300 GHz radar object recognition based on deep neural networks and transfer learning. Issue 10 (1st October 2020)

• Record Type: Journal Article
• Authors: Sheeny, Marcel; Wallace, Andrew; Wang, Sen
• Is Part Of: IET radar, sonar & navigation. Volume 14:Issue 10(2020)
• Page Start: 1483
• Page End: 1493
• Publication Date: 2020-10-01
• Subjects: radar imaging -- object detection -- millimetre wave radar -- optical radar -- learning (artificial intelligence) -- neural nets -- road vehicle radar -- object recognition; optical technologies -- future vehicle autonomy -- driver assistance -- adverse weather conditions -- automotive radar technology -- machine learning -- robust mapping -- deep neural networks -- 300 GHz radar images -- returned power data -- transfer learning -- multiple object scenes -- 300 GHz radar object recognition -- high‐resolution scene mapping -- frequency 300.0 GHz; Signal processing -- Periodicals; Radar -- Periodicals; Sonar -- Periodicals; Electronics in navigation -- Periodicals; Navigation -- Periodicals; 621.3848
• DOI: 10.1049/iet-rsn.2019.0601
• Languages: English
• ISSNs: 1751-8784

Abstract

Abstract : For high‐resolution scene mapping and object recognition, optical technologies such as cameras and LiDAR are the sensors of choice. However, for future vehicle autonomy and driver assistance in adverse weather conditions, improvements in automotive radar technology and the development of algorithms and machine learning for robust mapping and recognition are essential. In this study, the authors describe a methodology based on deep neural networks to recognise objects in 300 GHz radar images using the returned power data only, investigating robustness to changes in range, orientation and different receivers in a laboratory environment. As the training data is limited, they have also investigated the effects of transfer learning. As a necessary first step before road trials, they have also considered detection and classification in multiple object scenes.