Research Of Vehicle Recognition System Based On DM8127 Dual-core DSP

Vehicle detection and recognition, a important part of intelligent transportation system, are designed to acquire and analyze the information of the moving targets quickly and accurately, and make a critical difference in a road surveillance system. The research content is originated from Research of Network Image Acquisition and Analysis System Based on DM81 x Series Chip in Jiangsu Yitong High-tech Company Limited. In this paper, locating and recognizing the front view of a vehicle from high-definition video sequence images captured by traffic monitoring are presented as the following aspects:To begin with, for locating the rough area of front view of a vehicle, we study the detection of the moving vehicles from the road video. Besides, a horizontal gradient projection method is put forward to determine the desired block of vehicle face. The experiments about eight hundred vehicle images show that the detection rates of the face are about eighty-five percent.Next, based on determined vehicle faces, the Histograms of Oriented Gradients feature is chose as recognition feature by comparing different features. For improving distinctiveness, the features are processed by using linear discriminant analysis algorithm. Then based on the idea of ensemble learning, vehicle frontal face was divided into grids and every sub area was trained to integrate an ensemble classifier. The experiments show that the recognition rate is improved.Furthermore, a vehicle-type recognition method based on discrete particle swarm optimization algorithm is presented.SURF feature is decided as recognition feature by experiments. By using Invariance of topological structure of local feature points, Feature points are matched. The experimental results show that the method has a better correct recognition rateFinally, based on the TMS320DM8127 vehicle type recognition system is realized. The schematic and design of system hardware-IPC are focused on, which consists of main chip board, Interface board and power board. This content includes Flash module design, Ethernet interface module design?power module design and so on. In addition, it's briefly suggested that motion detection algorithm is transplanted into the DM8127 DSP. The experimental results indicate that this link can achieve the real-time extraction of video sequences.