메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색

논문 기본 정보

자료유형
학위논문
저자정보

이재광 (대전대학교, 대전대학교 대학원)

발행연도
2015
저작권
대전대학교 논문은 저작권에 의해 보호받습니다.

이용수0

표지
AI에게 요청하기
추천
검색

이 논문의 연구 히스토리 (2)

초록· 키워드

오류제보하기
This paper propose a temporal histogram ?based behavior pattern analysis and saved features of moving objects -based search descriptor algorithm to analyze the movement features of moving objects from the image inputted in real-time. For the purpose of detection, tracking and analysis of moving objects, it needs to be performed background learning which separated moving objects from the image background. Moving object is extracted as a background learning after identifying the object by using the coordinate correlation of the center of gravity is performed by the object tracking. Temporal histogram defines movement features pattern using x, y coordinates based on time axis, it compares each coordinates of objects for understanding its behavior pattern. The start frame, end frame, coordinates information and behavior information of each of the analysis object are stored and managed by the linked list. Creating a descriptor based on the stored features information and makes the image retrieval algorithm. Through experiments on self-collected demo video it confirmed a high recall and precision than existing methods. This System is expected to application on system which needs image retrieval and analysis of moving objects such as image data retrieval, supermarket, CCTV, department store.

목차

등록된 정보가 없습니다.

최근 본 자료

전체보기

댓글(0)

0