Presentation on theme: "Articulated People Detection and Pose Estimation: Reshaping the Future"— Presentation transcript:
1Articulated People Detection and Pose Estimation: Reshaping the Future Leonid Pishchulin Arjun Jain Mykhaylo AndrilukaThorsten Thorm¨ahlen Bernt SchieleMax Planck Institute for Informatics, Saarbr¨ucken, Germany
2OUTLINE Introduction Generation of novel training examples Articulated people detectionArticulated pose estimationArticulated pose estimation “in the wild”Conclusion
3IntroductionRecent progress in people detection and articulated pose estimation may be contributed to two key factors.Discriminative learning allows to learn powerful models on a large training corporarobust image features enable to deal with image clutter, occlusions and appearance variation
7Articulated people detection We use the deformable part model (DPM)  and evaluate its performance on the “Image Parsing” dataset .For training we use training sets from the publicly available datasets:DPM-VOC PASCAL VOC 2009 (VOC) DPM-IP “Image Parsing”(IP) DPM-LSP “Leeds Sports Poses” (LSP)dataset DPM-IP-R and DPM-IP-AR M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PASCAL visual object classes (VOC) challenge.IJCV’10. P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan.Object detection with discriminatively trained part-based models.PAMI’10. S. Johnson and M. Everingham. Clustered pose and nonlinear appearance models for human pose estimation. In BMVC’10. D. Ramanan. Learning to parse images of articulated objects. In NIPS’06.
14Articulated pose estimation “in the wild” We define a new dataset based on the LSP by using the publicly available original non-cropped images. This dataset, in the following denoted as “multi-scale LSP”
17ConclusionPropose a novel method for automatic generation of training examplesEvaluate our data generation method for articulated people detection and pose estimation and show that we significantly improve the performancePropose a joint model