Article
Chemistry, Analytical
Jan Rodziewicz-Bielewicz, Marcin Korze
Summary: This paper presents a simple yet robust computer vision system for robot arm tracking using RGB-D cameras. It tracks the robot's state in real time, given three angles and known restrictions about the robot's geometry. The system consists of two parts: image preprocessing and machine learning. In the machine learning part, two approaches are compared: fitting the robot pose to the point cloud and fitting the convolutional neural network model to the sparse 3D depth images. The presented approach directly uses the point cloud transformed to the sparse image in the network input, utilizing sparse CNN layers. Experiments confirm real-time robot tracking with accuracy comparable to that of the depth sensor.
Article
Computer Science, Artificial Intelligence
Jameel Malik, Soshi Shimada, Ahmed Elhayek, Sk Aziz Ali, Christian Theobalt, Vladislav Golyanik, Didier Stricker
Summary: Estimating 3D hand shape and pose from a single depth map is a challenging problem. To overcome the limitations of existing methods, researchers propose HandVoxNet++, a new deep network that combines two hand shape representations. Through extensive evaluations, HandVoxNet++ achieves state-of-the-art performance on public benchmark datasets.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Software Engineering
Kangkan Wang, Guofeng Zhang, Jian Yang
Summary: We propose a novel approach to estimate the 3D pose and shape of human bodies from a single depth image. The method combines correspondence learning and parametric model fitting to reconstruct 3D human body models. Experimental results demonstrate that the proposed method outperforms the state-of-the-art methods in terms of reconstruction accuracy.
Article
Engineering, Aerospace
Chang Liu, Wulong Guo, Weiduo Hu, Rongliang Chen, Jia Liu
Summary: This article introduces an innovative framework for real-time pose tracking of asteroids using their contour information in the image. The tracking is initialized with distance-based template matching and contour-based pose optimization, and the pose is obtained in real time by fitting the asteroid CAD model over the contour of the image with M-estimation. Experimental results confirm the accuracy and efficiency of the proposed method.
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
(2021)
Article
Optics
Peng Li, Mao Wang, Jinyu Fu, Bing Zhang
Summary: This paper proposes a method for relative position and attitude estimation using consecutive point clouds. The method extracts global features through fast plane detection, registers the point clouds using a two-stage angle adjustment and iterative closest point algorithm, and utilizes an unscented Kalman filter for estimating the target's pose and motion parameters.
Article
Computer Science, Artificial Intelligence
Chen Qin, Shuo Wang, Chen Chen, Wenjia Bai, Daniel Rueckert
Summary: This paper proposes a novel method for myocardial motion tracking by using a generative model based on variational autoencoder to learn biomechanically plausible deformations and embed them into a neural network-parameterized transformation model. Experimental results show that the proposed method outperforms other approaches in terms of motion tracking accuracy, volume preservation, and generalizability.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Computer Science, Software Engineering
Xiaofang Wang, Stephanie Prevost, Adnane Boukhayma, Eric Desjardin, Celine Loscos, Benoit Morisset, Franck Multon
Summary: This paper addresses the problem of capturing the shape and pose of a human character using a single depth sensor. The authors propose a hybrid approach that combines the advantages of model fitting and deep learning. Extensive experiments demonstrate that this hybrid approach improves pose and shape estimation compared to using either method separately.
COMPUTERS & GRAPHICS-UK
(2023)
Article
Automation & Control Systems
Guiyu Xia, Furong Ma, Qingshan Liu, Du Zhang
Summary: This article proposes a method to transform 2D motion synthesis into a pose conditional realistic motion image generation task. By designing a two-step and multistream network architecture, the drawback of generative adversarial networks in motion synthesis is addressed. The effectiveness of the proposed model is demonstrated through experiments.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Chemistry, Analytical
Audrius Kulikajevas, Rytis Maskeliunas, Robertas Damasevicius, Rafal Scherer
Summary: A novel two-tiered deep neural network architecture is proposed for reconstructing self-obstructed human-like morphing shapes, achieving good predictive capabilities in experiments.
Article
Computer Science, Artificial Intelligence
Chengfeng Zhao, Chen Fu, John Dolan, Jun Wang
Summary: This paper introduces a real-time tracking algorithm based on L-Shape fitting for detecting moving vehicles, which uses RANSAC to handle noisy data and implements a vehicle tracking system with multi-weight RBPF. The algorithm achieves real-time performance, mitigates the effect of noisy data, and improves estimation accuracy according to experiments on different datasets.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2021)
Article
Multidisciplinary Sciences
Alice Ruget, Max Tyler, German Mora Martin, Stirling Scholes, Feng Zhu, Istvan Gyongy, Brent Hearn, Steve McLaughlin, Abderrahim Halimi, Jonathan Leach
Summary: Single-photon-sensitive depth sensors have a growing application in human pose and gesture recognition in next-generation electronics. This study presents a temporal to spatial mapping to significantly enhance the resolution of a simple time-of-flight sensor. The developed explainable framework offers insight into how the network utilizes input data and relevant parameters.
