التفاصيل البيبلوغرافية
| العنوان: |
Multi-spectral image fusion based on a new joint bilateral filter for video analytics ; 비디오 분석 기법을 위한 새로운 결합 양방향 필터 기반의 다중 스펙트럼 영상 융합에 관한 연구 |
| المؤلفون: |
Choi, Eun-Jin(최은진) |
| المساهمون: |
Park, Dong-Jo(박동조) |
| بيانات النشر: |
한국과학기술원 |
| سنة النشر: |
2011 |
| المجموعة: |
Korea Advanced Institute of Science and Technology: KOASAS - KAIST Open Access Self-Archiving System |
| مصطلحات موضوعية: |
Image Fusion, Bilateral Filter, Video Analytics, 영상 융합, 양방향 필터, 비디오 분석, 소곡면 필터, Facet Filter |
| الوصف: |
학위논문(석사) - 한국과학기술원 : 전기 및 전자공학과, 2011.2, [ v, 88 p. ] ; In this paper, we propose a novel human detection system with thermal and visible image sensors using a new joint bilateral filter. There is a limitation to the performance of devices which attempt to detect humans by using only one sensor. We therefore use two sensors: an infrared sensor and a color image sensor. To fuse the best features of both types of sensor in order to achieve superior performance in human detection, we use low-level image fusion. To carry out this image fusion process, we propose a new joint bilateral filter which is useful for fusion of the edge information in the visible image and the white region in the thermal image and segmentation method of thermal image by using the facet filter and determinant of Hessian matrix. This image fusion process effectively removes the regions of human shadow which is trouble of background subtraction. To achieve this effect, we make the background model with multi-spectral fusion results. The results from different pairs of current fused images and the background model are subtracted to detect the human effectively. Experimental results show that effective and easy human detection can be achieved by the proposed algorithm. ; 한국과학기술원 : 전기 및 전자공학과 |
| نوع الوثيقة: |
other/unknown material |
| اللغة: |
English |
| الاتاحة: |
http://hdl.handle.net/10203/180812
http://library.kaist.ac.kr/index.php?TargetPageName=wSrchAllDetailView.php&bibctrlno=467802 |
| رقم الانضمام: |
edsbas.3B8D426 |
| قاعدة البيانات: |
BASE |