Infrared Target Recognition Method Based On LARK And Nearest Neighbor Structure Matching

With the rapid development of infrared imaging technology, the infrared object detection and identification technology has broad application prospects. In recent years, many scholars at home and abroad have proposed a variety of object detection and recognition method, such as methods based on training and classifier, no-training method based on Locally Adaptive Regression Kernels (LARK), and Local Similar Structure Statistical Matching (LSSSM) method, etc.In order to keep the advantages of Locally Adaptive Regression Kernels, and aimed at the low contrast ratio and high noise of infrared images, and the randomness and ambient occlusion of its objects, this paper presents a neighboring structure reconstructed matching (NSRM) algorithm based on LARK features. The neighboring structure relationships of local window are considered based on a non-negative linear reconstruction method to build a neighboring structure relationship matrix. Calculating the neighboring structure relationship matrix by non-negative linear reconstruction method. Then the LARK feature matrix and the NSRM matrix are processed separately to get two different similarity images. By fusing and analyzing the two similarity images, those infrared objects are detected and marked by the non-maximum suppression.The NSRM approach is extended to detect infrared objects with incompact structure. High performance is demonstrated on infrared body set, indicating a lower false detecting rate than conventional methods in complex natural scenes.