SDTracker: Synthetic Data Based Multi-Object Tracking
We present SDTracker, a method that harnesses the potential of synthetic data for multi-object tracking of real-world scenes in a domain generalization and semi-supervised fashion. First, we use the ImageNet dataset as an auxiliary to randomize the style of synthetic data. With out-of-domain data, we further enforce pyramid consistency loss across different "stylized" images from the same sample to learn domain invariant features. Second, we adopt the pseudo-labeling method to effectively utilize the unlabeled MOT17 training data. To obtain high-quality pseudo-labels, we apply proximal policy optimization (PPO2) algorithm to search confidence thresholds for each sequence. When using the unlabeled MOT17 training set, combined with the pure-motion tracking strategy upgraded via developed post-processing, we finally reach 61.4 HOTA.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain GeneralizationMulti-Object TrackingObjectObject TrackingSimilar Papers 제목 키워드 기반
3D Multi-Object Tracking with Differentiable Pose Estimation
We propose a novel approach for joint 3D multi-object tracking and reconstruction from RGB-D sequences in indoor environments. To this end, we detect and reconstruct objects in each frame while predicting dense correspon…
3D Multi-Object TrackingGraph Neural NetworkMulti-Object TrackingObject+2ROS 2-Based LiDAR Perception Framework for Mobile Robots in Dynamic Production Environments, Utilizing Synthetic Data Generation, Transformation-Equivariant 3D Detection and Multi-Object Tracking
Adaptive robots in dynamic production environments require robust perception capabilities, including 6D pose estimation and multi-object tracking. To address limitations in real-world data dependency, noise robustness, a…
Synthetic Data GenerationMulti-Object Tracking6D Pose EstimationGBOT: Graph-Based 3D Object Tracking for Augmented Reality-Assisted Assembly Guidance
Guidance for assemblable parts is a promising field for augmented reality. Augmented reality assembly guidance requires 6D object poses of target objects in real time. Especially in time-critical medical or industrial se…
3D Object Tracking6D Pose EstimationMulti-Object TrackingObject+2BrackishMOT: The Brackish Multi-Object Tracking Dataset
There exist no publicly available annotated underwater multi-object tracking (MOT) datasets captured in turbid environments. To remedy this we propose the BrackishMOT dataset with focus on tracking schools of small fish,…
Multi-Object TrackingObjectObject TrackingLearning to Track with Object Permanence
Tracking by detection, the dominant approach for online multi-object tracking, alternates between localization and association steps. As a result, it strongly depends on the quality of instantaneous observations, often f…
Multi-Object TrackingObjectobject-detectionObject Detection+2