Driver Distraction Detection Based on Multi-scale Feature Fusion Network
The occurrence of road traffic accidents has increased year by year.Driver inattention during driving is one of the major causes of traffic accidents.In this paper,we utilize multi-source data to detect driver distraction.However,the correlations derived from multi-source data will generate feature...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial office of Computer Science
2022-11-01
|
| Series: | Jisuanji kexue |
| Subjects: | |
| Online Access: | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-11-170.pdf |
| _version_ | 1797845134103019520 |
|---|---|
| author | ZHANG Yu-xin, CHEN Yi-qiang |
| author_facet | ZHANG Yu-xin, CHEN Yi-qiang |
| author_sort | ZHANG Yu-xin, CHEN Yi-qiang |
| collection | DOAJ |
| description | The occurrence of road traffic accidents has increased year by year.Driver inattention during driving is one of the major causes of traffic accidents.In this paper,we utilize multi-source data to detect driver distraction.However,the correlations derived from multi-source data will generate feature of high-dimensional entanglement.Existing methods perform similar processing for data of different sources or simply stick to concatenate multi-source features,which are not easy to catch the key feature of high-dimensional entanglement.And distracted driving can be affected by many factors.Supervised methods might cause misclassification when the type of driver distraction does not exist in the set of the known categories.Therefore,we propose a multi-dcale feature fusion network approach to tackle these challenges.Basically,it first learns low-dimensional representations from multi-source data through multiple embedding subnetworks,and then proposes a multi-scale feature Fusion method to aggregate these representations from the perspective of spatial-temporal correlation,thereby reducing the entanglement of feature.Finally,we utilize a ConvLSTM encoder-decoder model to detect driver distraction.Experimental results on a public loaded drive dataset show that the proposed method outperforms the existing methods. |
| first_indexed | 2024-04-09T17:33:40Z |
| format | Article |
| id | doaj.art-71d80c8b64444205944c158d64633513 |
| institution | Directory Open Access Journal |
| issn | 1002-137X |
| language | zho |
| last_indexed | 2024-04-09T17:33:40Z |
| publishDate | 2022-11-01 |
| publisher | Editorial office of Computer Science |
| record_format | Article |
| series | Jisuanji kexue |
| spelling | doaj.art-71d80c8b64444205944c158d646335132023-04-18T02:32:50ZzhoEditorial office of Computer ScienceJisuanji kexue1002-137X2022-11-01491117017810.11896/jsjkx.211000040Driver Distraction Detection Based on Multi-scale Feature Fusion NetworkZHANG Yu-xin, CHEN Yi-qiang01 Global Energy Interconnection Development and Cooperation Organization,Beijing 100031,China ;2 Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100094,ChinaThe occurrence of road traffic accidents has increased year by year.Driver inattention during driving is one of the major causes of traffic accidents.In this paper,we utilize multi-source data to detect driver distraction.However,the correlations derived from multi-source data will generate feature of high-dimensional entanglement.Existing methods perform similar processing for data of different sources or simply stick to concatenate multi-source features,which are not easy to catch the key feature of high-dimensional entanglement.And distracted driving can be affected by many factors.Supervised methods might cause misclassification when the type of driver distraction does not exist in the set of the known categories.Therefore,we propose a multi-dcale feature fusion network approach to tackle these challenges.Basically,it first learns low-dimensional representations from multi-source data through multiple embedding subnetworks,and then proposes a multi-scale feature Fusion method to aggregate these representations from the perspective of spatial-temporal correlation,thereby reducing the entanglement of feature.Finally,we utilize a ConvLSTM encoder-decoder model to detect driver distraction.Experimental results on a public loaded drive dataset show that the proposed method outperforms the existing methods.https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-11-170.pdfdriver distraction|unsupervised learning|multi-source|multi-scale fusion|encoder-decoder |
| spellingShingle | ZHANG Yu-xin, CHEN Yi-qiang Driver Distraction Detection Based on Multi-scale Feature Fusion Network Jisuanji kexue driver distraction|unsupervised learning|multi-source|multi-scale fusion|encoder-decoder |
| title | Driver Distraction Detection Based on Multi-scale Feature Fusion Network |
| title_full | Driver Distraction Detection Based on Multi-scale Feature Fusion Network |
| title_fullStr | Driver Distraction Detection Based on Multi-scale Feature Fusion Network |
| title_full_unstemmed | Driver Distraction Detection Based on Multi-scale Feature Fusion Network |
| title_short | Driver Distraction Detection Based on Multi-scale Feature Fusion Network |
| title_sort | driver distraction detection based on multi scale feature fusion network |
| topic | driver distraction|unsupervised learning|multi-source|multi-scale fusion|encoder-decoder |
| url | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-11-170.pdf |
| work_keys_str_mv | AT zhangyuxinchenyiqiang driverdistractiondetectionbasedonmultiscalefeaturefusionnetwork |