Pedestrian tracking by learning deep features

Abstract Pedestrian tracking technique is now widely used in many intelligent systems, such as video surveillance, security regions. But many methods suffer from illumination, human posture or human appendant. With the development of Convolutional Neural Networks (CNNs), deep feature can be learned. In this paper, training images will be divided into subregions to reduce the influence of human appendant, such as bags. The remain regions are almost fixed regions. Then these fixed regions will be fed into our CNNs for learning deep features. In order to copy with different sizes of training images, an arbitrarily-sized pooling layer is developed in our CNN architecture. Then, these deeply-learned feature vector can be used in pedestrian recognition. In our work, optical flow is used for pedestrian tracking. Experimental results show our proposed method can achieve pedestrian tracking effectively.

[1]  Valérie Renaudin,et al.  Pedestrian track estimation with handheld monocular camera and inertial-magnetic sensor for urban augmented reality , 2017, 2017 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[2]  Xiaogang Wang,et al.  Joint Deep Learning for Pedestrian Detection , 2013, 2013 IEEE International Conference on Computer Vision.

[3]  Yi Yang,et al.  Weakly Supervised Photo Cropping , 2014, IEEE Transactions on Multimedia.

[4]  Nanning Zheng,et al.  Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Sridhar Lakshmanan,et al.  A motion and shape-based pedestrian detection algorithm , 2003, IEEE IV2003 Intelligent Vehicles Symposium. Proceedings (Cat. No.03TH8683).

[6]  Lei Guo,et al.  When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Bernt Schiele,et al.  New features and insights for pedestrian detection , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Xiang Li,et al.  An enhanced deep feature representation for person re-identification , 2016, 2016 IEEE Winter Conference on Applications of Computer Vision (WACV).

[9]  Meng Wang,et al.  Deep Learning of Scene-Specific Classifier for Pedestrian Detection , 2014, ECCV.

[10]  Xuelong Li,et al.  Fusion of Multichannel Local and Global Structural Cues for Photo Aesthetics Evaluation , 2014, IEEE Transactions on Image Processing.

[11]  Ling Shao,et al.  Face recognition with a small occluded training set using spatial and statistical pooling , 2018, Inf. Sci..

[12]  Quan Pan,et al.  Classifier Fusion With Contextual Reliability Evaluation , 2018, IEEE Transactions on Cybernetics.

[13]  Junwei Han,et al.  Duplex Metric Learning for Image Set Classification , 2018, IEEE Transactions on Image Processing.

[14]  Feiping Nie,et al.  Robust Object Co-Segmentation Using Background Prior , 2018, IEEE Transactions on Image Processing.

[15]  Xuelong Li,et al.  A Review of Co-Saliency Detection Algorithms , 2018 .

[16]  ByoungChul Ko,et al.  Pedestrian Tracking Using Online Boosted Random Ferns Learning in Far-Infrared Imagery for Safe Driving at Night , 2017, IEEE Transactions on Intelligent Transportation Systems.

[17]  Dong Xu,et al.  Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey , 2018, IEEE Signal Processing Magazine.

[18]  Feiping Nie,et al.  Revisiting Co-Saliency Detection: A Novel Approach Based on Two-Stage Multi-View Spectral Rotation Co-clustering , 2017, IEEE Transactions on Image Processing.

[19]  Xiaogang Wang,et al.  Deep Learning Strong Parts for Pedestrian Detection , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[20]  Antonio Fernández-Caballero,et al.  Optical flow or image subtraction in human detection from infrared camera on mobile robot , 2010, Robotics Auton. Syst..