In this work, we address the problem of estimating 2d human pose from still images. Recent methods that rely on discriminatively trained deformable parts organized in a tree model have shown to be very successful in solving this task. Within such a pictorial structure framework, we address the problem of obtaining good part templates by proposing novel, non-linear joint regressors. In particular, we employ two-layered random forests as joint regressors. The first layer acts as a discriminative, independent body part classifier. The second layer takes the estimated class distributions of the first one into account and is thereby able to predict joint locations by modeling the interdependence and co-occurrence of the parts. This results in a pose estimation framework that takes dependencies between body parts already for joint localization into account and is thus able to circumvent typical ambiguities of tree structures, such as for legs and arms. In the experiments, we demonstrate that our body parts dependent joint regressors achieve a higher joint localization accuracy than tree-based state-of-the-art methods.
The dark gray rectangle on the l.h.s. illustrates a pictorial structure (PS) model with independent part templates. Each classifier estimates independently the probability that an image region belongs to a specific body part. The light gray rectangle on the r.h.s. illustrates the proposed approach where two layers are used. While the first layer consists of the same independent classifiers, the second layer regresses the locations of the joints in dependency of the independent part classifiers. The confidence maps of the regressed points are more discriminative and resolve the ambiguities between the legs.
Qualitative results on some representative images from the FashionPose and the LSP dataset.
If you have questions concerning the data, please contact Matthias Dantone.
Dantone M., Gall J., Leistner C., and van Gool L., Body Parts Dependent Joint Regressors for Human Pose Estimation in Still Images (PDF), IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 36, No. 11, 2131-2143, 2014. ©IEEE
Dantone M., Gall J., Leistner C., and van Gool L., Body Parts Dependent Joint Regressors for Human Pose Estimation in Still Images - Supplemental Material (PDF)
Dantone M., Gall J., Leistner C., and van Gool L., Body Parts Dependent Joint Regressors for Human Pose Estimation in Still Images - Extended Version (PDF), The extended version combines the article and supplemental material in one document.
Dantone M., Gall J., Leistner C., and van Gool L., Human Pose Estimation using Body Parts Dependent Joint Regressors (PDF), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'13), 3041-3048, 2013. ©IEEE