Deep learning for human part discovery in images

Oliveira, Gabriel L.; Valada, Abhinav; Bollen, Claas; Burgard, Wolfram; Brox, Thomas

doi:10.1109/icra.2016.7487304

Cited by 75 publications

(59 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…See Figure 5 for sample test images and corresponding ground truth (GT) annotation. We use the same train/test split as [25], 2 subjects for training and 4 subjects for test. The amount of data is limited for training deep networks.…”

Section: Segmentation On Freiburg Sitting Peoplementioning

confidence: 99%

“…In [25], the authors introduce a network that outputs a high-resolution segmentation after several layers of upcon-volutions. For a fair comparison, we modify our network to output full resolution by adding one bilinear upsampling layer followed by nonlinearity (ReLU) and a convolutional layer with 3 × 3 filters that outputs 15 × 300 × 300 instead of 15 × 64 × 64 as explained in Section 4.…”

Section: Segmentation On Freiburg Sitting Peoplementioning

confidence: 99%

See 1 more Smart Citation

Learning from Synthetic Humans

Varol

Romero²,

Martín

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

815

737

View full text Add to dashboard Cite

Estimating human pose, shape, and motion from images and videos are fundamental challenges with many applications. Recent advances in 2D human pose estimation use large amounts of manually-labeled training data for learning convolutional neural networks (CNNs). Such data is time consuming to acquire and difficult to extend. Moreover, manual labeling of 3D pose, depth and motion is impractical. In this work we present SURREAL (Synthetic hUmans foR REAL tasks): a new large-scale dataset with synthetically-generated but realistic images of people rendered from 3D sequences of human motion capture data. We generate more than 6 million frames together with ground truth pose, depth maps, and segmentation masks. We show that CNNs trained on our synthetic dataset allow for accurate human depth estimation and human part segmentation in real RGB images. Our results and the new dataset open up new possibilities for advancing person analysis using cheap and large-scale synthetic data.

show abstract

Section: Segmentation On Freiburg Sitting Peoplementioning

confidence: 99%

Section: Segmentation On Freiburg Sitting Peoplementioning

confidence: 99%

Learning from Synthetic Humans

Varol

Romero²,

Martín

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

815

737

View full text Add to dashboard Cite

show abstract

“…[28][29][30] Also, there is the more challenging task of simultaneous annotation of multiple people [17,31]. In addition, there is work like that of Oliveira et al [32] that performs human part segmentation based on fully convolutional networks [23]. Our work focuses solely on the task of keypoint localization of a single person's pose from an RGB image.…”

Section: Related Workmentioning

confidence: 99%

Stacked Hourglass Networks for Human Pose Estimation

Newell

Yang

Deng

2016

Computer Vision – ECCV 2016

3,881

4,005

View full text Add to dashboard Cite

Abstract. This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a "stacked hourglass" network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods. Keywords: Human Pose Estimation

show abstract

“…test the performance of our hybrid tracker against the method in [3] on our augmented test set to examine the how much our Fast-FCN based filtering improves overall tracking accuracy. We then compare the Fast-FCN architecture against the larger U-Net [23] and VGG-FCN [25] models and show that our simpler model performs almost as well as the U-Net and better than VGG-FCN in this context while being much faster. We also report raw segmentation performance on this dataset for all three models.…”

Section: Methodsmentioning

confidence: 99%

“…In [26] [24] [25] [34], researchers developed FCN architectures by adding deconvolve layers based on the VGG-16 [35] classification network. Thus, we chose the VGG-FCN structure proposed in [25] for body part labeling as our second comparison. We rebuilt the structure of these networks, and only modified the sizes to fit our dataset.…”

Section: Architecture Comparisonmentioning

confidence: 99%

Part Segmentation for Highly Accurate Deformable Tracking in Occlusions via Fully Convolutional Neural Networks

Wan

Walsman

Fox

2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Successfully tracking the human body is an important perceptual challenge for robots that must work around people. Existing methods fall into two broad categories: geometric tracking and direct pose estimation using machine learning. While recent work has shown direct estimation techniques can be quite powerful, geometric tracking methods using point clouds can provide a very high level of 3D accuracy which is necessary for many robotic applications. However these approaches can have difficulty in clutter when large portions of the subject are occluded. To overcome this limitation, we propose a solution based on fully convolutional neural networks (FCN). We develop an optimized Fast-FCN network architecture for our application which allows us to filter observed point clouds and improve tracking accuracy while maintaining interactive frame rates. We also show that this model can be trained with a limited number of examples and almost no manual labelling by using an existing geometric tracker and data augmentation to automatically generate segmentation maps. We demonstrate the accuracy of our full system by comparing it against an existing geometric tracker, and show significant improvement in these challenging scenarios.

show abstract

Deep learning for human part discovery in images

Cited by 75 publications

References 18 publications

Learning from Synthetic Humans

Learning from Synthetic Humans

Stacked Hourglass Networks for Human Pose Estimation

Part Segmentation for Highly Accurate Deformable Tracking in Occlusions via Fully Convolutional Neural Networks

Contact Info

Product

Resources

About