Crowdsensing monitoring
| dc.contributor.author | Makri, Leyla | |
| dc.contributor.author | Khelifi, Zeyneb | |
| dc.contributor.author | Lounnas, Bilal | |
| dc.date.accessioned | 2024-07-15T09:06:32Z | |
| dc.date.available | 2024-07-15T09:06:32Z | |
| dc.date.issued | 2024-06 | |
| dc.description.abstract | The collaborative of crowdsensing and advanced sensing technologies can vastly improve environmental and infrastructure monitoring in cities through creative applications. Novel use cases tracked important metrics like air quality, noise levels and traffic patterns to provide communities with valuable data. In this work, propose a Kinect sensor that leverage computer vision for detecte obstacles in the roads.with adopt YOLO-v8 as obstacle detector,added a series of methods proposed for road obstacle detection, like a self-driving car system and Kinect approach that effectively mapped hazards in 3D for navigation safety. Based on those methodes we are going to integrated to generate system in the futures. Results indicated addressing limitations of traditional solutions by enabling timely, comprehensive data collection, bringing significant benefits in safety, costs, transportation resilience and urban management. Overall,this work is helping advance the potential of collaborative digital tools to revolutionize smarter, safer mobility for all through continuous learning. | |
| dc.identifier.uri | https://dspace.univ-msila.dz/handle/123456789/43748 | |
| dc.language.iso | en | |
| dc.publisher | University of Mohamed Boudiaf, M’sila | |
| dc.subject | Road obstacle detection | |
| dc.subject | Self-Driving cars | |
| dc.subject | Microsoft kinect sensor | |
| dc.subject | Obstacle avoidance systems | |
| dc.subject | Crowdsensing | |
| dc.subject | YOLOv8 | |
| dc.subject | Advanced sensor fusion | |
| dc.subject | 3D mapping | |
| dc.subject | Real-time detection accuracy | |
| dc.subject | Depth image enhancement | |
| dc.title | Crowdsensing monitoring | |
| dc.type | Thesis |