paper-with-me

홈 › Papers

ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings

2020-03-29 · CVPR 2020 6 · Jiahui Huang, Sheng Yang, Tai-Jiang Mu, Shi-Min Hu

We present ClusterVO, a stereo Visual Odometry which simultaneously clusters and estimates the motion of both ego and surrounding rigid clusters/objects. Unlike previous solutions relying on batch input or imposing priors on scene structure or dynamic object models, ClusterVO is online, general and thus can be used in various scenarios including indoor scene understanding and autonomous driving. At the core of our system lies a multi-level probabilistic association mechanism and a heterogeneous Conditional Random Field (CRF) clustering approach combining semantic, spatial and motion information to jointly infer cluster segmentations online for every frame. The poses of camera and dynamic objects are instantly solved through a sliding-window optimization. Our system is evaluated on Oxford Multimotion and KITTI dataset both quantitatively and qualitatively, reaching comparable results to state-of-the-art solutions on both odometry and dynamic trajectory recovery.

📄 PDF Abstract BibTeX arXiv:2003.12980

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingClusteringScene UnderstandingTrajectory RecoveryVisual Odometry

Similar Papers 제목 키워드 기반

SeMoLi: What Moves Together Belongs Together

2024-02-29 · CVPR 2024 1 · Jenny Seidenschwarz, Aljoša Ošep, Francesco Ferroni, Simon Lucey 외

We tackle semi-supervised object detection based on motion cues. Recent results suggest that heuristic-based clustering methods in conjunction with object trackers can be used to pseudo-label instances of moving objects …

ClusteringObjectobject-detectionObject Detection+3

Multi-instance Point Cloud Registration by Efficient Correspondence Clustering

2021-11-29 · CVPR 2022 1 · Weixuan Tang, Danping Zou

We address the problem of estimating the poses of multiple instances of the source point cloud within a target point cloud. Existing solutions require sampling a lot of hypotheses to detect possible instances and reject …

ClusteringPoint Cloud Registration

Event-based Motion Segmentation by Cascaded Two-Level Multi-Model Fitting

2021-11-05 · Xiuyuan Lu, Yi Zhou, Shaojie Shen

Among prerequisites for a synthetic agent to interact with dynamic scenes, the ability to identify independently moving objects is specifically important. From an application perspective, nevertheless, standard cameras m…

ClusteringMotion SegmentationVocal Bursts Valence Prediction

Moving Window Regression: A Novel Approach to Ordinal Regression

2022-03-24 · CVPR 2022 1 · Nyeong-Ho Shin, Seon-Ho Lee, Chang-Su Kim

A novel ordinal regression algorithm, called moving window regression (MWR), is proposed in this paper. First, we propose the notion of relative rank ($\rho$-rank), which is a new order representation scheme for input an…

Age And Gender ClassificationAge Estimationimage-classificationImage Classification+1

Sense Discovery via Co-Clustering on Images and Text

2015-06-01 · CVPR 2015 6 · Xinlei Chen, Alan Ritter, Abhinav Gupta, Tom Mitchell

We present a co-clustering framework that can be used to discover multiple semantic and visual senses of a given Noun Phrase (NP). Unlike traditional clustering approaches which assume a one-to-one mapping between the cl…

Clustering