Open AccessTarget Detection and Tracking System Based on FPGA
Author(s) -
Xiaoyang Yu,
Li Bingqi,
Mingshuai Dong,
Yin Wei-min
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/793/1/012008
Subject(s) - field programmable gate array , computer science , sobel operator , computer vision , frame rate , artificial intelligence , tracking (education) , feature (linguistics) , tracking system , frame (networking) , image processing , filter (signal processing) , computer hardware , edge detection , image (mathematics) , psychology , pedagogy , telecommunications , linguistics , philosophy
The parallel processing mode of Field Programmable Gate Array (FPGA) and the ability to perform multiple tasks repeatedly meet the real-time and flexible requirements of target detection and tracking. The FPGA of Cyclone IV of ALTERA company is adopted as the hardware processor for the system platform to filter and preprocess color conversion of the collected image. The edge detection method of Sobel operator is adopted to realize the convolution and binarization processing of the third-order matrix of pixel points and the operator template, and the inter-frame difference algorithm is applied to the moving target. At the same time, the tracking algorithm based on centroid feature matching can realize the real-time tracking of target position. The system uses the characteristics of high real-time, low power consumption, parallel processing and strong expansibility of the FPGA, transplants machine vision algorithm into the FPGA, reduces the delay of image processing, and completes the hardware implementation of the target detection and tracking algorithm. Finally, the experiment verifies the real-time performance and effectiveness of the algorithm.