Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges
With recent developments, the performance of automotive radar has improved significantly. The next generation of 4D radar can achieve imaging capability in the form of high-resolution point clouds. In this context, we believe that the era of deep learning for radar perception has arrived. However, s...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/11/4208 |
| _version_ | 1827663951619424256 |
|---|---|
| author | Yi Zhou Lulu Liu Haocheng Zhao Miguel López-Benítez Limin Yu Yutao Yue |
| author_facet | Yi Zhou Lulu Liu Haocheng Zhao Miguel López-Benítez Limin Yu Yutao Yue |
| author_sort | Yi Zhou |
| collection | DOAJ |
| description | With recent developments, the performance of automotive radar has improved significantly. The next generation of 4D radar can achieve imaging capability in the form of high-resolution point clouds. In this context, we believe that the era of deep learning for radar perception has arrived. However, studies on radar deep learning are spread across different tasks, and a holistic overview is lacking. This review paper attempts to provide a big picture of the deep radar perception stack, including signal processing, datasets, labelling, data augmentation, and downstream tasks such as depth and velocity estimation, object detection, and sensor fusion. For these tasks, we focus on explaining how the network structure is adapted to radar domain knowledge. In particular, we summarise three overlooked challenges in deep radar perception, including multi-path effects, uncertainty problems, and adverse weather effects, and present some attempts to solve them. |
| first_indexed | 2024-03-10T00:52:28Z |
| format | Article |
| id | doaj.art-fefae3aa8a1942e784c22e8d39d1ec1e |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T00:52:28Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-fefae3aa8a1942e784c22e8d39d1ec1e2023-11-23T14:50:21ZengMDPI AGSensors1424-82202022-05-012211420810.3390/s22114208Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and ChallengesYi Zhou0Lulu Liu1Haocheng Zhao2Miguel López-Benítez3Limin Yu4Yutao Yue5Institute of Deep Perception Technology (JITRI), Wuxi 214000, ChinaInstitute of Deep Perception Technology (JITRI), Wuxi 214000, ChinaInstitute of Deep Perception Technology (JITRI), Wuxi 214000, ChinaDepartment of Electrical Engineering and Electronics, University of Liverpool, Liverpool L69 3GJ, UKDepartment of Electrical and Electronic Engineering, School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou 215123, ChinaInstitute of Deep Perception Technology (JITRI), Wuxi 214000, ChinaWith recent developments, the performance of automotive radar has improved significantly. The next generation of 4D radar can achieve imaging capability in the form of high-resolution point clouds. In this context, we believe that the era of deep learning for radar perception has arrived. However, studies on radar deep learning are spread across different tasks, and a holistic overview is lacking. This review paper attempts to provide a big picture of the deep radar perception stack, including signal processing, datasets, labelling, data augmentation, and downstream tasks such as depth and velocity estimation, object detection, and sensor fusion. For these tasks, we focus on explaining how the network structure is adapted to radar domain knowledge. In particular, we summarise three overlooked challenges in deep radar perception, including multi-path effects, uncertainty problems, and adverse weather effects, and present some attempts to solve them.https://www.mdpi.com/1424-8220/22/11/4208automotive radarsradar signal processingobject detectionmulti-sensor fusiondeep learningautonomous driving |
| spellingShingle | Yi Zhou Lulu Liu Haocheng Zhao Miguel López-Benítez Limin Yu Yutao Yue Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges Sensors automotive radars radar signal processing object detection multi-sensor fusion deep learning autonomous driving |
| title | Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges |
| title_full | Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges |
| title_fullStr | Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges |
| title_full_unstemmed | Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges |
| title_short | Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges |
| title_sort | towards deep radar perception for autonomous driving datasets methods and challenges |
| topic | automotive radars radar signal processing object detection multi-sensor fusion deep learning autonomous driving |
| url | https://www.mdpi.com/1424-8220/22/11/4208 |
| work_keys_str_mv | AT yizhou towardsdeepradarperceptionforautonomousdrivingdatasetsmethodsandchallenges AT lululiu towardsdeepradarperceptionforautonomousdrivingdatasetsmethodsandchallenges AT haochengzhao towardsdeepradarperceptionforautonomousdrivingdatasetsmethodsandchallenges AT miguellopezbenitez towardsdeepradarperceptionforautonomousdrivingdatasetsmethodsandchallenges AT liminyu towardsdeepradarperceptionforautonomousdrivingdatasetsmethodsandchallenges AT yutaoyue towardsdeepradarperceptionforautonomousdrivingdatasetsmethodsandchallenges |