检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ludwig, Katja Lorenz, Julian Kienzle, Daniel Bui, Tuan Lienhart, Rainer Chair for Machine Learning & Computer Vision University of Augsburg Germany

The basic body shape (i.e., the body shape in T-pose) of a person does not change within a single video. However, most SOTA human mesh estimation (HME) models output a slightly different, thus inconsistent basic body shape for each video frame. Furthermore, we find that SOTA 3D human pose estimation (HPE) models outperform HME models regarding the precision of the estimated 3D keypoint positions. We solve the problem of inconsistent body shapes by leveraging anthropometric measurements like taken by tailors from humans. We create a model called A2B that converts given anthropometric measurements to basic body shape parameters of human mesh models. We obtain superior and consistent human meshes by combining the A2B model results with the keypoints of 3D HPE models using inverse kinematics. We evaluate our approach on challenging datasets like ASPset or fit3D, where we can lower the MPJPE by over 30 mm compared to SOTA HME models. Further, replacing estimates of the body shape parameters from existing HME models with A2B results not only increases the performance of these HME models, but also guarantees consistent body shapes. Copyright © 2024, The Authors. All rights reserved.

关键词： Anthropometry

来源：评论

学校读者我要写书评

暂无评论

Impact of Pseudo Depth on Open World Object Segmentation with Minimal User Guidance

Impact of Pseudo Depth on Open World Object Segmentation wit...

引用

IEEE computer Society Conference on computer vision and Pattern Recognition Workshops (CVPRW)

作者： Robin Schön Katja Ludwig Rainer Lienhart Chair for Machine Learning and Computer Vision University of Augsburg

Pseudo depth maps are depth map predicitions which are used as ground truth during training. In this paper we leverage pseudo depth maps in order to segment objects of classes that have never been seen during training. This renders our object segmentation task an open world task. The pseudo depth maps are generated using pretrained networks, which have either been trained with the full intention to generalize to downstream tasks (LeRes and MiDaS), or which have been trained in an unsupervised fashion on video sequences (MonodepthV2). In order to tell our network which object to segment, we provide the network with a single click on the object’s surface on the pseudo depth map of the image as input. We test our approach on two different scenarios: One without the RGB image and one where the RGB image is part of the input. Our results demonstrate a considerably better generalization performance from seen to unseen object types when depth is used. On the Semantic Boundaries Dataset we achieve an improvement from 61.57 to 69.79 IoU score on unseen classes, when only using half of the training classes during training and performing the segmentation on depth maps only.

关键词：

来源：评论

学校读者我要写书评

暂无评论

All Keypoints You Need: Detecting Arbitrary Keypoints on the Body of Triple, High, and Long Jump Athletes

All Keypoints You Need: Detecting Arbitrary Keypoints on the...

引用

IEEE computer Society Conference on computer vision and Pattern Recognition Workshops (CVPRW)

作者： Katja Ludwig Julian Lorenz Robin Schön Rainer Lienhart Chair for Machine Learning and Computer Vision University of Augsburg

Performance analyses based on videos are commonly used by coaches of athletes in various sports disciplines. In individual sports, these analyses mainly comprise the body posture. This paper focuses on the disciplines of triple, high, and long jump, which require fine-grained locations of the athlete’s body. Typical human pose estimation datasets provide only a very limited set of keypoints, which is not sufficient in this case. Therefore, we propose a method to detect arbitrary keypoints on the whole body of the athlete by leveraging the limited set of annotated keypoints and auto-generated segmentation masks of body parts. Evaluations show that our model is capable of detecting keypoints on the head, torso, hands, feet, arms, and legs, including also bent elbows and knees. We analyze and compare different techniques to encode desired keypoints as the model’s input and their embedding for the Transformer backbone.

