Single-shot 3D multi-person pose estimation in complex images

Benzine, Abdallah; Luvison, Bertrand; Pham, Quoc Cuong; Achard, Catherine

doi:10.1016/j.patcog.2020.107534

Cited by 24 publications

(14 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, it would be interesting to explore the extension of the proposed framework to perform 3D pose estimation as part of our future research. In accordance with recent studies, 3D pose projection from 2D images can be achieved, either by employing geometric relationships between 2D keypoint positions and 3D human pose models [58], or by leveraging occlusion-robust pose-maps (ORPM) in combination with annotated 3D poses [3,31].…”

Section: Avenues For Further Researchsupporting

confidence: 53%

EfficientPose: Scalable single-person pose estimation

2020

View full text Add to dashboard Cite

Single-person human pose estimation facilitates markerless movement analysis in sports, as well as in clinical applications. Still, state-of-the-art models for human pose estimation generally do not meet the requirements of real-life applications. The proliferation of deep learning techniques has resulted in the development of many advanced approaches. However, with the progresses in the field, more complex and inefficient models have also been introduced, which have caused tremendous increases in computational demands. To cope with these complexity and inefficiency challenges, we propose a novel convolutional neural network architecture, called EfficientPose, which exploits recently proposed EfficientNets in order to deliver efficient and scalable single-person pose estimation. EfficientPose is a family of models harnessing an effective multi-scale feature extractor and computationally efficient detection blocks using mobile inverted bottleneck convolutions, while at the same time ensuring that the precision of the pose configurations is still improved. Due to its low complexity and efficiency, EfficientPose enables real-world applications on edge devices by limiting the memory footprint and computational cost. The results from our experiments, using the challenging MPII single-person benchmark, show that the proposed EfficientPose models substantially outperform the widely-used OpenPose model both in terms of accuracy and computational efficiency. In particular, our top-performing model achieves state-of-the-art accuracy on single-person MPII, with low-complexity ConvNets.

show abstract

Section: Avenues For Further Researchsupporting

confidence: 53%

EfficientPose: Scalable single-person pose estimation

2020

View full text Add to dashboard Cite

show abstract

“…Table 3 provides 3DPCK results according to the distance of people to the camera. PandaNet outperforms the model of Benzine et al [3] on all camera distances demon-Dist. <10 10-20 20-30 30-40 >40 All [3] 55.…”

Section: Comparison With Prior Workmentioning

confidence: 85%

“…Mehta et al [28] propose a bottomup approach system that predicts Occlusion-Robust Pose Maps (ORPM) and Part Affinity Fields [4] to manage multiperson 3D pose estimation even for occluded and cropped people. Benzine et al [2,3] perform single-shot multiperson 3D pose estimation by extending the 2D multiperson model in [31] to predict ORPM. ORPM based methods predict a fixed number of 2D heatmaps and ORPM, whatever the number of people in the image.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation

Benzine,

Chabot,

Luvison

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Figure 1: Qualitative results of PandaNet on JTA dataset [8] which consists in images with many people (up to 60), a large proportion of people at low resolution and many occlusion situations. Most of the previous 3D human pose estimation studies mainly focused on the single-person case or estimate 3D pose of few people at high resolution. In this paper, we propose an anchor-based and single-shot multi-person 3D pose estimation framework that allows the pose estimation of a large number of people at low resolution. Ground-truth translations and scales are used for visualisation.

show abstract

“…However, 3D pose estimation in this manner is extremely challenging due to depth ambiguities and occlusions from objects. Recent algorithms based on machine learning networks have achieved 3D pose estimation from single RGB images, demonstrating the reconstruction of multiple people that is robust to occlusions, in real-time, and in both controlled and uncontrolled environments [32][33][34][35][36][37][38][39] . Ref.…”

Section: Introductionmentioning

confidence: 99%

Real-time, low-cost multi-person 3D pose estimation

Ruget,

Tyler,

Martín

et al. 2021

Preprint

View full text Add to dashboard Cite

The process of tracking human anatomy in computer vision is referred to pose estimation, and it is used in fields ranging from gaming to surveillance. Three-dimensional pose estimation traditionally requires advanced equipment, such as multiple linked intensity cameras or high-resolution time-of-flight cameras to produce depth images. However, there are applications, e.g. consumer electronics, where significant constraints are placed on the size, power consumption, weight and cost of the usable technology. Here, we demonstrate that computational imaging methods can achieve accurate pose estimation and overcome the apparent limitations of time-of-flight sensors designed for much simpler tasks. The sensor we use is already widely integrated in consumer-grade mobile devices, and despite its low spatial resolution, only 4×4 pixels, our proposed Pixels2Pose system transforms its data into accurate depth maps and 3D pose data of multiple people up to a distance of 3 m from the sensor. We are able to generate depth maps at a resolution of 32×32 and 3D localization of a body parts with an error of only ≈10 cm at a frame rate of 7 fps. This work opens up promising real-life applications in scenarios that were previously restricted by the advanced hardware requirements and cost of time-of-flight technology.

show abstract

Single-shot 3D multi-person pose estimation in complex images

Cited by 24 publications

References 50 publications

EfficientPose: Scalable single-person pose estimation

EfficientPose: Scalable single-person pose estimation

PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation

Real-time, low-cost multi-person 3D pose estimation

Contact Info

Product

Resources

About