红外破碎人体目标的水平集修复算法

A level set based inpainting approach for fragmentary human bodies in binarized infrared images

许多图像分割方法提取红外人体目标时的结果常存在破碎现象,需要修复。将图像修复转化为图像分割问题,首先应用薛定谔变换使人体碎片形成连通区域,然后提出一种综合图像区域和边缘信息的水平集分割模型提取该连通区域,模型收敛时目标修复完成。实验结果表明,该方法可自动确定目标碎片位置与归属,排除背景干扰,填补目标内部缺损,胶连缺损人体轮廓段,修复结果与真实外形总体相似度高于80%,内部残缺率低于4%,通过优化模型参数可获得良好鲁棒性。

A number of image segmentation algorithms frequently fragmentize human targets in infrared images,therefore,an inpainting procedure is always needed for further application.The inpainting is transformed to be a segmentation process.Firstly,Schrdinger transform connects fragmentized human parts.Then a level set model integrating image region and boundary information is proposed to extract the connected regions produced by the Schrdinger transform,and finally the inpainting is done when the model converged to complete the segmentation.Experiments show the proposed algorithm recognizes and locates human parts automatically,fills gaps correctly,connects broken human silhouettes smoothly.The objective indictor of shape similarity between inpainting results and relevant ground-truths is above 80%,as well as the internal fragmentary proportion below 4%.With optimized parameters the approach is robust to noise disturbance.