3-Layer specific pedestrian continuous tracking framework

Pedestrian tracking is an important research direction and hot spot in the field of machine vision. In this paper a 3-layer specific pedestrian continuous tracking framework based on secondary feature extraction is proposed. Firstly, we give the image features set used in secondary feature extraction, as well as feature set difference measurement method and online feature weight Adjustment method. Secondly, a 3-layer continuous frame framework is described in detail: detection layer, tracking layer and management layer, and the pedestrian tracking tasks can be executed quickly and efficiently. Experiments show that this framework can complete the pedestrian tracking task in realtime and robustly.

[1]  Grzegorz Cielniak,et al.  Improved data association and occlusion handling for vision-based people tracking by mobile robots , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Huosheng Hu,et al.  Multimodal People Tracking and Identification for Service Robots , 2008, Int. J. Inf. Acquis..

[3]  A. G. Amitha Perera,et al.  A unified framework for tracking through occlusions and across sensor gaps , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  Sebastian Lang,et al.  Audiovisual Person Tracking with a Mobile Robot , 2004 .

[5]  Stefan Roth,et al.  People-tracking-by-detection and people-detection-by-tracking , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Huiyu Zhou,et al.  Age classification using Radon transform and entropy based scaling SVM , 2011, BMVC.

[7]  Dariu Gavrila,et al.  Multi-cue Pedestrian Detection and Tracking from a Moving Vehicle , 2007, International Journal of Computer Vision.

[8]  Bastian Leibe,et al.  Multi-person Tracking with Sparse Detection and Continuous Segmentation , 2010, ECCV.

[9]  Hai Tao,et al.  Object Tracking with Bayesian Estimation of Dynamic Layer Representations , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Hao Wang,et al.  Human Detection Algorithm Based on Edge Symmetry , 2014, RiTA.

[11]  Robert T. Collins,et al.  Multi-target Data Association by Tracklets with Unsupervised Parameter Estimation , 2008, BMVC.

[12]  Horst Bischof,et al.  Real-Time Tracking via On-line Boosting , 2006, BMVC.

[13]  Huiyu Zhou,et al.  Object tracking using SIFT features and mean shift , 2009, Comput. Vis. Image Underst..

[14]  Dietrich Paulus,et al.  An Evaluation of Open Source SURF Implementations , 2010, RoboCup.

[15]  Hao Wang,et al.  Generalized linear discriminant analysis based on euclidean norm for gait recognition , 2018, Int. J. Mach. Learn. Cybern..