Traffic Police Pose Estimation Based on Multi-branch Network

To precisely recognizing traffic police gesture, a two-branch multi-stage convolutional neural network (CNN) and an BP neural network (BPNN) classifier has been adopted to achieve the task of traffic police pose estimation in this paper. We simultaneously detect the human joints and associate body parts. When the detection work is done, a BPNN cascades after CNN and serve as a classifier. The experiment results show that traffic police-men's gestures are well recognized by this method.

[1]  Alan L. Yuille,et al.  Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations , 2014, NIPS.

[2]  Daniel P. Huttenlocher,et al.  Pictorial Structures for Object Recognition , 2004, International Journal of Computer Vision.

[3]  Christian Szegedy,et al.  DeepPose: Human Pose Estimation via Deep Neural Networks , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Peter V. Gehler,et al.  DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Bernt Schiele,et al.  DeeperCut: A Deeper, Stronger, and Faster Multi-person Pose Estimation Model , 2016, ECCV.

[6]  Martin A. Fischler,et al.  The Representation and Matching of Pictorial Structures , 1973, IEEE Transactions on Computers.

[7]  Yaser Sheikh,et al.  OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Tsuhan Chen,et al.  Pictorial structures for object recognition and part labeling in drawings , 2011, 2011 18th IEEE International Conference on Image Processing.

[10]  Shai Avidan.  Ensemble Tracking , 2007, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  D. West.  Introduction to Graph Theory , 1995 .

[12]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[13]  Gang Yu,et al.  Cascaded Pyramid Network for Multi-person Pose Estimation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.