针对复杂环境下运动物体的表面温度测量，实现了一种基于热红外图像与可见光图像相结合的物体表面温度检测方法。首先在可见光图像下检测运动物体的感兴趣区域，在仿射变换的基础上实现一种修正方法实现图像的精确配准，实时地将可见光图像的感兴趣区域映射到热红外图像上。然后对热红外图像进行图像运算，最终获取运动物体特定区域的温度。以行人的人脸为研究对象，实验结果表明，对非正面、轻微遮挡的人脸有较高的准确率，并且能快速地检测特定运动对象的表面温度，该方法测量误差在 0.2℃内，基本能满足在密集场合下快速筛选运动物体表面温度的要求。

In order to measure the surface temperature of moving objects in complex environments, a method based on the combination of thermal infrared image and visible light image is proposed in this paper. Firstly, the ROI of moving object is detected in the visible image, and a correction method is implemented based on affine transformation to achieve accurate registration of the image. Then the thermal infrared image is calculated and the temperature of the specific area of the moving object is finally obtained. In this paper, pedestrian face is taken as the research object. The experimental results show that the method has high accuracy for non-frontal and slightly occluded faces, and can quickly detect the surface temperature of specific moving objects. The measurement error of this method is within 0.2, which can basically meet the requirements of fast screening the surface temperature of moving objects in dense occasions.