摘要：Because in the traffic video image processing, the background image gotten from background modeling by traditional k-means clustering algorithm shows a lot of noises, thus the improvement of k-means clustering algorithm is proposed, and has been applied to the vehicle flow detection of traffic video image. By analyzing the vehicle detection method and comparing the flow detection algorithm, the improved k-means clustering algorithm is experimentally tested at last, and carries out software implementation . The experiment shows that the improved algorithm after background modeling is superior to the traditional one in time complexity, it has better adaptivity and robustness , which has increased the effect of vehicle flow detection.
关键词：Traffic Video Image;K-Means Clustering Algorithm;Flow Detection
