A Survey on Deep-Learning-Based LiDAR 3D Object Detection for Autonomous Driving
LiDAR is a commonly used sensor for autonomous driving to make accurate, robust, and fast decision-making when driving. The sensor is used in the perception system, especially object detection, to understand the driving environment. Although 2D object detection has succeeded during the deep-learning...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/24/9577 |
| _version_ | 1797455411859685376 |
|---|---|
| author | Simegnew Yihunie Alaba John E. Ball |
| author_facet | Simegnew Yihunie Alaba John E. Ball |
| author_sort | Simegnew Yihunie Alaba |
| collection | DOAJ |
| description | LiDAR is a commonly used sensor for autonomous driving to make accurate, robust, and fast decision-making when driving. The sensor is used in the perception system, especially object detection, to understand the driving environment. Although 2D object detection has succeeded during the deep-learning era, the lack of depth information limits understanding of the driving environment and object location. Three-dimensional sensors, such as LiDAR, give 3D information about the surrounding environment, which is essential for a 3D perception system. Despite the attention of the computer vision community to 3D object detection due to multiple applications in robotics and autonomous driving, there are challenges, such as scale change, sparsity, uneven distribution of LiDAR data, and occlusions. Different representations of LiDAR data and methods to minimize the effect of the sparsity of LiDAR data have been proposed. This survey presents the LiDAR-based 3D object detection and feature-extraction techniques for LiDAR data. The 3D coordinate systems differ in camera and LiDAR-based datasets and methods. Therefore, the commonly used 3D coordinate systems are summarized. Then, state-of-the-art LiDAR-based 3D object-detection methods are reviewed with a selected comparison among methods. |
| first_indexed | 2024-03-09T15:54:01Z |
| format | Article |
| id | doaj.art-ec33142d60bf48cba6345c2cca04560b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T15:54:01Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-ec33142d60bf48cba6345c2cca04560b2023-11-24T17:51:55ZengMDPI AGSensors1424-82202022-12-012224957710.3390/s22249577A Survey on Deep-Learning-Based LiDAR 3D Object Detection for Autonomous DrivingSimegnew Yihunie Alaba0John E. Ball1Department of Electrical and Computer Engineering, James Worth Bagley College of Engineering, Mississippi State University, Starkville, MS 39762, USADepartment of Electrical and Computer Engineering, James Worth Bagley College of Engineering, Mississippi State University, Starkville, MS 39762, USALiDAR is a commonly used sensor for autonomous driving to make accurate, robust, and fast decision-making when driving. The sensor is used in the perception system, especially object detection, to understand the driving environment. Although 2D object detection has succeeded during the deep-learning era, the lack of depth information limits understanding of the driving environment and object location. Three-dimensional sensors, such as LiDAR, give 3D information about the surrounding environment, which is essential for a 3D perception system. Despite the attention of the computer vision community to 3D object detection due to multiple applications in robotics and autonomous driving, there are challenges, such as scale change, sparsity, uneven distribution of LiDAR data, and occlusions. Different representations of LiDAR data and methods to minimize the effect of the sparsity of LiDAR data have been proposed. This survey presents the LiDAR-based 3D object detection and feature-extraction techniques for LiDAR data. The 3D coordinate systems differ in camera and LiDAR-based datasets and methods. Therefore, the commonly used 3D coordinate systems are summarized. Then, state-of-the-art LiDAR-based 3D object-detection methods are reviewed with a selected comparison among methods.https://www.mdpi.com/1424-8220/22/24/9577autonomous vehiclesclassificationdeep learningdeep learning for point cloud processingLiDARsparsity |
| spellingShingle | Simegnew Yihunie Alaba John E. Ball A Survey on Deep-Learning-Based LiDAR 3D Object Detection for Autonomous Driving Sensors autonomous vehicles classification deep learning deep learning for point cloud processing LiDAR sparsity |
| title | A Survey on Deep-Learning-Based LiDAR 3D Object Detection for Autonomous Driving |
| title_full | A Survey on Deep-Learning-Based LiDAR 3D Object Detection for Autonomous Driving |
| title_fullStr | A Survey on Deep-Learning-Based LiDAR 3D Object Detection for Autonomous Driving |
| title_full_unstemmed | A Survey on Deep-Learning-Based LiDAR 3D Object Detection for Autonomous Driving |
| title_short | A Survey on Deep-Learning-Based LiDAR 3D Object Detection for Autonomous Driving |
| title_sort | survey on deep learning based lidar 3d object detection for autonomous driving |
| topic | autonomous vehicles classification deep learning deep learning for point cloud processing LiDAR sparsity |
| url | https://www.mdpi.com/1424-8220/22/24/9577 |
| work_keys_str_mv | AT simegnewyihuniealaba asurveyondeeplearningbasedlidar3dobjectdetectionforautonomousdriving AT johneball asurveyondeeplearningbasedlidar3dobjectdetectionforautonomousdriving AT simegnewyihuniealaba surveyondeeplearningbasedlidar3dobjectdetectionforautonomousdriving AT johneball surveyondeeplearningbasedlidar3dobjectdetectionforautonomousdriving |