Concerning the problem of barrier among passengers and unstable illumination on the bus, a detection and tracking algorithm was proposed based on edge feature and local invariant feature of head-shoulder. Firstly, the algorithm used adaptive threshold background subtraction method to achieve passenger segmentation. Secondly, it used Histogram of Oriented Gradient (HOG) feature of different sample sets to train Support Vector Machine (SVM) classifiers, and combined Adaptive Boosting (AdaBoost) algorithm to extract a strong classifier. And then it scanned the foreground using strong classifier to achieve passenger detection. Lastly, it extracted Speeded-Up Robust Feature (SURF) of target region and current search region, and then matched feature points to achieve passenger tracking. The experimental results show that this algorithm has detection rate and tracking rate of more than 80% in the case of barrier among passengers and unstable illumination, and it can meet the requirement of real-time. It can be used for passenger flow counting.

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.