Distractor-aware Event-based Tracking
- URL: http://arxiv.org/abs/2310.14194v3
- Date: Fri, 10 Nov 2023 02:38:22 GMT
- Title: Distractor-aware Event-based Tracking
- Authors: Yingkai Fu, Meng Li, Wenxi Liu, Yuanchen Wang, Jiqing Zhang, Baocai
Yin, Xiaopeng Wei, Xin Yang
- Abstract summary: We propose a distractor-aware event-based tracker that introduces transformer modules into Siamese network architecture (named DANet)
Our model is mainly composed of a motion-aware network and a target-aware network, which simultaneously exploits both motion cues and object contours from event data.
Our DANet can be trained in an end-to-end manner without any post-processing and can run at over 80 FPS on a single V100.
- Score: 45.07711356111249
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Event cameras, or dynamic vision sensors, have recently achieved success from
fundamental vision tasks to high-level vision researches. Due to its ability to
asynchronously capture light intensity changes, event camera has an inherent
advantage to capture moving objects in challenging scenarios including objects
under low light, high dynamic range, or fast moving objects. Thus event camera
are natural for visual object tracking. However, the current event-based
trackers derived from RGB trackers simply modify the input images to event
frames and still follow conventional tracking pipeline that mainly focus on
object texture for target distinction. As a result, the trackers may not be
robust dealing with challenging scenarios such as moving cameras and cluttered
foreground. In this paper, we propose a distractor-aware event-based tracker
that introduces transformer modules into Siamese network architecture (named
DANet). Specifically, our model is mainly composed of a motion-aware network
and a target-aware network, which simultaneously exploits both motion cues and
object contours from event data, so as to discover motion objects and identify
the target object by removing dynamic distractors. Our DANet can be trained in
an end-to-end manner without any post-processing and can run at over 80 FPS on
a single V100. We conduct comprehensive experiments on two large event tracking
datasets to validate the proposed model. We demonstrate that our tracker has
superior performance against the state-of-the-art trackers in terms of both
accuracy and efficiency.
Related papers
- BlinkTrack: Feature Tracking over 100 FPS via Events and Images [50.98675227695814]
We propose a novel framework, BlinkTrack, which integrates event data with RGB images for high-frequency feature tracking.
Our method extends the traditional Kalman filter into a learning-based framework, utilizing differentiable Kalman filters in both event and image branches.
Experimental results indicate that BlinkTrack significantly outperforms existing event-based methods.
arXiv Detail & Related papers (2024-09-26T15:54:18Z) - SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Features [52.213656737672935]
SpikeMOT is an event-based multi-object tracker.
SpikeMOT uses spiking neural networks to extract sparsetemporal features from event streams associated with objects.
arXiv Detail & Related papers (2023-09-29T05:13:43Z) - 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) - Event-based Visual Tracking in Dynamic Environments [0.0]
We propose a framework to take advantage of both event cameras and off-the-shelf deep learning for object tracking.
We show that reconstructing event data into intensity frames improves the tracking performance in conditions under which conventional cameras fail to provide acceptable results.
arXiv Detail & Related papers (2022-12-15T12:18:13Z) - Moving Object Detection for Event-based vision using Graph Spectral
Clustering [6.354824287948164]
Moving object detection has been a central topic of discussion in computer vision for its wide range of applications.
We present an unsupervised Graph Spectral Clustering technique for Moving Object Detection in Event-based data.
We additionally show how the optimum number of moving objects can be automatically determined.
arXiv Detail & Related papers (2021-09-30T10:19:22Z) - VisEvent: Reliable Object Tracking via Collaboration of Frame and Event
Flows [93.54888104118822]
We propose a large-scale Visible-Event benchmark (termed VisEvent) due to the lack of a realistic and scaled dataset for this task.
Our dataset consists of 820 video pairs captured under low illumination, high speed, and background clutter scenarios.
Based on VisEvent, we transform the event flows into event images and construct more than 30 baseline methods.
arXiv Detail & Related papers (2021-08-11T03:55:12Z) - e-TLD: Event-based Framework for Dynamic Object Tracking [23.026432675020683]
This paper presents a long-term object tracking framework with a moving event camera under general tracking conditions.
The framework uses a discriminative representation for the object with online learning, and detects and re-tracks the object when it comes back into the field-of-view.
arXiv Detail & Related papers (2020-09-02T07:08:56Z) - 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) - Asynchronous Tracking-by-Detection on Adaptive Time Surfaces for
Event-based Object Tracking [87.0297771292994]
We propose an Event-based Tracking-by-Detection (ETD) method for generic bounding box-based object tracking.
To achieve this goal, we present an Adaptive Time-Surface with Linear Time Decay (ATSLTD) event-to-frame conversion algorithm.
We compare the proposed ETD method with seven popular object tracking methods, that are based on conventional cameras or event cameras, and two variants of ETD.
arXiv Detail & Related papers (2020-02-13T15:58:31Z)
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.