MF-MOS: A Motion-Focused Model for Moving Object Segmentation
South China Normal University(华南师范大学);Aberystwyth University(阿伯里斯特威斯大学);Hong Kong University of Science and Technology(香港科技大学);Jiangnan University(江南大学);National University of Defense Technology(国防科技大学);Tongji University(同济大学)
Jintao Cheng, Kang Zeng, Zhuoxu Huang, Xiaoyu Tang, Jin Wu, Chengxi Zhang, Xieyuanli Chen, Rui Fan
Moving object segmentation (MOS) provides a reliable solution for detecting traffic participants and thus is of great interest in the autonomous driving field. Dynamic capture is always critical in the MOS problem. Previous methods capture motion features from the range images directly. Differently, we argue that the residual maps provide greater potential for motion information, while range images contain rich semantic guidance. Based on this intuition, we propose MF-MOS, a novel motion-focused model with a dual-branch structure for LiDAR moving object segmentation. Novelly, we decouple the spatial-temporal information by capturing the motion from residual maps and generating semantic features from range images, which are used as movable object guidance for the motion branch. Our straightforward yet distinctive solution can make the most use of both range images and residual maps, thus greatly improving the performance of the LiDAR-based MOS task. Remarkably, our MF-MOS achieved a leading IoU of 76.7% on the MOS leaderboard of the SemanticKITTI dataset upon submission, demonstrating the current state-of-the-art performance. The implementation of our MF-MOS has been released at https://github.com/SCNU-RISLAB/MF-MOS.
MV-MOS: Multi-View Feature Fusion for 3D Moving Object Segmentation
Research Institute of Trustworthy Autonomous Systems(可信自主系统研究院);Southern University of Science and Technology(南方科技大学);School of Electronic and Information Engineering, South China Normal University(华南师范大学电子与信息工程学院);College of Intelligence Science and Technology, National University of Defense Technology(国防科技大学智能科学学院)
CV-MOS: A Cross-View Model for Motion Segmentation
Xingzhi College, South China Normal University(华南师范大学行知学院);College of Intelligence Science and Technology, National University of Defense Technology(国防科技大学智能科学学院);Hong Kong University of Science and Technology(香港科技大学)
Self-Supervised Moving Vehicle Detection from Audio-Visual Cues
University of Freiburg(弗莱堡大学);University of Technology Nuremberg(纽伦堡工业大学)
运动车辆的鲁棒检测对于任何自主操作的户外机器人或自动驾驶车辆来说都是一项关键任务。解决这一任务的大多数现代方法都依赖于使用nuScenes或Waymo Open Dataset等大规模车辆检测数据集来训练基于图像的检测器。提供手动注释是一项昂贵且费力的工作,并且在实践中无法很好地扩展。为了解决这个问题,我们提出了一种自我监督的方法,利用视听线索来检测视频中的移动车辆。我们的方法采用对比学习定位车辆的图像,从相应的图像和录音对。在使用真实世界数据集进行的广泛实验中,我们证明了我们的方法可以准确检测移动车辆,并且不需要手动注释。我们还表明,我们的模型可以作为一个老师来监督一个只检测音频的模型。该学生模型对光照变化不敏感,因此有效地弥补了仅利用视觉作为主要模态的模型所固有的领域差距。
GMOS: Grounding Moving Object Segmentation in 3D Space and Time
Visual Geometry Group, Department of Engineering Science, University of Oxford, UK(牛津大学工程科学系视觉几何组);SAI, Shanghai Jiao Tong University, China(上海交通大学SAI)
Event-Free Moving Object Segmentation from Moving Ego Vehicle
University of Burgundy(勃艮第大学);University of Wurzburg(维尔茨堡大学);INSAIT(保加利亚国家研究与技术创新研究所);Université Rouen Normandie(鲁昂诺曼底大学);INSA Rouen Normandie(鲁昂诺曼底国立应用科学学院);Université Le Havre Normandie(勒阿弗尔诺曼底大学);Normandie Université(诺曼底大学);ETH Zurich(苏黎世联邦理工学院);CVL(计算机视觉实验室)
运动目标检测是视频自动分析的关键技术之一,在视频监控跟踪、视频压缩编码等领域有着广泛的应用前景。鲁棒主成分分析(Robust Principal Component Analysis,RPCA)是目前最流行的运动目标建模方法之一,其目标是将运动目标的时变(即,从视频中的静态背景中移动)前景对象,假设背景帧是低秩的,而前景是空间稀疏的。经典的RPCA使用l1范数对前景分量施加稀疏性,并通过2范数使建模误差最小化。我们表明,这样的假设可能是过于限制在实践中,这限制了经典的RPCA的有效性,特别是当处理视频与动态背景,相机抖动,隐藏的移动对象,在本文中,我们提出了一种新的RPCA为基础的模型,称为超RPCA,检测运动物体的飞行。与经典的RPCA不同,超RPCA联合应用最大相关熵准则(MCC)的建模误差,拉普拉斯尺度混合(LSM)模型的前景对象。大量的实验已经进行,结果表明,所提出的超RPCA具有竞争力的性能,前景检测的国家的最先进的算法在几个著名的基准数据集。
HeLiMOS: A Dataset for Moving Object Segmentation in 3D Point Clouds From Heterogeneous LiDAR Sensors
School of Electrical Engineering, KAIST (Korea Advanced Institute of Science and Technology)(韩国科学技术院电气工程学院);Center for Robotics, University of Bonn(波恩大学机器人中心);Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔机器学习与人工智能研究所)
4D iterative reconstruction of brain fMRI in the moving fetus
Computational Imaging Research Lab(计算成像研究实验室);Medical University of Vienna(维也纳医科大学);Lausanne University Hospital (CHUV)(洛桑大学医院(CHUV));University of Lausanne (UNIL)(洛桑大学(UNIL));CIBM Center for Biomedical Imaging(CIBM生物医学成像中心)
Moving object detection for visual odometry in a dynamic environment based on occlusion accumulation
Lab for Autonomous Robotics Research (LARR), Seoul National University(首尔国立大学自主机器人研究实验室(LARR));Computer Graphics and Vision Lab (GrUVi), Simon Fraser University(西蒙弗雷泽大学计算机图形与视觉实验室(GrUVi))
MambaMOS: LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space Model
College of Computer Science and Electronic Engineering, Hunan University(湖南大学计算机与通信工程学院);College of Optical Science and Engineering, Zhejiang University(浙江大学光学工程学院);School of Robotics, Hunan University(湖南大学机器人学院);School of Electronics and Information Engineering, South China Normal University(华南师范大学电子与信息工程学院)