Research On The Integrated Processing Technology Of Guidance Image And Reconnaissance Image

It is contribute to improve the battlefield surveillance capability of combat system by adding image reconnaissance equipment to the image guided munition, and provides abundant information to support the operational command decision and damage assessment. The existing separate approach of guidance image and reconnaissance image increases the complexity of munition systems, making it difficult to make full combat effectiveness. Paper carried out the research on the integrated image processing technology for attack and reconnaissance. The main contents are as follows:1. According to analysis the main problems in guidance image processing and reconnaissance image processing, paper puts forward an integrated image processing solution of combining target detection with image compression. The solution detects the target from image first for guidance, then divides the reconnaissance image into target area and background area based on detection results, and encodes image of each area. The image processing solution can not only provide terminal guidance for the target position information, but also get high quality target area image in low bit rate channel.2. A rotation-invariant feature descripts method called Rotation Invariant Histogram of Oriented Gradients(RI-HOG) is proposed for automatic target recognition. RI-HOG calculates gradient of image first, then the image window is divided into a set of un-overlapped annular regions, called sells, and the Histogram of Gradient(HoG) is used to calculate a feature vector for each cells. After that the HoG of each circle is accumulated to get the main angle of the target area, and then it is rotated due to the main angle to make a normalization of the main angle. At last, the HoG of each circle after rotating is linked to generate the rotation-invariant target feature vector. Experiment results show that target detection method using RI-HOG can effectively adapt to changes in rotation, scaling and illumination, with better detection performance.3. Paper designs the image compression based on region of interest(ROI) area in embedded hardware, which is the core part of the integrated image processing solution. The design can make the compression of sub-region reconnaissance image based on TI’s processer TMS320DM6467 T. Both H.264 and JPEG standard are supported by the design in order to adapt different operational requirements.