Create a MOV video recording and move it to the working directory. Run ./init.sh <PATH_TO_MOV>
to create subdirectories, convert the MOV video to MP4, and download the YOLOv3 dependencies for OpenCV.
- wget https://raw.githubusercontent.com/pjreddie/darknet/master/data/coco.names -P yolov3
- wget https://raw.githubusercontent.com/pjreddie/darknet/master/cfg/yolov3.cfg -P yolov3
- wget https://pjreddie.com/media/files/yolov3.weights -P yolov3
- Inspiration: Inspired by a project assignment from the course Computer Vision I at OpenCV.org.
- Network Used: You Only Look Once (YOLO) Network.
From the active environment, run python tracker.py
and observe the frame-by-frame computations while the annotated output video is written.
The machine configuration for our experiment was as follows:
- RAM: 8 GB or More
- Operating System: Windows 10 or Linux
- Hard disk Size: 1 TB
- Python
- Keras (Tensorflow Backend)
- Anaconda
- Computer Vision Library: YOLO
That’s all.
Hope you got idea on real time object detection using Modified Yolo Neural Network.
You may be interested to read see yourself in Tracking Object using Yolo Neural Network.
Thanks for reading.