YOLO Output for Real-Time Detection

AlexeyAB / darknet

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

http://pjreddie.com/darknet/

Other

21.73k stars 7.96k forks source link

YOLO Output for Real-Time Detection #5164

Open LakyG opened 4 years ago

LakyG commented 4 years ago

I am new to using YOLO and this is my first time trying to use it for an application. I want to know if it is possible to get outputs from YOLO as it runs detection on a real-time webcam.

So I want to run YOLO detection on a real-time video stream and record the output that is coming at regular intervals, say every 10 seconds. I want to be able to see all the objects being detected by YOLO, I don't necessarily need to know the position that the detection occurs within the image, just the classification if it occurs.

This may not be clear enough so let me know if I can explain anything further! I appreciate the help, thank you!

AlexeyAB commented 4 years ago

./darknet detector demo ./cfg/coco.data ./cfg/yolov3.cfg ./yolov3.weights -c 0 -json_port 8070 -mjpeg_port 8090 > result.txt

Then you can

open file result.txt
open url ip:8070 in Chrome/Firefox or in your application
open url ip:8090 in Chrome/Firefox or in your application

Or you can use Darknet as SO/DLL library in your Python application: https://github.com/AlexeyAB/darknet/blob/master/darknet.py and https://github.com/AlexeyAB/darknet/blob/master/darknet_video.py