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
- 학위논문
- 저자정보
- 지도교수
- 기석철
- 발행연도
- 2022
- 저작권
- 충북대학교 논문은 저작권에 의해 보호받습니다.
이용수40
이 논문의 연구 히스토리 (2)
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
This paper proposes a detection method for parking areas and
collision risk areas in parking situations. Deep learning algorithms
using area detection use semantic segmentation, a method of classifying
pixels into semantic segmentation. The main architecture of this paper
is based on a harmonic densely connected network and cross stage
partial network. The dataset was calibrated for four 190-degree
wide-angle cameras to generate 500 AVM images based on the Chungbuk
National University parking lot, and an experiment was performed based
on this dataset. In the experimental results, the available parking
area is visualized by detecting the parking line, the parking area, and
the available driving area in the AVM image, and visualized the area
not detected in the semantic segmentation as a collision risk area to
derive the result. According to proposed Attention CSPHarDNet model,
experimental results were 81.89% mIoU and 18.36 FPS in the NVIDIA
Xavier environment.
collision risk areas in parking situations. Deep learning algorithms
using area detection use semantic segmentation, a method of classifying
pixels into semantic segmentation. The main architecture of this paper
is based on a harmonic densely connected network and cross stage
partial network. The dataset was calibrated for four 190-degree
wide-angle cameras to generate 500 AVM images based on the Chungbuk
National University parking lot, and an experiment was performed based
on this dataset. In the experimental results, the available parking
area is visualized by detecting the parking line, the parking area, and
the available driving area in the AVM image, and visualized the area
not detected in the semantic segmentation as a collision risk area to
derive the result. According to proposed Attention CSPHarDNet model,
experimental results were 81.89% mIoU and 18.36 FPS in the NVIDIA
Xavier environment.
목차
차례 ···············································································································································ⅰAbstract ·······································································································································ⅱList of Figures ···························································································································ⅲⅠ. 서 론 ·································································································································· 11. 연구 배경 ·································································································································· 22. 연구 목적 ·································································································································· 33. 관련 연구 ·································································································································· 5Ⅱ. 전처리 ···································································································································· 121. 카메라 왜곡 보정 ················································································································· 122. 카메라 내부 파라미터 보정 ······························································································· 143. 카메라 외부 파리미터 보정 ······························································································· 154. AVM 이미지 보정 ··············································································································· 16Ⅲ. 주차영역 및 충돌 위험 영역 검출 알고리즘 ·····················································171. CSPHarDNet ························································································································· 172. Attention CSPHarDNet ······································································································ 183. 네트워크 학습 기술 ············································································································· 194. Data Augmentation ············································································································· 225. 네트워크 최적화 ············································································································· 23Ⅳ. 실험 ········································································································································· 271. 실험환경 및 평가 방법 ······································································································· 272. 실험결과 ································································································································· 32Ⅴ. 결론 ········································································································································· 41참고문헌 ··········································································································································· 42감사의 글 ······································································································································· 46
최근 본 자료
댓글(0)
0