Abstract
In order to solve the problem that the deep neural network model is large in scale, the calculation time is too long, and the real-time performance is severely limited when combined with embedded devices, so studied the intelligent follower robot system based on YOLO-LITE algorithm combined with Raspberry Pi 3B+. The system mainly includes camera processing, target detection and other modules. Obtained the internal and external parameters of the camera through calibration, and according to these parameters to correct the binocular camera. Recognized and located the target in each frame of image, calculated the distance from the camera to the target and the center location error, and driven the car to move. The experimental results show that the following car has excellent real-time performance, the average detection frame rate can reach 20Fps, and the average detection accuracy can reach more than 80%.
Highlights
In order to solve the problem that the deep neural network model is large in scale, the calculation time is too long, and the real-time performance is severely limited when combined with embedded devices, so studied the intelligent follower robot system based on YOLO-LITE algorithm combined with Raspberry Pi 3B+
After the obtained binocular image is cut, the left camera The video frame is transferred to the Raspberry Pi 3B+ microprocessor, through the YOLO-LITE deep learning algorithm It performs functions such as target recognition, positioning and tracking
The target detection algorithm used in this paper is YOLO-LITE, which is a simplified version of Tiny-YOLOv2, Tiny-YOLOv2 consists of 9 convolutional layers, a total of 3181 filters and 6.97 billion FLOPS [6]
Summary
Intelligent service robots have been greatly developed by riding on the ride of the booming artificial intelligence technology. In recent years, deep learning technology has been developed rapidly, and neural networks have been widely used in the field of visual target detection. Joseph Redmon et al [5] of the University of Washington proposed the YOLOv2 target detection algorithm. This algorithm draws on the idea of Faster R-CNN, introduces Anchor, and solves the inaccurate positioning of the YOLO algorithm itself. The embedded device is well combined with the visual target detection algorithm, and there are still fewer intelligent follow-up robot systems that use cameras to capture and track targets. The research in this article is an intelligent follower robot system based on Raspberry Pi 3B+ and YOLO-LITE algorithm
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have