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
이미지 매칭은 인공지능, 머신비전, 시각적 내비게이션 분야의 중요한 연구 분야입니다. 본 논문에서는 시각적 탐색에 적합한 새로운 이미지 매칭 기법을 제시합니다. 이 방식에서는 그레이 스케일 이미지를 분할하고 양자화하여 부분대역 이진 이미지를 형성합니다. 그런 다음 이진 이미지의 정보는 서명되어 벡터 공간을 형성하고 서명은 중요도에 따라 정렬됩니다. 이렇게 정렬된 시그니처는 정규화되어 표현된 이미지 그림 특징을 회전 및 크기 불변 형식으로 변환합니다. 두 이미지의 두 벡터 공간이 일치하는 이미지의 경우 변환된 도메인에서 비교됩니다. 이 비교는 이미지 역변환의 필요성을 피하면서 이미지 공간 영역에서 직접적으로 효율적인 결과를 산출합니다. 기존 상관 관계와 비교하여 이 비교는 이미지 전체에 걸쳐 광범위한 제곱 오류 계산을 방지합니다. 실제로 항공 영상 시퀀스의 고속 성능에 대한 적응적 예측이 제공한 추정값으로 수렴하도록 솔루션을 직접 안내합니다. 30차원 솔루션 모집단 계획도 일치하는 신뢰도 요소와 함께 제시되었습니다. 이 요소는 필수 일치 조건이 달성되었을 때 반복을 종료하는 데 도움이 됩니다. 제안된 방식은 일반, 크기 조정 및 회전된 템플릿에 대해 강력하고 빠른 결과를 제공합니다. 이전 기술과의 속도 비교는 이 새로운 기술의 계산 실행 가능성과 이미지 크기에 대한 의존도가 훨씬 낮다는 것을 보여줍니다. 이 방법은 또한 XNUMXdB AWGN 및 충격성 잡음에서 잡음 내성을 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
Muhammad Anwaar MANZAR, Tanweer Ahmad CHEEMA, Abdul JALIL, Ijaz Mansoor QURESHI, "Visual Aerial Navigation through Adaptive Prediction and Hyper-Space Image Matching" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 2, pp. 283-297, February 2009, doi: 10.1587/transinf.E92.D.283.
Abstract: Image matching is an important area of research in the field of artificial intelligence, machine vision and visual navigation. This paper presents a new image matching scheme suitable for visual navigation. In this scheme, gray scale images are sliced and quantized to form sub-band binary images. The information in the binary images is then signaturized to form a vector space and the signatures are sorted as per significance. These sorted signatures are then normalized to transform the represented image pictorial features in a rotation and scale invariant form. For the image matching these two vector spaces from both the images are compared in the transformed domain. This comparison yields efficient results directly in the image spatial domain avoiding the need of image inverse transformation. As compared to the conventional correlation, this comparison avoids the wide range of square error calculations all over the image. In fact, it directly guides the solution to converge towards the estimate given by the adaptive prediction for a high speed performance in an aerial video sequence. A four dimensional solution population scheme has also been presented with a matching confidence factor. This factor helps in terminating the iterations when the essential matching conditions have been achieved. The proposed scheme gives robust and fast results for normal, scaled and rotated templates. Speed comparison with older techniques shows the computational viability of this new technique and its much lesser dependence on image size. The method also shows noise immunity at 30 dB AWGN and impulsive noise.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.283/_p
부
@ARTICLE{e92-d_2_283,
author={Muhammad Anwaar MANZAR, Tanweer Ahmad CHEEMA, Abdul JALIL, Ijaz Mansoor QURESHI, },
journal={IEICE TRANSACTIONS on Information},
title={Visual Aerial Navigation through Adaptive Prediction and Hyper-Space Image Matching},
year={2009},
volume={E92-D},
number={2},
pages={283-297},
abstract={Image matching is an important area of research in the field of artificial intelligence, machine vision and visual navigation. This paper presents a new image matching scheme suitable for visual navigation. In this scheme, gray scale images are sliced and quantized to form sub-band binary images. The information in the binary images is then signaturized to form a vector space and the signatures are sorted as per significance. These sorted signatures are then normalized to transform the represented image pictorial features in a rotation and scale invariant form. For the image matching these two vector spaces from both the images are compared in the transformed domain. This comparison yields efficient results directly in the image spatial domain avoiding the need of image inverse transformation. As compared to the conventional correlation, this comparison avoids the wide range of square error calculations all over the image. In fact, it directly guides the solution to converge towards the estimate given by the adaptive prediction for a high speed performance in an aerial video sequence. A four dimensional solution population scheme has also been presented with a matching confidence factor. This factor helps in terminating the iterations when the essential matching conditions have been achieved. The proposed scheme gives robust and fast results for normal, scaled and rotated templates. Speed comparison with older techniques shows the computational viability of this new technique and its much lesser dependence on image size. The method also shows noise immunity at 30 dB AWGN and impulsive noise.},
keywords={},
doi={10.1587/transinf.E92.D.283},
ISSN={1745-1361},
month={February},}
부
TY - JOUR
TI - Visual Aerial Navigation through Adaptive Prediction and Hyper-Space Image Matching
T2 - IEICE TRANSACTIONS on Information
SP - 283
EP - 297
AU - Muhammad Anwaar MANZAR
AU - Tanweer Ahmad CHEEMA
AU - Abdul JALIL
AU - Ijaz Mansoor QURESHI
PY - 2009
DO - 10.1587/transinf.E92.D.283
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2009
AB - Image matching is an important area of research in the field of artificial intelligence, machine vision and visual navigation. This paper presents a new image matching scheme suitable for visual navigation. In this scheme, gray scale images are sliced and quantized to form sub-band binary images. The information in the binary images is then signaturized to form a vector space and the signatures are sorted as per significance. These sorted signatures are then normalized to transform the represented image pictorial features in a rotation and scale invariant form. For the image matching these two vector spaces from both the images are compared in the transformed domain. This comparison yields efficient results directly in the image spatial domain avoiding the need of image inverse transformation. As compared to the conventional correlation, this comparison avoids the wide range of square error calculations all over the image. In fact, it directly guides the solution to converge towards the estimate given by the adaptive prediction for a high speed performance in an aerial video sequence. A four dimensional solution population scheme has also been presented with a matching confidence factor. This factor helps in terminating the iterations when the essential matching conditions have been achieved. The proposed scheme gives robust and fast results for normal, scaled and rotated templates. Speed comparison with older techniques shows the computational viability of this new technique and its much lesser dependence on image size. The method also shows noise immunity at 30 dB AWGN and impulsive noise.
ER -