Firstly,through using symmetrical DFD algorithm on infrared sequence frame,possible target areas are extracted by using frame difference(FD)algorithm and auto-adaptive segmentation of threshold. The area is extended and piled up,then the possible target area is gotten in continuous frames.
对序列红外图像做对称差分运算,通过图像差减运算和自适应阈值分割提取目标可能的运动区域,并对区域做扩张和叠加处理,得到连续帧间目标可能出现的区域。
参考来源 - 基于对称差分和光流估计的红外弱小目标检测·2,447,543篇论文数据，部分数据来源于NoteExpress
A recursively increasing threshold method for the segmentation of laser scanning confocal microscopic (LSCM) biomedical images is presented.
提出了用于激光共焦显微生物医学图象分割的循环递增阈值分割法。
Temporal segmentation was based on change detection, whose key factor was the selection of appropriate threshold by histogram analysis.
时间分割采用变化检测，其关键的阈值选取通过直方图分析得到。
The optimum threshold determined by the theory of image segmentation is to be the crossover point of the fuzzy enhancement in order to enhance the contrast of image.
利用图像分割原理确定的最佳阈值作为模糊增强的分界点，完成对图像的对比度增强。
应用推荐