SPBA-Net point cloud object detection with sparse attention and box aligning

被引:0
|
作者
Sha, Haojie [1 ]
Gao, Qingrui [1 ]
Zeng, Hao [2 ]
Li, Kai [1 ]
Li, Wang [1 ]
Zhang, Xuande [1 ]
Wang, Xiaohui [1 ]
机构
[1] Qingdao Univ, Coll Appl Technol, Qingdao 266100, Peoples R China
[2] Chinese Acad Sci, Inst Software, Beijing 100000, Peoples R China
来源
SCIENTIFIC REPORTS | 2024年 / 14卷 / 01期
关键词
3D object detection; Keypoint guided sparse attention; Instance-wise box aligning;
D O I
10.1038/s41598-024-77097-z
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Object detection in point clouds is essential for various applications, including autonomous navigation, household robots, and augmented/virtual reality. However, during voxelization and Bird's Eye View transformation, local point cloud data often remains sparse due to non-target areas and noise points, posing a significant challenge for feature extraction. In this paper, we propose a novel mechanism named Keypoint Guided Sparse Attention (KGSA) to enhance the semantic information of point clouds by calculating Euclidean distances between selected keypoints and others. Additionally, we introduce Instance-wise Box Aligning, a method for expanding predicted boxes and clustering the points within them to achieve precise alignment between predicted bounding boxes and ground-truth targets. Experimental results demonstrate the superiority of our proposed SPBA-Net in 3D object detection on point clouds compared to other state-of-the-art methods.The datasets used and/or analysed during the current study available from the corresponding author on reasonable request.
引用
收藏
页数:10
相关论文
共 50 条
  • [41] Time and Cost-Efficient Bathymetric Mapping System using Sparse Point Cloud Generation and Automatic Object Detection
    Pulido, Andres
    Qin, Ruoyao
    Diaz, Antonio
    Ortega, Andrew
    Ifju, Peter
    Shin, Jaejeong
    2022 OCEANS HAMPTON ROADS, 2022,
  • [42] GA-NET: Global Attention Network for Point Cloud Semantic Segmentation
    Deng, Shuang
    Dong, Qiulei
    IEEE SIGNAL PROCESSING LETTERS, 2021, 28 : 1300 - 1304
  • [43] Visual Object Detection based LiDAR Point Cloud Classification
    Muhammad, Sualeh
    Gon-Woo, Kim
    2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING (BIGCOMP 2020), 2020, : 438 - 440
  • [44] Covariance based point cloud descriptors for object detection and recognition
    Fehr, Duc
    Beksi, William J.
    Zermas, Dimitris
    Papanikolopoulos, Nikolaos
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2016, 142 : 80 - 93
  • [45] Point Cloud Compression: Impact on Object Detection in Outdoor Contexts
    Garrote, Luis
    Perdiz, Joao
    da Silva Cruz, Luis A.
    Nunes, Urbano J.
    SENSORS, 2022, 22 (15)
  • [46] Point-to-Box Network for Accurate Object Detection via Single Point Supervision
    Chen, Pengfei
    Yu, Xuehui
    Han, Xumeng
    Hassan, Najmul
    Wang, Kai
    Li, Jiachen
    Zhao, Jian
    Shi, Humphrey
    Han, Zhenjun
    Ye, Qixiang
    COMPUTER VISION, ECCV 2022, PT IX, 2022, 13669 : 51 - 67
  • [47] STD: Sparse-to-Dense 3D Object Detector for Point Cloud
    Yang, Zetong
    Sun, Yanan
    Liu, Shu
    Shen, Xiaoyong
    Jia, Jiaya
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 1951 - 1960
  • [48] Grid self-attention mechanism 3D object detection method based on raw point cloud
    Lu B.
    Sun Y.
    Yang Z.
    Tongxin Xuebao/Journal on Communications, 2023, 44 (10): : 72 - 84
  • [49] Muti-Frame Point Cloud Feature Fusion Based on Attention Mechanisms for 3D Object Detection
    Zhai, Zhenyu
    Wang, Qiantong
    Pan, Zongxu
    Gao, Zhentong
    Hu, Wenlong
    SENSORS, 2022, 22 (19)
  • [50] Video Sparse Transformer With Attention-Guided Memory for Video Object Detection
    Fujitake, Masato
    Sugimoto, Akihiro
    IEEE ACCESS, 2022, 10 : 65886 - 65900