4DSegStreamer: Streaming 4D Panoptic Segmentation via Dual Threads
Ling Liu, Jun Tian, Li Yi

TL;DR
4DSegStreamer is a real-time streaming 4D panoptic segmentation framework that uses a dual-thread system to enhance robustness and efficiency in dynamic environments, suitable for applications like autonomous driving.
Contribution
It introduces a novel dual-thread system that integrates predictive and inference processes for real-time 4D segmentation, adaptable to existing methods and robust under high FPS conditions.
Findings
Outperforms existing streaming perception methods in robustness and accuracy.
Effectively predicts dynamic objects in complex scenes.
Achieves real-time processing on multiple datasets.
Abstract
4D panoptic segmentation in a streaming setting is critical for highly dynamic environments, such as evacuating dense crowds and autonomous driving in complex scenarios, where real-time, fine-grained perception within a constrained time budget is essential. In this paper, we introduce 4DSegStreamer, a novel framework that employs a Dual-Thread System to efficiently process streaming frames. The framework is general and can be seamlessly integrated into existing 3D and 4D segmentation methods to enable real-time capability. It also demonstrates superior robustness compared to existing streaming perception approaches, particularly under high FPS conditions. The system consists of a predictive thread and an inference thread. The predictive thread leverages historical motion and geometric information to extract features and forecast future dynamics. The inference thread ensures timely…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Vision and Imaging · Human Pose and Action Recognition · Video Surveillance and Tracking Methods
