The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
본 논문에서는 색상 정보와 공간 임계화를 이용하여 장면에서 무광 표면 객체를 탐지하는 방법론을 제안합니다. 먼저, '깨끗한' 참조 이미지와 샘플 이미지의 색상 함량을 픽셀 단위로 비교하여 차이 이미지를 얻습니다. 그런 다음, 차이 영상의 공간적 임계화를 수행하여 관심 객체를 추출한 다음 형태학적 후처리를 수행하여 픽셀 노이즈를 제거합니다. 우리는 차이 이미지를 계산하기 위해 두 가지 대체 색 공간(HSV, CIE Lab)의 적용 가능성을 연구합니다. 마찬가지로, 우리는 차이 이미지의 로컬 공간 속성으로부터 전역 임계값을 결정하는 두 가지 공간 임계값 방법을 사용합니다. 우리는 현장 감시에서 제안된 접근 방식의 성능을 보여줍니다. 여기서 목표는 판지 상자와 같은 불필요한 물체가 나타나는지 선적 부두를 모니터링하는 것입니다. 접근 방식의 견고성을 분석하기 위해 실험에는 배경의 이질성, 그림자 존재 및 조명 변화와 같은 속성을 기반으로 '쉬움', '보통', '어려움'으로 분류된 세 가지 유형의 장면이 포함됩니다. 그리고 물체의 반사율과 채도 특성. 실험 결과는 '쉬움'과 '보통' 장면에서 상대적으로 좋은 인식 정확도가 달성되는 반면, '어려운' 장면은 향후 작업의 과제로 남아 있음을 보여줍니다.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Mika RAUTIAINEN, Timo OJALA, Hannu KAUNISKANGAS, "Detecting Perceptual Color Changes from Sequential Images for Scene Surveillance" in IEICE TRANSACTIONS on Information,
vol. E84-D, no. 12, pp. 1676-1683, December 2001, doi: .
Abstract: This paper proposes a methodology for detecting matte-surfaced objects on a scene using color information and spatial thresholding. First, a difference image is obtained via a pixel-wise comparison of the color content of a 'clean' reference image and a sample image. Then, spatial thresholding of the difference image is performed to extract any objects of interest, followed by morphological post-processing to remove pixel noise. We study the applicability of two alternate color spaces (HSV, CIE Lab) for computing the difference image. Similarly, we employ two spatial thresholding methods, which determine the global threshold from the local spatial properties of the difference image. We demonstrate the performance of the proposed approach in scene surveillance, where the objective is to monitor a shipping dock for the appearance of needless objects such as cardboard boxes. In order to analyze the robustness of the approach, the experiment includes three different types of scenes categorized as 'easy,' 'moderate,' and 'difficult,' based on properties such as heterogeneity of the background, existence of shadows and illumination changes, and reflectivity and chroma properties of the objects. The experimental results show that relatively good recognition accuracy is achieved on 'easy' and 'moderate' scenes, whereas 'difficult' scenes remain a challenge for future work.
URL: https://global.ieice.org/en_transactions/information/10.1587/e84-d_12_1676/_p
부
@ARTICLE{e84-d_12_1676,
author={Mika RAUTIAINEN, Timo OJALA, Hannu KAUNISKANGAS, },
journal={IEICE TRANSACTIONS on Information},
title={Detecting Perceptual Color Changes from Sequential Images for Scene Surveillance},
year={2001},
volume={E84-D},
number={12},
pages={1676-1683},
abstract={This paper proposes a methodology for detecting matte-surfaced objects on a scene using color information and spatial thresholding. First, a difference image is obtained via a pixel-wise comparison of the color content of a 'clean' reference image and a sample image. Then, spatial thresholding of the difference image is performed to extract any objects of interest, followed by morphological post-processing to remove pixel noise. We study the applicability of two alternate color spaces (HSV, CIE Lab) for computing the difference image. Similarly, we employ two spatial thresholding methods, which determine the global threshold from the local spatial properties of the difference image. We demonstrate the performance of the proposed approach in scene surveillance, where the objective is to monitor a shipping dock for the appearance of needless objects such as cardboard boxes. In order to analyze the robustness of the approach, the experiment includes three different types of scenes categorized as 'easy,' 'moderate,' and 'difficult,' based on properties such as heterogeneity of the background, existence of shadows and illumination changes, and reflectivity and chroma properties of the objects. The experimental results show that relatively good recognition accuracy is achieved on 'easy' and 'moderate' scenes, whereas 'difficult' scenes remain a challenge for future work.},
keywords={},
doi={},
ISSN={},
month={December},}
부
TY - JOUR
TI - Detecting Perceptual Color Changes from Sequential Images for Scene Surveillance
T2 - IEICE TRANSACTIONS on Information
SP - 1676
EP - 1683
AU - Mika RAUTIAINEN
AU - Timo OJALA
AU - Hannu KAUNISKANGAS
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E84-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2001
AB - This paper proposes a methodology for detecting matte-surfaced objects on a scene using color information and spatial thresholding. First, a difference image is obtained via a pixel-wise comparison of the color content of a 'clean' reference image and a sample image. Then, spatial thresholding of the difference image is performed to extract any objects of interest, followed by morphological post-processing to remove pixel noise. We study the applicability of two alternate color spaces (HSV, CIE Lab) for computing the difference image. Similarly, we employ two spatial thresholding methods, which determine the global threshold from the local spatial properties of the difference image. We demonstrate the performance of the proposed approach in scene surveillance, where the objective is to monitor a shipping dock for the appearance of needless objects such as cardboard boxes. In order to analyze the robustness of the approach, the experiment includes three different types of scenes categorized as 'easy,' 'moderate,' and 'difficult,' based on properties such as heterogeneity of the background, existence of shadows and illumination changes, and reflectivity and chroma properties of the objects. The experimental results show that relatively good recognition accuracy is achieved on 'easy' and 'moderate' scenes, whereas 'difficult' scenes remain a challenge for future work.
ER -