Deep neural networks for human pose estimation from a very low resolution depth image

Szczuko, Piotr

doi:10.1007/s11042-019-7433-7

Cited by 21 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By converting it to the frequency domain and using the Fast Fourier Transform (FFT), we sample all 512 points. Since the number of human fingers per palm is always less than six, only the first six frequencies (F 1 -F 6 ) need to be considered and described as in Equations (11)(12)(13)(14):…”

Section: Methodsmentioning

confidence: 99%

Smart Living: An Interactive Control System for Household Appliances

Chen

Arifai

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Hand-gesture based control has enormous potential both theoretically and for practical applications due to its convenience and intuitiveness. This study presents a real-time interactive control system for household appliances. The interactive control system allowing wireless control of household appliances using a combination of 11 hand gestures and 2 waving motions is tested on hundreds of samples. It is implemented using a regular personal computer (PC) and existing digital single processing (DSP) platforms. The evaluation results show that the system performs efficiently reaching an accuracy recognition rate of 91% and spending around 30 seconds to complete the control operation for household appliances. The contributions of this work are both academic (1) successful demonstration of the integration of algorithms for solving image detection, processing, and pattern recognition, and practical (2) showing its feasibility and using commonly available hardware and software configurations for practical uses, and finally (3) establishing a mechanism for intuitively interactive control system that facilitates smart living.INDEX TERMS Smart home, human computer interaction, hand gesture recognition, household appliance control.

show abstract

Section: Methodsmentioning

confidence: 99%

Smart Living: An Interactive Control System for Household Appliances

Chen

Arifai

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…HUMAN4D enables research to human pose-related computer vision tasks by providing spatio-temporally aligned RGBD data from multiple views under a HW-SYNC setting, along with accurate 3D and 2D poses. Recent research efforts are devoted on various single-and multi-person pose estimation approaches, from single RGB in the wild [18], [57]- [59], depth [60], [61], multi-view RGB [23], [62] and multiview RGBD [22], [63], among others. However, the selection criteria of the methods we benchmark are to be open-source and applicable to HUMAN4D, producing baseline results for our dataset.…”

Section: Pose Estimationmentioning

confidence: 99%

HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media

et al. 2020

View full text Add to dashboard Cite

We introduce HUMAN4D, a large and multimodal 4D dataset that contains a variety of human activities simultaneously captured by a professional marker-based MoCap, a volumetric capture and an audio recording system. By capturing 2 female and 2 male professional actors performing various fullbody movements and expressions, HUMAN4D provides a diverse set of motions and poses encountered as part of single-and multi-person daily, physical and social activities (jumping, dancing, etc.), along with multi-RGBD (mRGBD), volumetric and audio data. Despite the existence of multi-view color datasets captured with the use of hardware (HW) synchronization, to the best of our knowledge, HUMAN4D is the first and only public resource that provides volumetric depth maps with high synchronization precision due to the use of intra-and inter-sensor HW-SYNC. Moreover, a spatio-temporally aligned scanned and rigged 3D character complements HUMAN4D to enable joint research on time-varying and highquality dynamic meshes. We provide evaluation baselines by benchmarking HUMAN4D with state-of-theart human pose estimation and 3D compression methods. We apply OpenPose and AlphaPose reaching 70.02% and 82.95% mAP PCKh-0.5 on single-and 68.48% and 73.94% mAP PCKh-0.5 on two-person 2D pose estimation, respectively. In 3D pose, a recent multi-view approach named Learnable Triangulation, achieves 80.26% mAP PCK3D-10cm. For 3D compression, we benchmark Draco, Corto and CWIPC open-source 3D codecs, respecting online encoding and steady bit-rates between 7-155 and 2-90 Mbps for mesh-and pointbased volumetric video, respectively. Qualitative and quantitative visual comparison between mesh-based volumetric data reconstructed in different qualities and captured RGB, showcases the available options with respect to 4D representations. HUMAN4D is introduced to enable joint research on spatio-temporally aligned pose, volumetric, mRGBD and audio data cues. The dataset and its code are available online.

show abstract

“…Chen et al [24] propose to use generative adversarial networks to exploit the constrained human-pose distribution for improving single-person pose estimation. Szczuko proposes to localize single-person body joints in 3D space based on a single low resolution depth image [25].…”

Section: Deep Neural Network For Single Person Pose Estimationmentioning

confidence: 99%

“…In addition, the accuracy of non-deep neural network approaches is lower than the following deep neural network approaches [16,18]. The single person pose estimation works with the guarantee of only one person present in the image [16][17][18][19][20][21][22][23][24][25]35,36]. However, the scenes with multi-person are exceedingly common in our daily life.…”

Section: Information Used For Human Pose Estimationmentioning

confidence: 99%

Multi-Person Pose Estimation using an Orientation and Occlusion Aware Deep Learning Network

Zhang

Kamijo

2020

Sensors

View full text Add to dashboard Cite

Image based human behavior and activity understanding has been a hot topic in the field of computer vision and multimedia. As an important part, skeleton estimation, which is also called pose estimation, has attracted lots of interests. For pose estimation, most of the deep learning approaches mainly focus on the joint feature. However, the joint feature is not sufficient, especially when the image includes multi-person and the pose is occluded or not fully visible. This paper proposes a novel multi-task framework for the multi-person pose estimation. The proposed framework is developed based on Mask Region-based Convolutional Neural Networks (R-CNN) and extended to integrate the joint feature, body boundary, body orientation and occlusion condition together. In order to further improve the performance of the multi-person pose estimation, this paper proposes to organize the different information in serial multi-task models instead of the widely used parallel multi-task network. The proposed models are trained on the public dataset Common Objects in Context (COCO), which is further augmented by ground truths of body orientation and mutual-occlusion mask. Experiments demonstrate the performance of the proposed method for multi-person pose estimation and body orientation estimation. The proposed method can detect 84.6% of the Percentage of Correct Keypoints (PCK) and has an 83.7% Correct Detection Rate (CDR). Comparisons further illustrate the proposed model can reduce the over-detection compared with other methods.

show abstract

Deep neural networks for human pose estimation from a very low resolution depth image

Cited by 21 publications

References 25 publications

Smart Living: An Interactive Control System for Household Appliances

Smart Living: An Interactive Control System for Household Appliances

HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media

Multi-Person Pose Estimation using an Orientation and Occlusion Aware Deep Learning Network

Contact Info

Product

Resources

About