A computer vision approach for detection and counting of motorcycle riders in university campus

2014 International Electrical Engineering Congress (iEECON) Pub Date : 2014-03-19 DOI:10.1109/IEECON.2014.6925906

Rattapoom Waranusast, Vasan Timtong, Nannaphat Bundon, Chainarong Tangnoi

引用次数: 5

Abstract

Essential tasks of automatic traffic monitoring are a vehicle classification and a vehicle or passenger counting system. These tasks provide useful data in planning transportation system. This paper presents an automatic system to classify a motorcycle and count riders on it. The system extracts moving objects and classifies them as a motorcycle or other moving objects based on features derived from their region properties using K-Nearest Neighbor (KNN) classifier. The heads of the riders on the recognized motorcycle are then counted based on projection profiling. Experiment results show an average correct motorcycle classification at 95.31% and correct rider count at 83.82%.

查看原文本刊更多论文

基于计算机视觉的大学校园摩托车骑手检测与计数方法

自动交通监控的基本任务是车辆分类和车辆或乘客计数系统。这些任务为规划运输系统提供了有用的数据。本文介绍了一种摩托车自动分类和计数系统。该系统利用k -最近邻(K-Nearest Neighbor, KNN)分类器提取运动物体，并根据其区域属性衍生的特征将其分类为摩托车或其他运动物体。然后，根据投影轮廓对被识别的摩托车上的骑手的头部进行计数。实验结果表明，该算法对摩托车的平均正确分类率为95.31%，正确骑乘人数为83.82%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2014 International Electrical Engineering Congress (iEECON)

自引率

0.00%

发文量