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

• URL: http://arxiv.org/abs/2111.03483v1
• Date: Fri, 5 Nov 2021 12:59:41 GMT
• Title: Event-based Motion Segmentation by Cascaded Two-Level Multi-Model Fitting
• Authors: Xiuyuan Lu, Yi Zhou and Shaojie Shen
• Abstract summary: We present a cascaded two-level multi-model fitting method for identifying independently moving objects with a monocular event camera. Experiments demonstrate the effectiveness and versatility of our method in real-world scenes with different motion patterns and an unknown number of moving objects.
• Score: 44.97191206895915
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 may deteriorate remarkably under aggressive motion and challenging illumination conditions. In contrast, event-based cameras, as a category of novel biologically inspired sensors, deliver advantages to deal with these challenges. Its rapid response and asynchronous nature enables it to capture visual stimuli at exactly the same rate of the scene dynamics. In this paper, we present a cascaded two-level multi-model fitting method for identifying independently moving objects (i.e., the motion segmentation problem) with a monocular event camera. The first level leverages tracking of event features and solves the feature clustering problem under a progressive multi-model fitting scheme. Initialized with the resulting motion model instances, the second level further addresses the event clustering problem using a spatio-temporal graph-cut method. This combination leads to efficient and accurate event-wise motion segmentation that cannot be achieved by any of them alone. Experiments demonstrate the effectiveness and versatility of our method in real-world scenes with different motion patterns and an unknown number of independently moving objects.

Related papers

• EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting [95.44545809256473]
  EgoGaussian is a method capable of simultaneously reconstructing 3D scenes and dynamically tracking 3D object motion from RGB egocentric input alone. We show significant improvements in terms of both dynamic object and background reconstruction quality compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-06-28T10:39:36Z)
• Motion Segmentation for Neuromorphic Aerial Surveillance [42.04157319642197]
  Event cameras offer superior temporal resolution, superior dynamic range, and minimal power requirements. Unlike traditional frame-based sensors that capture redundant information at fixed intervals, event cameras asynchronously record pixel-level brightness changes. We introduce a novel motion segmentation method that leverages self-supervised vision transformers on both event data and optical flow information.
  arXiv  Detail & Related papers  (2024-05-24T04:36:13Z)
• Motion Segmentation from a Moving Monocular Camera [3.115818438802931]
  We take advantage of two popular branches of monocular motion segmentation approaches: point trajectory based and optical flow based methods. We are able to model various complex object motions in different scene structures at once. Our method shows state-of-the-art performance on the KT3DMoSeg dataset.
  arXiv  Detail & Related papers  (2023-09-24T22:59:05Z)
• MotionTrack: Learning Motion Predictor for Multiple Object Tracking [68.68339102749358]
  We introduce a novel motion-based tracker, MotionTrack, centered around a learnable motion predictor. Our experimental results demonstrate that MotionTrack yields state-of-the-art performance on datasets such as Dancetrack and SportsMOT.
  arXiv  Detail & Related papers  (2023-06-05T04:24:11Z)
• Attentive and Contrastive Learning for Joint Depth and Motion Field Estimation [76.58256020932312]
  Estimating the motion of the camera together with the 3D structure of the scene from a monocular vision system is a complex task. We present a self-supervised learning framework for 3D object motion field estimation from monocular videos.
  arXiv  Detail & Related papers  (2021-10-13T16:45:01Z)
• AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control [145.61135774698002]
  We propose a fully automated approach to selecting motion for a character to track in a given scenario. High-level task objectives that the character should perform can be specified by relatively simple reward functions. Low-level style of the character's behaviors can be specified by a dataset of unstructured motion clips. Our system produces high-quality motions comparable to those achieved by state-of-the-art tracking-based techniques.
  arXiv  Detail & Related papers  (2021-04-05T22:43:14Z)
• Event-based Motion Segmentation with Spatio-Temporal Graph Cuts [51.17064599766138]
  We have developed a method to identify independently objects acquired with an event-based camera. The method performs on par or better than the state of the art without having to predetermine the number of expected moving objects.
  arXiv  Detail & Related papers  (2020-12-16T04:06:02Z)
• 0-MMS: Zero-Shot Multi-Motion Segmentation With A Monocular Event Camera [13.39518293550118]
  We present an approach for monocular multi-motion segmentation, which combines bottom-up feature tracking and top-down motion compensation into a unified pipeline. Using the events within a time-interval, our method segments the scene into multiple motions by splitting and merging. The approach was successfully evaluated on both challenging real-world and synthetic scenarios from the EV-IMO, EED, and MOD datasets.
  arXiv  Detail & Related papers  (2020-06-11T02:34:29Z)
• End-to-end Learning of Object Motion Estimation from Retinal Events for Event-based Object Tracking [35.95703377642108]
  We propose a novel deep neural network to learn and regress a parametric object-level motion/transform model for event-based object tracking. To achieve this goal, we propose a synchronous Time-Surface with Linear Time Decay representation. We feed the sequence of TSLTD frames to a novel Retinal Motion Regression Network (RMRNet) perform to an end-to-end 5-DoF object motion regression.
  arXiv  Detail & Related papers  (2020-02-14T08:19:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.