Improving efficiency of DNN-based relocalization module for autonomous driving with server-side computing
Abstract The substantial computational demands associated with Deep Neural Network (DNN)-based camera relocalization during the reasoning process impede their integration into autonomous vehicles. Cost and energy efficiency considerations may dissuade automotive manufacturers from employing high-com...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-01-01
|
| Series: | Journal of Cloud Computing: Advances, Systems and Applications |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13677-024-00592-1 |
| _version_ | 1797276294613827584 |
|---|---|
| author | Dengbo Li Hanning Zhang Jieren Cheng Bernie Liu |
| author_facet | Dengbo Li Hanning Zhang Jieren Cheng Bernie Liu |
| author_sort | Dengbo Li |
| collection | DOAJ |
| description | Abstract The substantial computational demands associated with Deep Neural Network (DNN)-based camera relocalization during the reasoning process impede their integration into autonomous vehicles. Cost and energy efficiency considerations may dissuade automotive manufacturers from employing high-computing equipment, limiting the adoption of advanced models. In response to this challenge, we present an innovative edge cloud collaborative framework designed for camera relocalization in autonomous vehicles. Specifically, we strategically offload certain modules of the neural network to the server and evaluate the inference time of data frames under different network segmentation schemes to guide our offloading decisions. Our findings highlight the vital role of server-side offloading in DNN-based camera relocation for autonomous vehicles, and we also discuss the results of data fusion. Finally, we validate the effectiveness of our proposed framework through experimental evaluation. |
| first_indexed | 2024-03-07T15:26:11Z |
| format | Article |
| id | doaj.art-d4c342d057244789a2cab7a8375e1b8f |
| institution | Directory Open Access Journal |
| issn | 2192-113X |
| language | English |
| last_indexed | 2024-03-07T15:26:11Z |
| publishDate | 2024-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Cloud Computing: Advances, Systems and Applications |
| spelling | doaj.art-d4c342d057244789a2cab7a8375e1b8f2024-03-05T16:43:27ZengSpringerOpenJournal of Cloud Computing: Advances, Systems and Applications2192-113X2024-01-0113111210.1186/s13677-024-00592-1Improving efficiency of DNN-based relocalization module for autonomous driving with server-side computingDengbo Li0Hanning Zhang1Jieren Cheng2Bernie Liu3School of Computer Science and Technology, Hainan UniversityChina Unicom(Hainan) Innovation Research InstituteSchool of Computer Science and Technology, Hainan UniversityHainan Shuyi Technology Co., LtdAbstract The substantial computational demands associated with Deep Neural Network (DNN)-based camera relocalization during the reasoning process impede their integration into autonomous vehicles. Cost and energy efficiency considerations may dissuade automotive manufacturers from employing high-computing equipment, limiting the adoption of advanced models. In response to this challenge, we present an innovative edge cloud collaborative framework designed for camera relocalization in autonomous vehicles. Specifically, we strategically offload certain modules of the neural network to the server and evaluate the inference time of data frames under different network segmentation schemes to guide our offloading decisions. Our findings highlight the vital role of server-side offloading in DNN-based camera relocation for autonomous vehicles, and we also discuss the results of data fusion. Finally, we validate the effectiveness of our proposed framework through experimental evaluation.https://doi.org/10.1186/s13677-024-00592-1Autonomous DrivingOffloadingRelocalizationEdge Cloud Collaboration |
| spellingShingle | Dengbo Li Hanning Zhang Jieren Cheng Bernie Liu Improving efficiency of DNN-based relocalization module for autonomous driving with server-side computing Journal of Cloud Computing: Advances, Systems and Applications Autonomous Driving Offloading Relocalization Edge Cloud Collaboration |
| title | Improving efficiency of DNN-based relocalization module for autonomous driving with server-side computing |
| title_full | Improving efficiency of DNN-based relocalization module for autonomous driving with server-side computing |
| title_fullStr | Improving efficiency of DNN-based relocalization module for autonomous driving with server-side computing |
| title_full_unstemmed | Improving efficiency of DNN-based relocalization module for autonomous driving with server-side computing |
| title_short | Improving efficiency of DNN-based relocalization module for autonomous driving with server-side computing |
| title_sort | improving efficiency of dnn based relocalization module for autonomous driving with server side computing |
| topic | Autonomous Driving Offloading Relocalization Edge Cloud Collaboration |
| url | https://doi.org/10.1186/s13677-024-00592-1 |
| work_keys_str_mv | AT dengboli improvingefficiencyofdnnbasedrelocalizationmoduleforautonomousdrivingwithserversidecomputing AT hanningzhang improvingefficiencyofdnnbasedrelocalizationmoduleforautonomousdrivingwithserversidecomputing AT jierencheng improvingefficiencyofdnnbasedrelocalizationmoduleforautonomousdrivingwithserversidecomputing AT bernieliu improvingefficiencyofdnnbasedrelocalizationmoduleforautonomousdrivingwithserversidecomputing |