Real-time object detection and tracking using YOLOv3 network by quadcopter

Abstract

In this article, artificial intelligence is applied for real-time object detection in Tello quadcopters. For this purpose, the YOLOv3 detection algorithm as a highly used deep-learning method is employed. The results indicate that the YOLOv3 network can be trained with an accuracy of 99 percent and can detect the target with above 95 percent accuracy at a speed of 15 frames-per-second for different ambient lighting and background conditions. The YOLOv3 algorithm is trained using a custom dataset and implemented in Python. Images are sent to a computer using Python language to detect the target and entered into the YOLOv3 algorithm. After detecting the target, the errors are calculated and given to the control system to track the target in real-time. There are two purposes in tracking, the target is in the view of the quadcopter, and the quadcopter is at a certain distance from the target. For this purpose, the effect of quadcopter movements on the coordinates and area of the target is examined and four controllers are designed to follow the target and keep the robot at a certain distance from the target. The designed controllers efficiently follow the target and prevent flying robots from losing sight of the target.