Video Detection System of Traffic Flow toward Urban Roads
Hao Chen, Peng Wu, Juan Meng · Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence · 2018
The video detection system of traffic flow toward urban roads is designed in this paper for improving the detection effect under the changing background, light, shadow and covering. First, vehicle detection is realized by using Histogram of Oriented Gradient (HOG) and Support Vector Machine (SVM). Then, vehicle classification is achieved by using Gaussian Mixed Model (GMM), vehicle count is achieved by defining Interval Frames and Continuous Detected Frames. Finally, the performance and evaluation show the practicability of the system, which can provide important information for traffic real-time adjustment and the planning and design of urban roads.