Top-Down System for Multi-Person 3D Absolute Pose Estimation from Monocular Videos

Kaid, Amal El; Brazey, Denis; Barra, Vincent; Bäına, Karim

doi:10.3390/s22114109

Cited by 8 publications

(8 citation statements)

References 89 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the same comparison context and beyond the ground truth accuracy, Table 4 illustrates another comparison, using the matched ground truth accuracy as a parameter, with Refs. 62 and 60; therefore, the suggested method surpasses existing 3D multi-person position recognition algorithms by a wide margin. However, there is still significant opportunity for improvement.…”

Section: Numerical Resultsmentioning

confidence: 91%

HPAR: deep neural network-based approach for human pose-activity recognition

et al. 2023

View full text Add to dashboard Cite

.Human pose activity recognition (HPAR) offers a wide range of applications due to the widespread use of collection devices such as smartphones and video cameras, as well as its capacity to gather human activity data. Electronic devices and applications continue to evolve, and breakthroughs in artificial intelligence (AI) have transformed the capacity to extract deeply buried information for accurate recognition and interpretation. We propose a systematic design for integrating conventional networks and constraints into the attention framework for learning long-range dependencies, thereby achieving end-to-end pose estimation with flexibility and scalability. The proposed method modifies the temporal receptive field using a multi-scale structure of dilated convolutions and can be adapted to a causal model for real-time performance. Our approach achieves state-of-the-art performance on the task of three-dimensional HPAR and outperforms previous methods while maintaining a lower complexity cost.

show abstract

Section: Numerical Resultsmentioning

confidence: 91%

HPAR: deep neural network-based approach for human pose-activity recognition

et al. 2023

View full text Add to dashboard Cite

show abstract

“…[169] introduces a two-stage pipeline and presents a unified framework that combines YOLOv5, HRNet, and TCN for real-time 2D/3D human pose estimation. In the work presented in [170], a similar pipeline was pursued, but it was expanded by incorporating a root depth estimator, a feature not present in the approach outlined in [169]. This incorporation enables the system to derive camera-centric coordinates and integrates YOLOv3 for human detection, HRNet as the 2D pose estimator, and GAST-Net for 3D root-relative pose reconstruction.…”

Section: Unified Framework For Real-time Applicationsmentioning

confidence: 99%

“…Adopting a top-down approach similar to Refs. [169,170], Dong et al [171] proposed an approach for multi-person 3D pose estimation. However, a notable distinction lies in their consideration of multiple views instead of a monocular view.…”

Section: Unified Framework For Real-time Applicationsmentioning

confidence: 99%

A Systematic Review of Recent Deep Learning Approaches for 3D Human Pose Estimation

El Kaid,

Baïna

2023

J. Imaging

Self Cite

View full text Add to dashboard Cite

Three-dimensional human pose estimation has made significant advancements through the integration of deep learning techniques. This survey provides a comprehensive review of recent 3D human pose estimation methods, with a focus on monocular images, videos, and multi-view cameras. Our approach stands out through a systematic literature review methodology, ensuring an up-to-date and meticulous overview. Unlike many existing surveys that categorize approaches based on learning paradigms, our survey offers a fresh perspective, delving deeper into the subject. For image-based approaches, we not only follow existing categorizations but also introduce and compare significant 2D models. Additionally, we provide a comparative analysis of these methods, enhancing the understanding of image-based pose estimation techniques. In the realm of video-based approaches, we categorize them based on the types of models used to capture inter-frame information. Furthermore, in the context of multi-person pose estimation, our survey uniquely differentiates between approaches focusing on relative poses and those addressing absolute poses. Our survey aims to serve as a pivotal resource for researchers, highlighting state-of-the-art deep learning strategies and identifying promising directions for future exploration in 3D human pose estimation.

show abstract

“…Over the past few years, deep neural networks have achieved state-of-the-art performance in computer vision [1][2][3][4], natural language processing [5][6][7], reinforcement learning [8][9][10], and various other fields [11][12][13]. However, with the increasing depth, as well as the width of the network, for example from the shallow LeNet to the wider Inception structure in GoogLeNet and deeper Resnet convolutional architecture, as well as the currently popular transformer architecture, the number of parameters of the deep model is constantly growing, which in turn, leads to a series of problems such as the redundancy of network parameters, more rigorous hardware requirements, and difficulty in training the model, and large deep models severely limit their applications in low-memory or high-real-time conditions.…”

Section: Introductionmentioning

confidence: 99%

Collaborative Consistent Knowledge Distillation Framework for Remote Sensing Image Scene Classification Network

Xing

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

For remote sensing image scene classification tasks, the classification accuracy of the small-scale deep neural network tends to be low and fails to achieve accuracy in real-world application scenarios. However, although large deep neural networks can improve the classification accuracy of remote sensing image scenes to some extent, the corresponding deep neural networks also have more parameters and cannot be used on existing embedded devices. The main reason for this is that there are a large number of redundant parameters in large deep networks, which directly leads to the difficulty of application on embedded devices and also reduces the classification speed. Considering the contradiction between hardware equipment and classification accuracy requirements, we propose a collaborative consistent knowledge distillation method for improving the classification accuracy of remote sensing image scenes on embedded devices, called CKD. In essence, our method addresses two aspects: (1) We design a multi-branch fused redundant feature mapping module, which significantly improves the parameter redundancy problem. (2) To improve the classification accuracy of the deep model on embedded devices, we propose a knowledge distillation method based on mutually supervised learning. Experiments were conducted on two remote sensing image classification datasets, SIRI-WHU and NWPU-RESISC45, and the experimental results showed that our approach significantly reduced the number of redundant parameters in the deep network; the number of parameters decreased from 1.73 M to 0.90 M. In addition, compared to a series of student sub-networks obtained based on the existing different knowledge distillation methods, the performance of the student sub-networks obtained by CKD for remote sensing scene classification was significantly improved on two different datasets, with an average accuracy of 0.943 and 0.916, respectively.

show abstract

Top-Down System for Multi-Person 3D Absolute Pose Estimation from Monocular Videos

Cited by 8 publications

References 89 publications

HPAR: deep neural network-based approach for human pose-activity recognition

HPAR: deep neural network-based approach for human pose-activity recognition

A Systematic Review of Recent Deep Learning Approaches for 3D Human Pose Estimation

Collaborative Consistent Knowledge Distillation Framework for Remote Sensing Image Scene Classification Network

Contact Info

Product

Resources

About