Article
Computer Science, Artificial Intelligence
Chaoqiang Zhao, Gary G. Yen, Qiyu Sun, Chongzhen Zhang, Yang Tang
Summary: This article proposes a masked generative adversarial network (GAN) for unsupervised monocular depth and ego-motion estimations. The MaskNet and Boolean mask scheme are designed to eliminate the effects of occlusions and impacts of visual field changes. Experiments show that each component proposed in this article contributes to the performance, and both depth and trajectory predictions achieve competitive performance on the KITTI and Make3D data sets.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Information Systems
Jing Sun, Yi-Mu Ji, Shang-Dong Liu
Summary: In this paper, a vehicle pose estimation method with heuristic L-shape fitting and grid-based particle filter is proposed, which achieves significant improvements in both the runtime efficiency and pose estimation accuracy of incomplete point clouds.
Article
Biology
Philip R. L. Parker, Elliott T. T. Abe, Natalie T. Beatie, Emmalyn S. P. Leonard, Dylan M. Martins, Shelby L. Sharp, David G. Wyrick, Luca Mazzucato, Cristopher M. Niell
Summary: In natural contexts, the connection between sensory processing and motor output is evident, as many brain areas contain both sensory and movement signals. This study investigates distance estimation in mice during a naturalistic task, finding that mice use vision to accurately jump across a variable gap, even without relying solely on binocular disparity and stereo vision. Monocular conditions lead to changes in head positioning and more vertical head movements, indicating a shift in reliance on different visual cues. Additionally, optogenetic suppression of the primary visual cortex impairs task performance, highlighting the importance of the visual cortex in distance judgment.
Article
Neurosciences
XiaoLe Liu, Si-yang Yu, Nico A. Flierman, Sebastian Loyola, Maarten Kamermans, Tycho M. Hoogland, Chris I. De Zeeuw
Summary: OptiFlex is a novel multi-frame animal pose estimation framework that integrates a flexible base model and an OpticalFlow model to improve prediction accuracy by considering variability in animal body shape and incorporating temporal context.
FRONTIERS IN CELLULAR NEUROSCIENCE
(2021)
Article
Computer Science, Software Engineering
Yuxin Ma, Anthony K. H. Tung, Wei Wang, Xiang Gao, Zhigeng Pan, Wei Chen
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2020)
Article
Biochemistry & Molecular Biology
Yan Zhang, Hui Wang, Ruigang Yang, Lihao Wang, Guanpin Yang, Tianzhong Liu
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2020)
Article
Computer Science, Artificial Intelligence
Xinxin Zuo, Sen Wang, Jiangbin Zheng, Zhigeng Pan, Ruigang Yang
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2020)
Article
Computer Science, Artificial Intelligence
Xinjing Cheng, Peng Wang, Ruigang Yang
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2020)
Article
Computer Science, Artificial Intelligence
Xinyu Huang, Peng Wang, Xinjing Cheng, Dingfu Zhou, Qichuan Geng, Ruigang Yang
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2020)
Article
Computer Science, Artificial Intelligence
Wenguan Wang, Qiuxia Lai, Huazhu Fu, Jianbing Shen, Haibin Ling, Ruigang Yang
Summary: This paper provides a comprehensive survey on deep salient object detection (SOD), covering algorithm taxonomy, unsolved issues, and dataset evaluation. The research shows that deep learning algorithms have made significant progress in SOD, and investigates the performance under different attribute settings, the robustness to random input perturbations and adversarial attacks, and the generalization of existing datasets.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Wei Wang, Xiaoyang Suo, Xiangyu Wei, Bin Wang, Hao Wang, Hong-Ning Dai, Xiangliang Zhang
Summary: Graph Auto-Encoder is a framework for unsupervised learning on graph-structured data. However, it is not applicable for heterogeneous graphs that contain more abundant semantic information. Therefore, this work proposes a novel HGATE method for unsupervised representation learning on heterogeneous graph-structured data.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Qichuan Geng, Hong Zhang, Xiaojuan Qi, Gao Huang, Ruigang Yang, Zhong Zhou
Summary: The proposed GPSNet method achieves good performance in semantic segmentation tasks by dynamically selecting receptive fields and aggregating dense semantic context information.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Proceedings Paper
Automation & Control Systems
Xinjing Cheng, Peng Wang, Yanqi Zhou, Chenye Guan, Ruigang Yang
2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)
(2020)
Proceedings Paper
Automation & Control Systems
Tingxiang Fan, Pinxin Long, Wenxi Liu, Jia Pan, Ruigang Yang, Dinesh Manocha
2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Dingfu Zhou, Jin Fang, Xibin Song, Liu Liu, Junbo Yin, Yuchao Dai, Hongdong Li, Ruigang Yang
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Article
Computer Science, Software Engineering
Feixiang Lu, Haotian Peng, Hongyu Wu, Jun Yang, Xinhang Yang, Ruizhi Cao, Liangjun Zhang, Ruigang Yang, Bin Zhou
COMPUTER GRAPHICS FORUM
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Tianhua Xie, Mingliang Cao, Zhigeng Pan
PROCEEDINGS OF THE 2020 3RD INTERNATIONAL CONFERENCE ON IMAGE AND GRAPHICS PROCESSING (ICIGP 2020)
(2020)
Proceedings Paper
Computer Science, Theory & Methods
Binbin Zhou, Zhigeng Pan, Mingmin Zhang
ELEVENTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2019)
(2020)
Article
Robotics
Jin Fang, Dingfu Zhou, Feilong Yan, Tongtong Zhao, Feihu Zhang, Yu Ma, Liang Wang, Ruigang Yang
IEEE ROBOTICS AND AUTOMATION LETTERS
(2020)