Design and implementation of pavement crack detection system based on FPGA

With the rapid development of highway construction and gradual improvement of road network construction in China, road maintenance work has been paid more and more attention. The research for pavement cracks automatic detection and recognition is particularly urgent. This thesis designs a pavement crack detection system based on FPGA. The system uses Altera's DE2 development board as the hardware platform, a CMOS image sensor to collect pavement crack materials, and uses hardware and software co-design approach to image gray-scale transformation, image enhancement, adaptive filtering, image segmentation and thinning process and so on. based on the characteristics of various types of cracks resulting image analysis, feature extraction values and based on the eigenvalues of BP neural network to classify. Finally, we calculate the geometric characteristics of fractures, and fractures of the damage evaluation. Tests show that the system achieve better pavement crack detection function. System, image acquisition, image caching, and image display three modules Verilog hardware description language to write, crack detection module built SOPC, using the C programming language processing implementation in Nios II IDE environment.