LIÊN KẾT WEBSITE
Hardware Architecture Design for Vehicle Detection
Proceedings - 2019 International Symposium on Electrical and Electronics Engineering, ISEE 2019 Số , năm 2019 (Tập , trang 33-36)
DOI: 10.1109/ISEE2.2019.8920984
Tài liệu thuộc danh mục: Scopus
English
Từ khóa: Edge detection; Gaussian distribution; Motor transportation; Object detection; Parallel architectures; Roads and streets; Background subtraction; Corner detection; Dedicated hardware; Gaussian Mixture Model; Hardware architecture design; Stationary cameras; Vehicle detection; Vehicles detection; Vehicles
Tóm tắt tiếng anh
Nowadays, road safety systems based on vehicles detection are researched and become one of the important issues in Vietnam. In these systems, there are many study using CNNs which require model and many samples to train and long time in processing. In this paper, we propose an efficient method for solving this problem. This algorithm is called Background Subtraction With Gaussian Mixture Model (GMM) and implemented on FPGA - a dedicated hardware architecture. In our algortihm, all vehicle detection functions, including vehicle corner detection, vehicle region expansion, and vehicle region validation, is implemented using parallel architecture. Our testing model using a stationary camera to capture vehicles on the road and the algorithm is applied in order to detect the moving objects. � 2019 IEEE.
