An infrared image target segmentation based on improved threshold method

—In recent years, infrared images have been applied in more and more extensive fields and the current research of infrared image segmentation and recognition can’t satisfy the needs of practical engineering applications. The interference of various factors on infrared detectors result in the targets detected presenting the targets of low contrast, low signal-to-noise ratio (SNR) and fuzzy edges on the infrared image, thus increasing the difficulty of target detection and recognition; therefore, it is the key point to segment the target in an accurate and complete manner when it comes to infrared target detection and recognition and it has great importance and practical value to make in-depth research in this respect. Intelligent algorithms have paved a new way for infrared image segmentation. To achieve target detection, segmentation, recognition and tracking with infrared imaging infrared thermography technology mainly analyzes such features as the grayscale, location and contour information of both background and target of infrared image, segments the target from the background with the help of various tools, extracts the corresponding target features and then proceeds recognition and tracking. To seek the optimal threshold of an image can be seen as to find the optimum value of a confinement problem. As to seek the threshold requires much computation, to seek the threshold through intelligent algorithms is more accurate. This paper proposes an automatic segmentation method for infrared target image based on differential evolution (DE) algorithm and OTSU. This proposed method not only takes into consideration the grayscale information of the image, but also pays attention to the relevant information of neighborhood space to facilitate more accurate image segmentation. After determining the scope of the optimal threshold, it integrates DE’s ability of globally searching the optimal solution. This method can lower the operation time and improve the segmentation efficiency. The simulation experiment proves that this method is very effective. © 2021, North Atlantic University Union NAUN. All rights reserved.