测试科学与仪器2021，Vol.12Issue(2)：232-241,10.DOI:10.3969/j.issn.1674-8042.2021.02.013
自适应性多模态特征融合的远小困难目标检测
Adaptive multi-modal feature fusion for far and hard obj ect detection
摘要
Abstract
In order to solve difficult detection of far and hard obj ects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is proposed,which makes use of multi-neighborhood information of voxel and image information. Firstly, design an improved ResNet that maintains the structure information of far and hard objects in low-resolution feature maps,which is more suitable for detection task. Meanwhile,semantema of each image feature map is enhanced by semantic information from all subsequent feature maps. Secondly,extract multi-neighborhood context information with different receptive field sizes to make up for the defect of sparseness of point cloud which improves the ability of voxel features to represent the spatial structure and semantic information of objects.Finally,propose a multi-modal feature adaptive fusion strategy which uses learnable weights to express the contribution of different modal features to the detection task,and voxel attention further enhances the fused feature expression of effective target obj ects.The experimental results on the KITTI benchmark show that this method outperforms VoxelNet with remarkable margins,i.e.increasing the AP by 8.78％ and 5.49％ on medium and hard difficulty levels.Meanwhile,our method achieves greater detection performance compared with many mainstream multi-modal methods,i.e.outperforming the AP by 1％ compared with that of MVX-Net on medium and hard difficulty levels.关键词
3D目标检测/自适应性融合/多模态数据融合/注意力机制/多邻域特征Key words
3D object detection/adaptive fusion/multi-modal data fusion/attention mechanism/multi-neighborhood features引用本文复制引用
李阳,葛洪伟..自适应性多模态特征融合的远小困难目标检测[J].测试科学与仪器,2021,12(2):232-241,10.基金项目
National Youth Natural Science Foundation of China(No.61806006) （No.61806006）
Innovation Program for Graduate of Jiangsu Province(No.KYLX160-781) （No.KYLX160-781）
Jiangsu University Superior Discipline Construction Project （）
