Articulated pose estimation with flexible mixtures-of-parts

Yang, Yi; Ramanan, Deva

doi:10.1109/cvpr.2011.5995741

Cited by 934 publications

(1,271 citation statements)

References 20 publications

Supporting

Mentioning

1,232

Contrasting

Order By: Relevance

“…Experimental results demonstrate that our approach outperforms the base methods [1], [11]. While our proposed method improves robustness against occlusion in a learning stage of each base method, its pose inference process is performed with no change in our experiments.…”

Section: Introductionmentioning

confidence: 77%

“…In this paper, based on the approach in [1], we explicitly examine the effect of occlusion in appearance modeling. In our model we weight a sample containing an occluded body part in order to mitigate the adverse effect of occlusion.…”

Section: Related Workmentioning

confidence: 99%

“…In the appearance score, w i represents a filter for body part i and φ(I, p i ) is a feature vector (e.g., HOG descriptor [4]) extracted from pixel location p i in I. In a typical example of the deformation score, w i j represents a four dimensional vector specifying coefficients of quadratic function [1]. φ d (p i − p j ) defines the deformation between body parts i and j.…”

Section: Pictorial Structure Modelmentioning

confidence: 99%

“…This section describes the basis of the PSM [2] used in the base models [1], [11] of our implementation. A tree-based model is defined by a set of body parts V and a set of links E connecting two of the body parts.…”

Section: Pictorial Structure Modelmentioning

confidence: 99%

“…We base our approach on the pictorial structure model (PSM) [1]- [3]. The PSM represents a human body configuration as a graphical tree model capturing inter-part spatial relationships such as relative position and orientation, and decomposes appearance of a human body into local part templates.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Occluded Appearance Modeling with Sample Weighting for Human Pose Estimation

Kawana

Ukita

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis paper proposes a method for human pose estimation in still images. The proposed method achieves occlusion-aware appearance modeling. Appearance modeling with less accurate appearance data is problematic because it adversely affects the entire training process. The proposed method evaluates the effectiveness of mitigating the influence of occluded body parts in training sample images. In order to improve occlusion evaluation by a discriminatively-trained model, occlusion images are synthesized and employed with non-occlusion images for discriminative modeling. The score of this discriminative model is used for weighting each sample in the training process. Experimental results demonstrate that our approach improves the performance of human pose estimation in contrast to base models. key words: human pose estimation, pictorial structure models, occlusion

show abstract

Section: Introductionmentioning

confidence: 77%

Section: Related Workmentioning

confidence: 99%

Section: Pictorial Structure Modelmentioning

confidence: 99%

Section: Pictorial Structure Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Occluded Appearance Modeling with Sample Weighting for Human Pose Estimation

Kawana

Ukita

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

Human Pose Estimation

Sigal¹

2014

Computer Vision

View full text Add to dashboard Cite

Computer Vision Metrics

Krig¹

2014

View full text Add to dashboard Cite

Distance From Sensor in meters Depth granularity or resolution in mm Depth granularity or resolution in mm Raw Z depth map Raw YYZ vertex map & Surface normal map 6DOF pose via ICP Volume surface integration 3D surface rendering Volume YYZ vertex map & Surface normal map a. Method of volume integration, 6DOF camera pose, and surface rendering used in KinectFusion [474][475]. Name Middlebury Computer Vision Datasets Description Scholarly and comprehensive datasets, and algorithm comparisons over most of the datasets Categories Stereo vision (excellent), multi-view stereo (excellent), MRF, Optical Flow (excellent), Color processing Contributions Algorithm benchmarks over the datasets can be submitted Key papers Several; see website Owner Middlebury College Link http://vision.middlebury.edu/ Name ADL Activity Recognition Dataset Description Annotated scenes for activity recognition of common living scenes Categories Daily life Tools and apps Activity recognition code available (see link below) Key papers [73] Link http://deepthought.ics.uci.edu/ADLdataset/adl.html Name MIT Indoor Scenes 67, Scene Classification Description Annotated dataset specifically containing diverse indoor scenes Categories 15,620 images organized into 67 indoor categories, some annotations in Labelme format Key papers [74] Link http://web.mit.edu/torralba/www/indoor.html Name RGB-D Object Recognition Dataset, U of W Description Dataset contains RGB and corresponding depth images Categories 300 common household objects, 51 categories using Wordnet similar to Imagenet style (Imagenet dataset reviewed above), each object recorded in RGB and Kinect depth at various rotational angles and viewpoints Key papers [75] Link http://www.cs.washington.edu/rgbd-dataset/ APPENDIX B ■ SurvEy of GrouND TruTh DATASETS 405 Name NYU Depth Datasets Description Annotated dataset of indoor scenes using RGB-D datasets + accelerometer data Categories Over 500,000 frames, many different indoor scenes and scene types, thousands of classes, accelerometer data, inpainted and raw depth information Tools and apps Matlab toolbox + g++ code Key papers [76] Link http://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html Name Intel Labs Seattle -Egocentric Recognition of Handled Objects Description Annotated dataset for egocentric handled objects using a wearable camera Categories Over 42 everyday objects under varied lighting, occlusion, perspectives; over 6GB total video sequence data Key papers [77] [78] Link http://seattle.intel-research.net/~xren/egovision09/ Name Georgia Tech GTEA Egocentric Activities -Gaze(+) Description Annotated dataset for egocentric handled objects using a wearable camera Categories Many everyday objects under varied lighting, occlusion, perspectives Tools and apps Code library of vision functions and mathematical functions Key papers [79] Link http://www.cc.gatech.edu/~afathi3/GTEA_Gaze_Website/ Name CUReT: Columbia-Utrecht Reflectance and Texture Database Description Extensive texture sample and illumination datasets directions Categories Over 60 di...

show abstract

Articulated pose estimation with flexible mixtures-of-parts

Cited by 934 publications

References 20 publications

Occluded Appearance Modeling with Sample Weighting for Human Pose Estimation

Occluded Appearance Modeling with Sample Weighting for Human Pose Estimation

Human Pose Estimation

Computer Vision Metrics

Contact Info

Product

Resources

About