DESIGN AND IMPLEMENTATION OF MULTI-FEATURE FUSION KERNEL CORRELATION FILTERING ALGORITHM BASED ON HLS

In order to balance the accuracy and real-time performance of the moving target tracking system, an optimized design and implementation method based on high-level synthesis (HLS) of multi-feature fusion with kernel correlation filtering algorithms on FPGA is designed. This design improves the KCF algorithm with LBP and HOG features, and proposes a new dimensionality reduction method for LBP, which enhances the real-time performance while maintaining effective extraction of target features. The algorithm is implemented with FPGA, and a well acceleration effect is obtained on the basis of high precision. In test, the frame rate reaches 35 frames per second. Finally, it is verified through simulation that this feature extraction method can be used to process various image data such as infrared detection and SAR radar imaging, and has a wide range of applications.