人工智能
计算机科学
目标检测
计算机视觉
Boosting(机器学习)
杠杆(统计)
点云
传感器融合
模式识别(心理学)
特征提取
视频跟踪
图像融合
视觉对象识别的认知神经科学
融合
变更检测
激光雷达
保险丝(电气)
稳健性(进化)
特征(语言学)
数据建模
感知
先验与后验
试验装置
集合(抽象数据类型)
实体造型
作者
Wei Tian,Zhenglin Du,Xiaolong Zhao,Qiankun Yu
标识
DOI:10.1109/tcsvt.2026.3679483
摘要
Accurate perception of surrounding 3D objects is indispensable for ensuring the safety of autonomous driving systems. Furthermore, the integration of multi-modal sensors has emerged as a pivotal research area within detection paradigms based on Bird’s Eye View. In this paper, we introduce a sparse query-based 3D object detection framework by adaptive multi-modal temporal fusion of camera and LiDAR sensor data. Initially, we leverage the spatial-aware cross-modal feature aggregation to adaptively fuse instance-level point cloud and image features. We further elaborate a sequential temporal modeling approach, which facilitates an enhanced multi-modal 3D object detection within constant spatial and temporal complexity. To mitigate the challenge posed by limited high-quality training data, we incorporate a fragment-wise multi-modal temporal data augmentation strategy, aimed at bolstering the model’s performance for detecting long-tail distributed objects. Our approach achieves an NDS detection score of 75.5% on the nuScenes test set (without test time augmentation and model ensembling). These results underscore the efficacy of our approach and highlight its superiority compared to prior state-of-the-art methods. We further show that our approach remarkably improves the accuracy of multi-object tracking on nuScenes dataset.
科研通智能强力驱动
Strongly Powered by AbleSci AI