Multi-Person Pose Estimation for PoseTrack with Enhanced Part Affinity Fields

This paper is a description for method we adopted in the competition of “PoseTrack, ICCV 2017 workshop” [1]. We presents an improved approach based on Part Affinity Fields (PAFs) [2]. To achieve a better performance on PoseTrack benchmark, several modifications are proposed, including pre-training model on COCO [3], rethinking the network structure and redundant PAFs. As a result, the framework obtains a significant improvement comparing to baseline methods. Moreover, inspired by semantic segmentation, we conduct some experiments using the hole algorithm and DenseNet, which achieves a desirable performance. Our submission achieves 72.5% mAP on PoseTrack validation dataset and 68.3% on Posetrack benchmark.

[1]  Zhiao Huang,et al.  Associative Embedding: End-to-End Learning for Joint Detection and Grouping , 2016, NIPS.

[2]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

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

[4]  Varun Ramakrishna,et al.  Convolutional Pose Machines , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[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]  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).

[9]  Juergen Gall,et al.  PoseTrack: Joint Multi-person Pose Estimation and Tracking , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Cewu Lu,et al.  RMPE: Regional Multi-person Pose Estimation , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[11]  Kilian Q. Weinberger,et al.  Multi-Scale Dense Convolutional Networks for Efficient Prediction , 2017, ArXiv.

[12]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Jun Fu,et al.  Stacked Deconvolutional Network for Semantic Segmentation , 2017, IEEE transactions on image processing : a publication of the IEEE Signal Processing Society.