Search

High-performance mobile phone cameras are MIPI interface currently,its signal can′t be collected by FPGA or DSP directly.However,with the miniaturization trend of equipment and improvement of the performance,using mobile phone cameras becomes one of the most important schemes in the military and industrial areas.In order to use mobile phone cameras in the areas mentioned above,this paper presents a common MIPI-PHY which can receive and process MIPI signal.An appropriate FPGA is adopted to collect the special voltage-level signal by designing electrical matching and pin construction.According to the signal protocol,the aliasing MIPI signal is processed,separated and integrated sequentially,then image information is decoded into common LVCMOS signal according to the integrated signal.Under the condition that frame rate is 22fps and image resolution is 3 256× 2 448,a high imaging quality is achieved via this system with no distortion and frame losing.What′s more,with powerful transplantable capability and parallel signal,the program can satisfy developer′s need and is already applied into some projects.

Compared with traditional global threshold algorithms,which can not extract the pavement crack exactly under non-uniform illumination,an improved image segmentation and classification method is proposed to overcome the drawbacks.Firstly,a new image segmentation method combining sobel and maximum entropy is presented and the solitary noise is reduced based on the pixel geometrical shape of the image.Secondly,a pattern classifier based on RBF neural network is designed to recognize different cracks according to the geometrical shape differences of different cracks.The experimental result indicates that compared with other image segmentation algorithms,the method proposed in this paper has a good ability to extract the image edge,and a strong ability to suppress the noise in the image.Moreover,it can achieve classification accuracy.