关键词：

来源：评论

学校读者我要写书评

暂无评论

All Keypoints You Need: Detecting Arbitrary Keypoints on the Body of Triple, High, and Long Jump Athletes

arXiv

引用

arXiv 2023年

作者： Ludwig, Katja Lorenz, Julian Schön, Robin Lienhart, Rainer Chair for Machine Learning and Computer Vision University of Augsburg Germany

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

Efficient 2D to Full 3D Human Pose Uplifting including Joint Rotations

arXiv

引用

arXiv 2025年

作者： Ludwig, Katja Oksymets, Yuliia Schön, Robin Kienzle, Daniel Lienhart, Rainer Chair for Machine Learning & Computer Vision University of Augsburg Germany

In sports analytics, accurately capturing both the 3D locations and rotations of body joints is essential for understanding an athlete’s biomechanics. While Human Mesh Recovery (HMR) models can estimate joint rotations, they often exhibit lower accuracy in joint localization compared to 3D Human Pose Estimation (HPE) models. Recent work [18] addressed this limitation by combining a 3D HPE model with inverse kinematics (IK) to estimate both joint locations and rotations. However, IK is computationally expensive. To overcome this, we propose a novel 2D-to-3D uplifting model that directly estimates 3D human poses, including joint rotations, in a single forward pass. We investigate multiple rotation representations, loss functions, and training strategies — both with and without access to ground truth rotations. Our models achieve state-of-the-art accuracy in rotation estimation, are 150 times faster than the IK-based approach, and surpass HMR models in joint localization precision. Copyright © 2025, The Authors. All rights reserved.

关键词： Inverse kinematics

来源：评论

学校读者我要写书评

暂无评论

New Parameters to Monitor Rehabilitation after Tibial Fractures Based on Ground-Reaction Forces Enable Assessment of Heavily Altered Gait

SSRN

引用

SSRN 2024年

作者： Wolff, Christian Warmerdam, Elke Dahmen, Tim Pohlemann, Tim Slusallek, Philipp Ganse, Bergita Saarbrücken Germany Saarbrücken Graduate School of Computer Science Germany Departments and Institutes of Surgery Saarland University Homburg Germany Chair for Computer Vision and Machine Learning Hochschule Aalen Aalen Germany Department of Trauma Hand and Reconstructive Surgery Departments and Institutes of Surgery Saarland University Homburg Germany

Background and Objective: Instrumented insoles have created new opportunities for patient monitoring. As the shape of the ground-reaction force curve during the stance phase is altered in patients after lower-extremity fracture, classical parameters derived from the curve often cannot be used to monitor the early rehabilitation process. We proposed new parameters applicable to individuals in the early stages of recovery after a tibial fracture and hypothesized interrelation with healing progress. Methods: In an observational prospective longitudinal study, data were collected from 13 patients with tibial fractures during straight walking at each hospital visit using instrumented insoles with 16 pressure sensors at 100 Hz. To analyse changes of the new parameters throughout healing, parametrized curves were fitted. If successful, linear, polynomial (2nd and 3rd degree), and logarithmic regression analyses were conducted to determine the best fit reflected in the highest R2-value and lowest-fitting error. A Wald Test with t-distribution was employed for statistical analysis. Strides were classified as regular or non-regular, and changes in this proportion throughout healing were analysed. Results: The parameters with the highest R2-values were the mean force between enclosing turning points (R2 = 0.715), the absolute time between enclosing turning points (R2 = 0.707), and the highest overall force (R2 = 0.722). There was a significant increase of regular strides on both the injured (R2 = 0.427, p 2 = 0.506, p © 2024, The Authors. All rights reserved.

关键词： Patient monitoring

来源：评论

学校读者我要写书评

暂无评论

Novel ground reaction force-based parameters for monitoring rehabilitation in tibial fractures

引用

Gait & Posture 2024年 113卷 256-257页

作者： Christian Wolff Elke Warmerdam Tim Dahmen Tim Pohlemann Philipp Slusallek Bergita Ganse German Research Center for Artificial Intelligence Agents and Simulated Reality Saarbrücken Germany Saarland University Saarbrücken Graduate School of Computer Science Saarbrücken Germany Saarland University Werner Siemens-Endowed Chair for Innovative Implant Development Fracture Healing- Departments and Institutes of Surgery Homburg Germany Hochschule Aalen Chair for Computer Vision and Machine Learning Aalen Germany Saarland University Department of Trauma- Hand and Reconstructive Surgery- Departments and Institutes of Surgery Homburg Germany

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：