基于支持向量机优化的行人跟踪学习检测方法
2016-11-30孙炜薛敏孙天宇胡梦云吕云峰
孙炜+薛敏+孙天宇+胡梦云+吕云峰



摘 要:提出一种基于SVM(Support Vector Machine)优化的TLD(Track-Learning-Detection)行人检测跟踪算法.将行人作为正样本,背景作为负样本,提取出行人的HOG特征并投入线性SVM中进行训练,得到行人检测分类器,并标定出目标区域,实现行人自动识别;然后在TLD算法的基础上对行人进行跟踪和在线学习,估计检测出的正负样本并实时修正检测器在当前帧中的误检,利用相邻帧间特征点配准剔除误配点,同时更新跟踪器数据,以避免后续出现类似错误.实验表明,该算法能够适应遮挡变化且自动识别并稳定跟踪目标行人,较传统跟踪算法具有更强的鲁棒性.
关键词:支持向量机;行人检测跟踪;TLD
中图分类号:TP391.4 文献标识码:A
文章编号:1674-2974(2016)10-0102-08
Abstract:A new method based on optimized TLD (Track-Learning-Detection) and SVM (Support Vector Machine) for tracking pedestrian was proposed. First, with pedestrians as positive samples and the background as negative samples respectively, HOG (Histogram of Oriented Gradient) descriptor of pedestrian was extracted and combined with linear SVM to train the pedestrian classifier,which was used to obtain the calibrated pedestrian area accurately. Then, adaptive tracking and online learning on the pedestrians on the basis of TLD were integrated to estimate the reliability of the positive and negative samples, to rectify error existing in the current frame caused by detection and to update the tracking data simultaneously to avoid subsequent similar mistakes. The experiment results demonstrate that, compared with the conventional tracking algorithm, the proposed algorithm can not only significantly adapt to occlusions and appearance changes but also automatically identify and track pedestrian targets at arbitrary position, manifesting stronger robustness.
Key words:support vector machine; pedestrian detection and tracking; TLD
在计算机视觉应用中,长期稳定实时检测跟踪运动物体已经成为一个重要的研究课题,随着技术的不断成熟,该领域的应用也相当广泛,比如:工业生产、实时监督、自动目标定位、自动导航、人机交互、增强现实技术、SLAM、游戏开发等.研究人员根据实际应用的需要提出不同的跟踪方案,其中D.Comaniciu等[1]利用改进的mean-shift来跟踪运动物体,该方法可通过迭代步骤找到离跟踪目标最近的位置,但其不能解决目标被遮挡或发生形变等问题,在前后背景颜色相似的环境中,容易发生目标跟丢的情况.Martinez等[2]用背景差分法提取目标,根据轨迹建立数学模型实现行人跟踪,该方法可取得较好的检测效果,但由于计算时间长,跟踪的实时性不能得到保证.季玉……
