Research of Vehicle Counting Based on DBSCAN in Video Analysis
Dayang Sun, Binbin Li, Zhihong Qian · 2013
In order to provide better traffic planning, monitoring for road traffic is very necessary. In this paper, interframe difference is mainly studied for extracting moving vehicles and clustering analysis is used to get the target number. DBSCAN clustering analysis is the key to deal with the problem to get the number of the targets. In order to achieve better clustering effect, this paper uses the median filter and mathematical morphology filtering. According to the target state change, traffic statistics has been done. Meanwhile, parameters such as searching area, clusters threshold and frame differing threshold are made adaptive in this paper. In order to improve real-time performance, sampling is adopted to each frame. By analyzing a streaming video, the algorithm for traffic statistics can achieve good results.