TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking

Reddy, N. Dinesh; Guigues, Laurent; Pishchulin, Leonid; Eledath, Jayan; Narasimhan, Srinivasa G.

doi:10.1109/cvpr46437.2021.01494

Cited by 79 publications

(36 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To evaluate the accuracy of the full architecture, we computed the MPJPE across all the detected keypoints and obtained an error of 23.65 millimeters, again comparable to the one obtained in [15] (e.g., 19.5 millimeters on the same dataset, however with fewer keypoints-the feet were excluded) and also comparable with the error obtained in the best performing recent works about 3D pose estimation (between 19 and 30 millimeters) [40][41][42][43].…”

Section: Keypointssupporting

confidence: 71%

Markerless vs. Marker-Based Gait Analysis: A Proof of Concept Study

Moro

Marchesi

Hesse

et al. 2022

Sensors

View full text Add to dashboard Cite

The analysis of human gait is an important tool in medicine and rehabilitation to evaluate the effects and the progression of neurological diseases resulting in neuromotor disorders. In these fields, the gold standard techniques adopted to perform gait analysis rely on motion capture systems and markers. However, these systems present drawbacks: they are expensive, time consuming and they can affect the naturalness of the motion. For these reasons, in the last few years, considerable effort has been spent to study and implement markerless systems based on videography for gait analysis. Unfortunately, only few studies quantitatively compare the differences between markerless and marker-based systems in 3D settings. This work presented a new RGB video-based markerless system leveraging computer vision and deep learning to perform 3D gait analysis. These results were compared with those obtained by a marker-based motion capture system. To this end, we acquired simultaneously with the two systems a multimodal dataset of 16 people repeatedly walking in an indoor environment. With the two methods we obtained similar spatio-temporal parameters. The joint angles were comparable, except for a slight underestimation of the maximum flexion for ankle and knee angles. Taking together these results highlighted the possibility to adopt markerless technique for gait analysis.

show abstract

Section: Keypointssupporting

confidence: 71%

Markerless vs. Marker-Based Gait Analysis: A Proof of Concept Study

Moro

Marchesi

Hesse

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Reddy et al [252] TesseTrack (bottom-up) 18.70 mm (average MPJPE) JAAD Gujjar and Vaughan [232] Res-EnDec (deep learning) 81.14% (AP) PePScenes Yau et al [235] Graph-SIM (deep learning) 94.40% (accuracy) 3D Pedstria Trajectory Zhong et al [253] SocialGAN (bottom-up) sequences have failed. To address this issue, the latest methods (PoseTrack [254] , HRNer [240] , Exploiting temporal context [255] , HigherHRNet [224] , Efficient human pose estimation (EfficientPose) [246] , Graph-SIM [227] , etc.)…”

Section: Discussionmentioning

confidence: 99%

A Survey of Human Action Recognition and Posture Prediction

Cheung

et al. 2022

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

Human action recognition and posture prediction aim to recognize and predict respectively the action and postures of persons in videos. They are both active research topics in computer vision community, which have attracted considerable attention from academia and industry. They are also the precondition for intelligent interaction and human-computer cooperation, and they help the machine perceive the external environment. In the past decade, tremendous progress has been made in the field, especially after the emergence of deep learning technologies.Hence, it is necessary to make a comprehensive review of recent developments. In this paper, firstly, we attempt to present the background, and then discuss research progresses. Secondly, we introduce datasets, various typical feature representation methods, and explore advanced human action recognition and posture prediction algorithms.Finally, facing the challenges in the field, this paper puts forward the research focus, and introduces the importance of action recognition and posture prediction by taking interactive cognition in self-driving vehicle as an example.

show abstract

“…Local and Absolute 3D Human Pose Estimation. It is popular to estimate the 3D human pose in the local coordinate system (relative to the root) [1,11,12,13,14,15,16,20,24,25,27,30,37,39] where translation is discarded and root rotation is defined in the camera coordinate frame. Among these methods, some focus on lifting 2D keypoints to 3D [1,27], while others use a template 3D human mesh (the SMPL [19] body model and its extensions [26,32]) and jointly recover the body shape and joint angles.…”

Section: Related Workmentioning

confidence: 99%