Pictorial structures revisited: People detection and articulated pose estimation
Top Cited Papers
- 1 June 2009
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1014-1021
- https://doi.org/10.1109/cvpr.2009.5206754
Abstract
Non-rigid object detection and articulated pose estimation are two related and challenging problems in computer vision. Numerous models have been proposed over the years and often address different special cases, such as pedestrian detection or upper body pose estimation in TV footage. This paper shows that such specialization may not be necessary, and proposes a generic approach based on the pictorial structures framework. We show that the right selection of components for both appearance and spatial modeling is crucial for general applicability and overall performance of the model. The appearance of body parts is modeled using densely sampled shape context descriptors and discriminatively trained AdaBoost classifiers. Furthermore, we interpret the normalized margin of each classifier as likelihood in a generative model. Non-Gaussian relationships between parts are represented as Gaussians in the coordinate system of the joint between parts. The marginal posterior of each part is inferred using belief propagation. We demonstrate that such a model is equally suitable for both detection and pose estimation tasks, outperforming the state of the art on three recently proposed datasets.Keywords
This publication has 16 references indexed in Scilit:
- A Study of Parts-Based Object Class Detection Using Complete GraphsInternational Journal of Computer Vision, 2009
- Training Deformable Models for LocalizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose EstimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- 3D People Tracking with Gaussian Process Dynamical ModelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Multiple Object Class Detection with a Generative ModelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- A performance evaluation of local descriptorsIeee Transactions On Pattern Analysis and Machine Intelligence, 2005
- Image Parsing: Unifying Segmentation, Detection, and RecognitionInternational Journal of Computer Vision, 2005
- Pedestrian Detection in Crowded ScenesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- An Evaluation of Local Shape-Based Features for Pedestrian DetectionPublished by British Machine Vision Association and Society for Pattern Recognition ,2005
- Detecting pedestrians using patterns of motion and appearancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003