FCNet: Stereo 3D Object Detection with Feature Correlation Networks

doi:10.3390/e24081121

	FCNet: Stereo 3D Object Detection with Feature Correlation Networks
	Wu, Yingyu 1; Liu, Ziyan 1,2,3; Chen, Yunlei 1; Zheng, Xuhui 1; Zhang, Qian 1; Yang, Mo 1; Tang, Guangming 3
	2022-08-01
发表期刊	ENTROPY
卷号	24 期号:8 页码:17
摘要	Deep-learning techniques have significantly improved object detection performance, especially with binocular images in 3D scenarios. To supervise the depth information in stereo 3D object detection, reconstructing the 3D dense depth of LiDAR point clouds causes higher computational costs and lower inference speed. After exploring the intrinsic relationship between the implicit depth information and semantic texture features of the binocular images, we propose an efficient and accurate 3D object detection algorithm, FCNet, in stereo images. First, we construct a multi-scale cost-volume containing implicit depth information using the normalized dot-product by generating multi-scale feature maps from the input stereo images. Secondly, the variant attention model enhances its global and local description, and the sparse region monitors the depth loss deep regression. Thirdly, for balancing the channel information preservation of the re-fused left-right feature maps and computational burden, a reweighting strategy is employed to enhance the feature correlation in merging the last-layer features of binocular images. Extensive experiment results on the challenging KITTI benchmark demonstrate that the proposed algorithm achieves better performance, including a lower computational cost and higher inference speed in 3D object detection.
关键词	3D object detection deep learning stereo matching multi-scale cost-volume channel similarity parallel convolutional attention
DOI	10.3390/e24081121
收录类别	SCI
语种	英语
资助项目	Guizhou Science and Technology Foundation[(2016) 1054] ; Guizhou Province Joint funding Project[LH (2017) 7226] ; Guizhou University Academic New Seeding training and Innovation and Exploration Project[(2017) 5788]
WOS研究方向	Physics
WOS类目	Physics, Multidisciplinary
WOS记录号	WOS:000846029000001
出版者	MDPI
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19449
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Liu, Ziyan
作者单位	1.Guizhou Univ, Coll Big Data & Informat Engn, Guiyang 550025, Peoples R China 2.Guizhou Univ, State Key Lab Publ Big Data, Guiyang 550025, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Wu, Yingyu,Liu, Ziyan,Chen, Yunlei,et al. FCNet: Stereo 3D Object Detection with Feature Correlation Networks[J]. ENTROPY,2022,24(8):17.
APA	Wu, Yingyu.,Liu, Ziyan.,Chen, Yunlei.,Zheng, Xuhui.,Zhang, Qian.,...&Tang, Guangming.(2022).FCNet: Stereo 3D Object Detection with Feature Correlation Networks.ENTROPY,24(8),17.
MLA	Wu, Yingyu,et al."FCNet: Stereo 3D Object Detection with Feature Correlation Networks".ENTROPY 24.8(2022):17.