Forward-Looking Infrared Image Segmentation Using Support Vector Machine Based on Feature Extraction

Forward-looking infrared (FLIR) image segmentation is a key technology in the target recognition and tracking. The FLIR image often contains undulated and non-consistent background. These characteristics make standard segmentation methods ineffective for extracting target. For this reason a method for FLIR image segmentation using support vector machine (SVM) is proposed to extract target. A region of interest (ROI), which contains a target to be segmented, is selected at first so as to reduce computation workload. And then in the ROI SVM is used to segment the image based on feature extraction in order to make the target and background separated. Experimental results prove that the proposed method is precise and effective compared with other approaches.