Data augmentation method for improving the accuracy of human pose estimation with cropped images

Park, Soonchan; Lee, Sang-Baek; Park, Jinah

doi:10.1016/j.patrec.2020.06.015

Cited by 27 publications

(12 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All the above augmentation operations are generally applicable for many different computer vision tasks. Besides, pose-specific augmentation techniques [40,79,57] have been proposed additionally. Specifically, in the real world, it is often the case that human body joints are obscured by other objects; In crowded scenes, there may be multiple joints of the same class that can greatly confuse a model.…”

Section: Random Data Augmentationmentioning

confidence: 99%

See 1 more Smart Citation

Single Person Pose Estimation: A Survey

Zhang,

Zhu,

Wang

2021

Preprint

View full text Add to dashboard Cite

Human pose estimation in unconstrained images and videos is a fundamental computer vision task. To illustrate the evolutionary path in technique, in this survey we summarize representative human pose methods in a structured taxonomy, with a particular focus on deep learning models and single-person image setting. Specifically, we examine and survey all the components of a typical human pose estimation pipeline, including data augmentation, model architecture and backbone, supervision representation, post-processing, standard datasets, evaluation metrics. To envisage the future directions, we finally discuss the key unsolved problems and potential trends for human pose estimation.

show abstract

Section: Random Data Augmentationmentioning

confidence: 99%

“…Generic data augmentation [75,60] Pose-specific data augmentation [40,79,57] Optimized data augmentation Neural Architecture Search (NAS) based methods [35] Generative Adversarial Network (GAN) based methods [58] Deep human pose model…”

Section: Random Data Augmentationmentioning

confidence: 99%

Single Person Pose Estimation: A Survey

Zhang,

Zhu,

Wang

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…e original data use 10,000 images as the training set and 3,466 images as the test set. Data augmentation [20,21] can be used to increase the number of training samples to effectively improve the performance of the convolutional neural network. To be consistent with the actual facts, we set the left 15-degree and right 12-degree center rotation (the label coordinates should also be rotated), and the rotation method is given in formula (8), where θ is the rotation angle.…”

Section: Datasetmentioning

confidence: 99%

Face Alignment Algorithm Based on an Improved Cascaded Convolutional Neural Network

Duan

Wang

2021

Advances in Multimedia

View full text Add to dashboard Cite

Aiming at the problem of a large number of parameters and high time complexity caused by the current deep convolutional neural network models, an improved face alignment algorithm of a cascaded convolutional neural network (CCNN) is proposed from the network structure, random perturbation factor (shake), and data scale. The algorithm steps are as follows: 3 groups of lightweight CNNs are designed; the first group takes facial images with face frame as input, trains 3 CNNs in parallel, and weighted outputs the facial images with 5 facial key points (anchor points). Then, the anchor points and 2 different windows with a shake mechanism are used to crop out 10 partial images of human faces. The networks in the second group train 10 CNNs in parallel and every 2 networks’ weighted average and colocated a key point. Based on the second group of networks, the third group designed a smaller shake mechanism and windows, to achieve more fine-tuning. When training the network, the idea of parallel within groups and serial between groups is adopted. Experiments show that, on the LFPW face dataset, the improved CCNN in this paper is superior to any other algorithm of the same type in positioning speed, algorithm parameter amount, and test error.

show abstract

“…Generally, pose estimation performance under truncation has not been studied extensively in the literature. Recent work by Park et al [44] uses cropping data Fig. 2.…”

Section: Truncated Pose Estimationmentioning

confidence: 99%

MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation

Sárándi,

Linder,

Arras

et al. 2020

Preprint

View full text Add to dashboard Cite

Heatmap representations have formed the basis of human pose estimation systems for many years, and their extension to 3D has been a fruitful line of recent research. This includes 2.5D volumetric heatmaps, whose X and Y axes correspond to image space and Z to metric depth around the subject. To obtain metric-scale predictions, 2.5D methods need a separate post-processing step to resolve scale ambiguity. Further, they cannot localize body joints outside the image boundaries, leading to incomplete estimates for truncated images. To address these limitations, we propose metric-scale truncation-robust (MeTRo) volumetric heatmaps, whose dimensions are all defined in metric 3D space, instead of being aligned with image space. This reinterpretation of heatmap dimensions allows us to directly estimate complete, metric-scale poses without test-time knowledge of distance or relying on anthropometric heuristics, such as bone lengths. To further demonstrate the utility our representation, we present a differentiable combination of our 3D metric-scale heatmaps with 2D image-space ones to estimate absolute 3D pose (our MeTRAbs architecture). We find that supervision via absolute pose loss is crucial for accurate non-root-relative localization. Using a ResNet-50 backbone without further learned layers, we obtain state-of-the-art results on Human3.6M, MPI-INF-3DHP and MuPoTS-3D. Our code is publicly available.

show abstract

Data augmentation method for improving the accuracy of human pose estimation with cropped images

Cited by 27 publications

References 3 publications

Single Person Pose Estimation: A Survey

Single Person Pose Estimation: A Survey

Face Alignment Algorithm Based on an Improved Cascaded Convolutional Neural Network

MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation

Contact Info

Product

Resources

About