Based on Frond-End and Back-End Platfrom and Image Processing Algorithm to Design People Counting Analysis System

This paper presents a people counting method that is derived from traditional machine learning and deep learning algorithms. The proposed design mainly provides cognition information of a period of time which is peak hour or off hour in specific public places, such as transportation tools, hotel lobby, and bus shelter. Its advantage can efficient save management cost. In previously literatures, the traditional machine learning technique, such as Support Vector Machine (SVM) would be adopted for the people counting. However, pedestrian recognition rate of the previous means is lower than deep learning method. Hence, the Convolutional Neural Network (CNN) is derived to improved drawback of worse recognition rate. But, in view of its computation task is very heavy when processing of operating the system. Therefore, the proposed system is designed based on two-stage architecture which contains previous two methods in front-end and back-end, respectively. Among these, the first stage which is front-end that mainly be used for pedestrian recognition. According to the above results, the people number counting could be executed. After that, the statistics consequence is classified to two-level and then the back-end stage only need to process pedestrian recognition of level two. Finally, the experimental results shows that the pedestrian recognition is increased and computational complexity is reduced when comparing with traditional machine learning and deep learning, respectively. The experimental results indicated that the proposed front-end design had 84.56% accuracy for detection performance. The other proposed architecture which is back-end can obtain detection accuracy of 93.59%. On the other hand, the proposed method also improves average 29% execution time when comparing with the related designs.