인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2025.5
- 수록면
- 618 - 626 (9page)
- DOI
- 10.9717/kmms.2025.05.28.5.618
이용수
초록· 키워드
Recent urbanization and population growth have created significant challenges in transportation due to increased residential density and the growing number of vehicles. Issues such as traffic congestion, accidents, and environmental pollution are major factors hindering sustainable urban development. To address these challenges, the necessity for Smart Traffic Systems has emerged, which can optimize vehicle flow and enhance safety through real-time data collection and analysis. This study aims to design a smart traffic system and video processing analysis system based on the latest image recognition technology, YOLO v11 (You Only Look Once). To achieve this, we implemented a mapping system (Cam2WorldMapper) utilizing the YOLOv11-n learning model and OpenCV's perspective transform method, enabling real-time monitoring of the traffic system in conjunction with speed coordinate systems. YOLOv11 demonstrates a high inference speed of 588 FPS, achieving a mAP@0.5 of 66% and an F1 score of 69.6%, indicating its capability for accurate traffic situation detection. Furthermore, the system visualizes traffic data and provides intuitive information to users, thereby enhancing the efficiency of traffic management.
상세정보 수정요청해당 페이지 내 제목·저자·목차·페이지정보가 잘못된 경우 알려주세요!
목차
- ABSTRACT
- 1. 서론
- 2. 기존 연구
- 3. 제안 방법
- 4. 실험 결과 및 분석
- 5. 결론
- REFERENCE
참고문헌
참고문헌 신청최근 본 자료
UCI(KEPA) : I410-151-25-02-093119762