A Modified Multi-Pedestrian Tracking System

The intelligent vehicle driverless technology has become a very hot topic in the past two decades. To solve the road safety problem, the multi-target tracking system has attracted more and more attention in recent study since it can detect and track multiple objects in traffic scene so as to help the whole driving system plan the safe route. In this work, a novel multi-pedestrian tracking system based on deep neural network is proposed to improve the tracking efficiency while providing high recognition accuracy. The proposed tracking system consists of two parts: pedestrian detector and target tracker. We refer to the structure of SSD detection network to design our own detection network, replacing the traditional pooling layers by image convolution operation implemented in complex frequency domain. Then, a deep appearance model is trained to track the detected targets by their similarity between the continuous frames. To evaluate the performance of our proposed system, we implement the system on MOT16 benchmark. The detector can improve tracking accuracy by up to 9.3% and the tracker updates at a rate of 138Hz, our extensions reducing the number of identity switches by 16.2%. The experimental results show that the proposed multi-pedestrian tracking system provides better real-time performance and accuracy than the state-of-the-art methods, which can provide more accurate object information for the following auto-driving system with higher safety.