Download presentation
Presentation is loading. Please wait.
Published byFrankie Scollard Modified over 9 years ago
1
Articulated People Detection and Pose Estimation: Reshaping the Future
Leonid Pishchulin Arjun Jain Mykhaylo Andriluka Thorsten Thorm¨ahlen Bernt Schiele Max Planck Institute for Informatics, Saarbr¨ucken, Germany
2
OUTLINE Introduction Generation of novel training examples
Articulated people detection Articulated pose estimation Articulated pose estimation “in the wild” Conclusion
3
Introduction Recent 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 corpora robust image features enable to deal with image clutter, occlusions and appearance variation
4
Introduction
5
Generation of novel training examples
6
Generation of novel training examples
7
Articulated people detection
We use the deformable part model (DPM) [11] and evaluate its performance on the “Image Parsing” dataset [25]. For training we use training sets from the publicly available datasets: DPM-VOC PASCAL VOC 2009 (VOC) [10] DPM-IP “Image Parsing”(IP) [25] DPM-LSP “Leeds Sports Poses” (LSP)dataset [19] DPM-IP-R and DPM-IP-AR [10] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PASCAL visual object classes (VOC) challenge.IJCV’10. [11] P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan.Object detection with discriminatively trained part-based models.PAMI’10. [19] S. Johnson and M. Everingham. Clustered pose and nonlinear appearance models for human pose estimation. In BMVC’10. [25] D. Ramanan. Learning to parse images of articulated objects. In NIPS’06.
8
Articulated people detection
9
Articulated people detection
10
Articulated people detection
11
Articulated pose estimation
Proposes a new joint model for body pose estimation combining pictorial structures [12,14]model with DPM
12
Articulated pose estimation
13
Articulated pose estimation
14
Articulated 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”
15
Articulated pose estimation “in the wild”
16
Articulated pose estimation “in the wild”
17
Conclusion Propose a novel method for automatic generation of training examples Evaluate our data generation method for articulated people detection and pose estimation and show that we significantly improve the performance Propose a joint model
18
Thank you for listening
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.