自适应尺度显著图融合的红外舰船检测算法  

Infrared Ship Detection Algorithm Based on Adaptive Scale Saliency Map Fusion

作　　者：樊宇亮 王钢[1] 张佳岩[1] FAN Yuliang;WANG Gang;ZHANG Jiayan(Communication Research Center,Harbin Institute of Technology,Harbin 150001,China)

机构地区：[1]哈尔滨工业大学通信技术研究所,黑龙江哈尔滨150001

出　　处：《无线电通信技术》2022年第6期1122-1129,共8页Radio Communications Technology

基　　金：国家自然科学基金面上项目(62071146)。

摘　　要：红外舰船目标识别逐渐成为无人机侦查和精确制导等领域的研究重点。基于视觉显著性目标检测,对ITTI模型和HOU模型的算法进行研究。为了兼顾识别精度和速度,提出了一种基于直方图的自适应尺度的显著图融合检测算法,通过在HOU算法的显著图中加入了ITTI模型的亮度特征,并在形成图像金字塔时,利用直方图确定目标尺寸,进而自适应地得到合适数量的金字塔图层,使得生成的显著图更精确。仿真表明该算法能有效提高红外舰船目标的识别率,并可以适用于不同大小目标的检测。Infrared ship target recognition has gradually become a research focus in UAV reconnaissance and precision guidance.Based on visual saliency target detection,algorithms of ITTI model and HOU model are studied.In order to take into account the recognition accuracy and speed,a histogram-based adaptive scale saliency map fusion detection algorithm is proposed.By adding the brightness feature of the ITTI model to the saliency map of the HOU algorithm,and when forming an image pyramid,the histogram is used.The image determines the target size,and then adaptively obtains an appropriate number of pyramid layers,so that the generated saliency map is more accurate.Simulation shows that the algorithm can effectively improve the recognition rate of infrared ship targets,and can be applied to the detection of targets of different sizes.

关 键 词：红外舰船图像 目标识别 自适应尺度 显著图 

分 类 号：TN911.73[电子电信—通信与信息系统]