吉林大学学报（理学版）2026，Vol.64Issue(3)：591-602,12.DOI:10.13413/j.cnki.jdxblxb.2025021
基于多层级交互式特征融合的三维目标检测算法
Three-Dimensional Object Detection Algorithm Based on Multi-level Interactive Feature Fusion
摘要
Abstract
Aiming at the problems of small-object recognition difficulty,sparse point clouds at long distances,and insufficient multimodal feature fusion in three-dimensional object detection for autonomous driving scenarios,we proposed an improved algorithm based on a multimodal three-dimensional object detection framework.The algorithm enhanced the ability to preserve foreground information and suppress background noise interference by constructing a class-and centroid-aware foreground point sampling strategy.By introducing a dynamic convolutional image feature extraction mechanism,the quality of image feature representation was improved.By designing a multi-stage interactive feature attention fusion module,the deep collaborative modeling ability between point cloud features and image features was improved.Experimental results on a public dataset show that the proposed method achieves average detection accuracies of 83.49％,46.98％and 68.28％for three types of objects:cars,pedestrians and cyclists,respectively,and outperforms current mainstream methods in overall performance.The proposed method can effectively improve the accuracy and robustness of three-dimensional object detection in complex traffic scenarios and has certain reference value for promoting the development of autonomous driving environment perception technology.关键词
计算机视觉/关键点采样/动态卷积/三维目标检测/多模态融合Key words
computer vision/key point sampling/dynamic convolution/3D object detection/multimodal fusion分类
信息技术与安全科学引用本文复制引用
高凯,王晟宇,付强,才华,张晨洁,王伟刚..基于多层级交互式特征融合的三维目标检测算法[J].吉林大学学报（理学版）,2026,64(3):591-602,12.基金项目
国家自然科学基金联合基金(批准号:U2341226)、吉林省科技厅项目(批准号:20260102267JC （批准号:U2341226）
20240302089GX)、吉林省医疗卫生人才专项基金(批准号:JLSWSRCZX2023-70)和2024年空间智能控制技术全国重点实验室开放基金(批准号:2024-CXPT-GF-JJ-012-12). （批准号:JLSWSRCZX2023-70）
