Video Analysis and Rule-Based Reasoning for Driving Maneuver Classification at Intersections
We propose a system for monitoring the driving maneuver at road intersections using rule-based reasoning and deep learning-based computer vision techniques. Along with detecting and classifying turning movements online, the system also detects violations such as ignoring STOP signs and failing to yi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9761233/ |
| _version_ | 1818157593160318976 |
|---|---|
| author | Zakaria Charouh Amal Ezzouhri Mounir Ghogho Zouhair Guennoun |
| author_facet | Zakaria Charouh Amal Ezzouhri Mounir Ghogho Zouhair Guennoun |
| author_sort | Zakaria Charouh |
| collection | DOAJ |
| description | We propose a system for monitoring the driving maneuver at road intersections using rule-based reasoning and deep learning-based computer vision techniques. Along with detecting and classifying turning movements online, the system also detects violations such as ignoring STOP signs and failing to yield the right-of-way to other drivers. There is no distinction between temporarily and permanently stopped vehicles in the majority of frameworks proposed in the literature. Therefore, to conduct an accurate right-of-way study, permanently stopped vehicles should be excluded not to confound the results. Moreover, we also propose in this work a low-cost Convolutional Neural Network (CNN)-based object detection framework able to detect moving and temporally stopped vehicles. The detection framework combines the reasoning system with background subtraction and a CNN-based object detector. The obtained results are promising. Compared to the conventional CNN-based methods, the detection framework reduces the execution time of the object detection module by about 30% (i.e., 54.1 instead of 75ms/image) while preserving the same detection reliability. The accuracy of trajectory recognition is 95.32%, that of the zero-speed detection is 96.67%, and the right-of-way detection was perfect. |
| first_indexed | 2024-12-11T15:16:39Z |
| format | Article |
| id | doaj.art-0ef1ff8d824c49d09f769c41e51afcd7 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-11T15:16:39Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-0ef1ff8d824c49d09f769c41e51afcd72022-12-22T01:00:32ZengIEEEIEEE Access2169-35362022-01-0110451024511110.1109/ACCESS.2022.31691409761233Video Analysis and Rule-Based Reasoning for Driving Maneuver Classification at IntersectionsZakaria Charouh0https://orcid.org/0000-0003-2867-5491Amal Ezzouhri1https://orcid.org/0000-0002-4790-1442Mounir Ghogho2https://orcid.org/0000-0002-0055-7867Zouhair Guennoun3https://orcid.org/0000-0002-7142-0550ERSC Team, Mohammadia Engineering School, Mohammed V University, Rabat, MoroccoERSC Team, Mohammadia Engineering School, Mohammed V University, Rabat, MoroccoTICLab, International University of Rabat, Rabat, MoroccoERSC Team, Mohammadia Engineering School, Mohammed V University, Rabat, MoroccoWe propose a system for monitoring the driving maneuver at road intersections using rule-based reasoning and deep learning-based computer vision techniques. Along with detecting and classifying turning movements online, the system also detects violations such as ignoring STOP signs and failing to yield the right-of-way to other drivers. There is no distinction between temporarily and permanently stopped vehicles in the majority of frameworks proposed in the literature. Therefore, to conduct an accurate right-of-way study, permanently stopped vehicles should be excluded not to confound the results. Moreover, we also propose in this work a low-cost Convolutional Neural Network (CNN)-based object detection framework able to detect moving and temporally stopped vehicles. The detection framework combines the reasoning system with background subtraction and a CNN-based object detector. The obtained results are promising. Compared to the conventional CNN-based methods, the detection framework reduces the execution time of the object detection module by about 30% (i.e., 54.1 instead of 75ms/image) while preserving the same detection reliability. The accuracy of trajectory recognition is 95.32%, that of the zero-speed detection is 96.67%, and the right-of-way detection was perfect.https://ieeexplore.ieee.org/document/9761233/Monitoringdriving behaviorroad intersectionAI~reasoningmaneuver classificationcomputer vision |
| spellingShingle | Zakaria Charouh Amal Ezzouhri Mounir Ghogho Zouhair Guennoun Video Analysis and Rule-Based Reasoning for Driving Maneuver Classification at Intersections IEEE Access Monitoring driving behavior road intersection AI~reasoning maneuver classification computer vision |
| title | Video Analysis and Rule-Based Reasoning for Driving Maneuver Classification at Intersections |
| title_full | Video Analysis and Rule-Based Reasoning for Driving Maneuver Classification at Intersections |
| title_fullStr | Video Analysis and Rule-Based Reasoning for Driving Maneuver Classification at Intersections |
| title_full_unstemmed | Video Analysis and Rule-Based Reasoning for Driving Maneuver Classification at Intersections |
| title_short | Video Analysis and Rule-Based Reasoning for Driving Maneuver Classification at Intersections |
| title_sort | video analysis and rule based reasoning for driving maneuver classification at intersections |
| topic | Monitoring driving behavior road intersection AI~reasoning maneuver classification computer vision |
| url | https://ieeexplore.ieee.org/document/9761233/ |
| work_keys_str_mv | AT zakariacharouh videoanalysisandrulebasedreasoningfordrivingmaneuverclassificationatintersections AT amalezzouhri videoanalysisandrulebasedreasoningfordrivingmaneuverclassificationatintersections AT mounirghogho videoanalysisandrulebasedreasoningfordrivingmaneuverclassificationatintersections AT zouhairguennoun videoanalysisandrulebasedreasoningfordrivingmaneuverclassificationatintersections |