针对光照以及人脸的尺度变换、遮挡等问题，提出一种基于多尺度韦伯脸与实时压缩在复杂光照情况下的跟踪算法。对实时压缩跟踪方法的理论模型的认真分析与研究，提出采用光照预处理方法来提高复杂光照情况下跟踪过程中目标信息的采集精准度。在目标检测跟踪过程中，与经典的实时压缩跟踪算法相比，基于多尺度韦伯脸与实时压缩的人脸跟踪算法在复杂光照情况下跟踪性能得到明显提升，能较好应对人脸尺度变换及局部遮挡的情况。

Aiming at the resolution of problems of illumination and face scale conversion and occlusion, a tracking algorithm based on multi-scale Weberface and real-time compression under complex lighting conditions is proposed. After a careful analysis and research on the theoretical model of the real-time compression tracking method, the illumination preprocessing method is proposed to improve the acquisition accuracy of the target information in the tracking process under complex lighting conditions. In the process of target detection and tracking, compared with the classical real-time compression tracking algorithm, the tracking performance based on multi-scale Weberface and real-time compression can clearly improve tracking performance under complex lighting conditions and better cope with face scale transformation and local occlusion cases.