基于深度信息的压缩感知人脸检测跟踪①.PDFVIP

2015 年 第 24 卷 第 9 期 计 算 机 系 统 应 用 基于深度信息的压缩感知人脸检测跟踪① 1 1 1,2 1 郑宪成 , 蒋 敏 , 孔 军 , 吴 佼 1(江南大学 轻工过程先进控制教育部重点实验室, 无锡 214122) 2(新疆大学 电气工程学院, 乌鲁木齐 830047) 摘 要: 传统的压缩感知跟踪是基于彩色视频图像序列中的目标跟踪, 但在跟踪过程中可能会受到光照变化和 旋转遮挡因素的影响, 从而导致复杂环境下跟踪结果的鲁棒性不足. 为了获得稳定的跟踪结果, 提出了一种基于 深度信息的压缩感知人脸检测跟踪算法. 首先, 根据改进的质心分割算法确定首帧深度图中人脸的跟踪位置. 其 次, 根据深度信息计算出深度图中每一点对应的平均曲率并形成平均曲率图. 然后, 基于平均曲率图随机提取压 缩特征; 最后, 通过压缩降维, 目标邻域搜索, 迭代更新特征模板, 计算出平均曲率图中下一帧人脸的最优跟踪 位置, 实现人脸跟踪. 实验结果表明, 将人脸的深度信息和压缩感知特征相结合在光照变化和旋转遮挡情况下具 有很好的鲁棒性, 能更好的实现复杂背景下对多姿态人脸的跟踪. 关键词: 压缩感知; 平均曲率图; 深度信息; 人脸跟踪 Depth Based Face Detection and Tracking Using Compressive Sensing 1 1 1,2 1 HENG Xian-Cheng , JIANG Min , KONG Jun , WU Jiao 1(Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi 214122, China) 2(College of Electrical Engineering, Xinjiang University, Urumqi 830047, China) Abstract: The traditional target tracking algorithms based on compressive sensing uses color video sequence. It is easily affected by rotation, occlusion and illumination. Thus it has poor robustness in complex environment. In order to obtain stable tracking results, this paper proposed a novel face detection and tracking algorithm using compressive sensing based on depth information. Firstly, we identify the position of face in the initial depth map automatically using the improved centroids segmentation algorithm. Secondly, we calculate the mean curvature graph with the depth map. Thirdly, the compression features are extracted based on the mean curvature graph. Finally, by compression and dimen