PriorMotion: Generative Class-Agnostic Motion Prediction with Raster-Vector Motion Field Priors

Autor:	Qian, Kangan, Jiao, Xinyu, Shi, Yining, Wang, Yunlong, Luo, Ziang, Fu, Zheng, Jiang, Kun, Yang, Diange
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Performance Computer Science - Robotics
Druh dokumentu:	Working Paper
Popis:	Reliable perception of spatial and motion information is crucial for safe autonomous navigation. Traditional approaches typically fall into two categories: object-centric and class-agnostic methods. While object-centric methods often struggle with missed detections, leading to inaccuracies in motion prediction, many class-agnostic methods focus heavily on encoder design, often overlooking important priors like rigidity and temporal consistency, leading to suboptimal performance, particularly with sparse LiDAR data at distant region. To address these issues, we propose $\textbf{PriorMotion}$, a generative framework that extracts rasterized and vectorized scene representations to model spatio-temporal priors. Our model comprises a BEV encoder, an Raster-Vector prior Encoder, and a Spatio-Temporal prior Generator, improving both spatial and temporal consistency in motion prediction. Additionally, we introduce a standardized evaluation protocol for class-agnostic motion prediction. Experiments on the nuScenes dataset show that PriorMotion achieves state-of-the-art performance, with further validation on advanced FMCW LiDAR confirming its robustness. Comment: 8 pages, 6 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2412.04020 Zobrazit plný text záznamu View this record from Arxiv