Abstract: Most of the existing bus ridership count methods dont consider the video jitter caused by bus vibration and the trapezoidal distortion caused by the camera angle. The authors proposed a bus ridership count method based on video stabilization and perspective switching. Firstly, the presented method used video stabilization based on block-matching to reduce the offset between image sequences caused by vibration. Secondly, the method used perspective switching to correct the trapezoidal distortion caused by the camera angle. Lastly, the method used detection and tracking based on the characteristics of head and shoulder for statistics of the number of passengers. The experimental results show that the Peak Signal-to-Noise Ratio (PSNR) value of the stabilization video increases by about 4.5dB than that of the shaky video, and human recognition rate of the perspective switched video increases by about 10% than that of the original video. The method has greatly improved the accuracy of ridership count.

Key words: bus ridership count, video surveillance, image stabilization, perspective switching

摘要： 已有的公交客流计数方法大多没有考虑车体振动引起的视频抖动问题和摄像头角度引起的图像梯形失真问题,因此提出一种基于视频稳像和视角变换的公交客流计数方法。首先采用基于块匹配的视频稳像技术，减小车体振动引起的图像序列间的偏移；然后通过对视频图像进行视角变换，校正摄像头角度引起的图像梯形失真；最后采用基于头肩部特征的人体检测及跟踪方法，统计各个时段的上下客流量和乘客总人数。经实验测试，稳像处理后的视频与稳像前相比，峰值信噪比（PSNR）提高了约5.5dB，稳像速率达到25帧/s。视角变换后的视频与原始视频相比，人体识别率提高了约10%，大大提高了客流计数精度

关键词: 公交客流计数, 视频监控, 稳像, 视角变换