Computer Vision Aided mmWave Beam Alignment in V2X Communications

被引:52
作者
Xu, Weihua [1 ,2 ]
Gao, Feifei [1 ,2 ]
Tao, Xiaoming [3 ]
Zhang, Jianhua [4 ]
Alkhateeb, Ahmed [5 ]
机构
[1] Tsinghua Univ, Inst Artificial Intelligence THUAI, Beijing 100084, Peoples R China
[2] Tsinghua Univ, Beijing Natl Res Ctr Informat Sci & Technol BNRist, Dept Automat, Beijing 100084, Peoples R China
[3] Tsinghua Univ, Dept Elect Engn, Beijing 100084, Peoples R China
[4] Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing 100876, Peoples R China
[5] Arizona State Univ, Sch Elect, Comp & Energy Engn, Tempe, AZ 85281 USA
基金
中国国家自然科学基金;
关键词
Cameras; Array signal processing; Laser radar; Radar tracking; Visualization; Three-dimensional displays; Radar detection; Deep learning; beam alignment; beam coherence time; computer vision; V2X communication; SEQUENCE DESIGN; SELECTION; CODEBOOK; TRACKING;
D O I
10.1109/TWC.2022.3213541
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Visual information, captured for example by cameras, can effectively reflect the sizes and locations of the environmental scattering objects, and thereby can be used to infer communications parameters like propagation directions, receiver powers, as well as the blockage status. In this paper, we propose a novel beam alignment framework that leverages images taken by cameras installed at the mobile user. Specifically, we utilize 3D object detection techniques to extract the size and location information of the dynamic vehicles around the mobile user, and design a deep neural network (DNN) to infer the optimal beam pair for transceivers without any pilot signal overhead. Moreover, to avoid performing beam alignment too frequently or too slowly, a beam coherence time (BCT) prediction method is developed based on the vision information. This can effectively improve the transmission rate compared with the beam alignment approach with the fixed BCT. Simulation results show that the proposed vision based beam alignment methods outperform the existing LIDAR and vision based solutions, and demand for much lower hardware cost and communication overhead.
引用
收藏
页码:2699 / 2714
页数:16
相关论文
共 41 条
[1]   A 3D CNN-LSTM-Based Image-to-Image Foreground Segmentation [J].
Akilan, Thangarajah ;
Wu, Qingming Jonathan ;
Safaei, Amin ;
Huo, Jie ;
Yang, Yimin .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2020, 21 (03) :959-971
[2]  
[Anonymous], VISION COMMUNICATION
[3]  
[Anonymous], Wireless InSite EM Propagation software v3.3.3
[4]   A Survey on 3D Object Detection Methods for Autonomous Driving Applications [J].
Arnold, Eduardo ;
Al-Jarrah, Omar Y. ;
Dianati, Mehrdad ;
Fallah, Saber ;
Oxtoby, David ;
Mouzakitis, Alex .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2019, 20 (10) :3782-3795
[5]  
Babu S, 2020, 2020 IEEE 3RD 5G WORLD FORUM (5GWF), P263, DOI [10.1109/5GWF49715.2020.9221228, 10.1109/5gwf49715.2020.9221228]
[6]   A Smart Road Side Unit in a Microeolic Box to Provide Edge Computing for Vehicular Applications [J].
Busacca, Fabio ;
Grasso, Christian ;
Palazzo, Sergio ;
Schembra, Giovanni .
IEEE TRANSACTIONS ON GREEN COMMUNICATIONS AND NETWORKING, 2023, 7 (01) :194-210
[7]  
CARLA, About us
[8]   Vision-Position Multi-Modal Beam Prediction Using Real Millimeter Wave Datasets [J].
Charan, Gouranga ;
Osman, Tawfik ;
Hredzak, Andrew ;
Thawdar, Ngwe ;
Alkhateeb, Ahmed .
2022 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC), 2022, :2727-2731
[9]   Vision-Aided 6G Wireless Communications: Blockage Prediction and Proactive Handoff [J].
Charan, Gouranga ;
Alrabeiah, Muhammad ;
Alkhateeb, Ahmed .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2021, 70 (10) :10193-10208
[10]   Self-Driving Cars [J].
Daily, Mike ;
Medasani, Swarup ;
Behringer, Reinhold ;
Trivedi, Mohan .
COMPUTER, 2017, 50 (12) :18-23