ZTE Communications ›› 2022, Vol. 20 ›› Issue (S1): 36-43.doi: 10.12142/ZTECOM.2022S1006

• Research Paper • Previous Articles     Next Articles

Intelligent Antenna Attitude Parameters Measurement Based on Deep Learning SSD Model

FAN Guotian1(), WANG Zhibin2   

  1. 1.ZTE Corporation, Shenzhen 518057, China
    2.Xidian University, Xi’an 710071, China
  • Received:2021-04-16 Online:2022-01-25 Published:2022-03-01
  • About author:FAN Guotian (fan.guotian@zte.com.cn) received his M.Sc. degree in network systems from Univeristy of Sunderland, UK in 2008. Currently he is working as a deputy director in ZTE Corporation, China. His research interests include big-data mining, deep learning of digital image, intelligent planning and optimization of wireless network.|WANG Zhibin received his master’s degree in computer science and technology from Xidian University, China in 2020. He is now a Ph.D. candidate of computer science and technology, Xidian University. His main research interests include database SQL engine & executor related machine learning and deep learning, spatio temporal data retrieval, data analysis, and image analysis and processing.
  • Supported by:
    ZTE Industry?Academia?Research Cooperation Funds(HC?CN?20181030016)


Due to the consideration of safety, non-contact measurement methods are becoming more acceptable. However, massive measurement will bring high labor-cost and low working efficiency. To address these limitations, this paper introduces a deep learning model for the antenna attitude parameter measurement, which can be divided into an antenna location phase and a calculation phase of the attitude parameter. In the first phase, a single shot multibox detector (SSD) is applied to automatically recognize and discover the antenna from pictures taken by drones. In the second phase, the located antennas’ feature lines are extracted and their attitude parameters are then calculated mathematically. Experiments show that the proposed algorithms outperform existing related works in efficiency and accuracy, and therefore can be effectively used in engineering applications.

Key words: deep learning, drone, object detection, SSD algorithm, visual measurement, antenna attitude parameters