基于视线追踪的卫星观测图像分割技术

Satellite Observation Image Segmentation Based on Eye Tracking

基于卫星观测图像的数据应用往往需要通过目标识别提取来获取有用数据。而图像分割是目标提取的前提,传统的图像分割技术主要是通过各类目标检测算法,获取目标区域并完成分割。本文提出了一种基于视线追踪的图像分割方法,通过分析视觉关注度提取目标图像并完成分割,再使用目标检测算法直接分析真正包含目标的图像。这种利用人的直觉配合算法处理的方式,可有效减少无效分析,降低算法运算量,提高目标识别分析效率。

Data applications based on satellite observation images used to obtain useful data through target recognition and extraction.Image segmentation is the premise of target extraction.The traditional image segmentation technology mainly uses various target detection algorithms to obtain the target area and complete the segmentation.In this paper,an image segmentation method based on eye tracking is proposed.By analyzing the visual attention,the target image is extracted and segmented,and then the target detection algorithm is used to directly analyze the image containing the target.This method can reduce invalid analysis effectively,decrease the amount of computation and improve the efficiency of target recognition and analysis.