EMOS: Enhanced moving object detection and classification via sensor fusion and noise filtering
Dynamic object detection is essential for ensuring safe and reliable autonomous driving. Recently, light detection and ranging (LiDAR)-based object detection has been introduced and shown excellent performance on various benchmarks. Although LiDAR sensors have excellent accuracy in estimating distan...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Electronics and Telecommunications Research Institute (ETRI)
2023-10-01
|
| Series: | ETRI Journal |
| Subjects: | |
| Online Access: | https://doi.org/10.4218/etrij.2023-0109 |
| _version_ | 1827767658284580864 |
|---|---|
| author | Dongjin Lee Seung-Jun Han Kyoung-Wook Min Jungdan Choi Cheong Hee Park |
| author_facet | Dongjin Lee Seung-Jun Han Kyoung-Wook Min Jungdan Choi Cheong Hee Park |
| author_sort | Dongjin Lee |
| collection | DOAJ |
| description | Dynamic object detection is essential for ensuring safe and reliable autonomous driving. Recently, light detection and ranging (LiDAR)-based object detection has been introduced and shown excellent performance on various benchmarks. Although LiDAR sensors have excellent accuracy in estimating distance, they lack texture or color information and have a lower resolution than conventional cameras. In addition, performance degradation occurs when a LiDAR-based object detection model is applied to different driving environments or when sensors from different LiDAR manufacturers are utilized owing to the domain gap phenomenon. To address these issues, a sensor-fusion-based object detection and classification method is proposed. The proposed method operates in real time, making it suitable for integration into autonomous vehicles. It performs well on our custom dataset and on publicly available datasets, demonstrating its effectiveness in real-world road environments. In addition, we will make available a novel three-dimensional moving object detection dataset called ETRI 3D MOD. |
| first_indexed | 2024-03-11T12:01:09Z |
| format | Article |
| id | doaj.art-e3494fda33a646468d55f68b70f55cb1 |
| institution | Directory Open Access Journal |
| issn | 1225-6463 |
| language | English |
| last_indexed | 2024-03-11T12:01:09Z |
| publishDate | 2023-10-01 |
| publisher | Electronics and Telecommunications Research Institute (ETRI) |
| record_format | Article |
| series | ETRI Journal |
| spelling | doaj.art-e3494fda33a646468d55f68b70f55cb12023-11-08T05:10:22ZengElectronics and Telecommunications Research Institute (ETRI)ETRI Journal1225-64632023-10-0145584786110.4218/etrij.2023-010910.4218/etrij.2023-0109EMOS: Enhanced moving object detection and classification via sensor fusion and noise filteringDongjin LeeSeung-Jun HanKyoung-Wook MinJungdan ChoiCheong Hee ParkDynamic object detection is essential for ensuring safe and reliable autonomous driving. Recently, light detection and ranging (LiDAR)-based object detection has been introduced and shown excellent performance on various benchmarks. Although LiDAR sensors have excellent accuracy in estimating distance, they lack texture or color information and have a lower resolution than conventional cameras. In addition, performance degradation occurs when a LiDAR-based object detection model is applied to different driving environments or when sensors from different LiDAR manufacturers are utilized owing to the domain gap phenomenon. To address these issues, a sensor-fusion-based object detection and classification method is proposed. The proposed method operates in real time, making it suitable for integration into autonomous vehicles. It performs well on our custom dataset and on publicly available datasets, demonstrating its effectiveness in real-world road environments. In addition, we will make available a novel three-dimensional moving object detection dataset called ETRI 3D MOD.https://doi.org/10.4218/etrij.2023-0109autonomous drivingdeep learningimage classificationobject detectionsensor fusion |
| spellingShingle | Dongjin Lee Seung-Jun Han Kyoung-Wook Min Jungdan Choi Cheong Hee Park EMOS: Enhanced moving object detection and classification via sensor fusion and noise filtering ETRI Journal autonomous driving deep learning image classification object detection sensor fusion |
| title | EMOS: Enhanced moving object detection and classification via sensor fusion and noise filtering |
| title_full | EMOS: Enhanced moving object detection and classification via sensor fusion and noise filtering |
| title_fullStr | EMOS: Enhanced moving object detection and classification via sensor fusion and noise filtering |
| title_full_unstemmed | EMOS: Enhanced moving object detection and classification via sensor fusion and noise filtering |
| title_short | EMOS: Enhanced moving object detection and classification via sensor fusion and noise filtering |
| title_sort | emos enhanced moving object detection and classification via sensor fusion and noise filtering |
| topic | autonomous driving deep learning image classification object detection sensor fusion |
| url | https://doi.org/10.4218/etrij.2023-0109 |
| work_keys_str_mv | AT dongjinlee emosenhancedmovingobjectdetectionandclassificationviasensorfusionandnoisefiltering AT seungjunhan emosenhancedmovingobjectdetectionandclassificationviasensorfusionandnoisefiltering AT kyoungwookmin emosenhancedmovingobjectdetectionandclassificationviasensorfusionandnoisefiltering AT jungdanchoi emosenhancedmovingobjectdetectionandclassificationviasensorfusionandnoisefiltering AT cheongheepark emosenhancedmovingobjectdetectionandclassificationviasensorfusionandnoisefiltering |