The Experts below are selected from a list of 1119 Experts worldwide ranked by ideXlab platform
Shijie Sun - One of the best experts on this subject based on the ideXlab platform.
-
multimodal image matching based on multimodality robust line Segment Descriptor
Neurocomputing, 2016Co-Authors: Chunyang Zhao, Huaici Zhao, Shijie SunAbstract:Although a number of local feature-based methods have been proposed, the multimodality matching is still a challenging problem in object recognition, remote sensing and medical image processing where the image contrast is significantly different. The local feature-based multimodality matching method is usually intensity-based, so the matching performance is not good enough because intensity-based method is sensitive to contrast variations. In order to solve these problems, we propose a novel Multimodality Robust Line Segment Descriptor (MRLSD) and develop a MRLSD matching method. The proposed method generates MRLSD Descriptors based on extracted highly equivalent corners and line Segments for two multimodal images, and then performs image matching by measuring the similarity of corresponding Descriptors over two images. The proposed corner and line Segment extraction method is based on local phase and direction information, and is insensitive to contrast variations, so the MRLSD Descriptor is robust to modality variations. The MRLSD Descriptor is rotation invariant by selecting circular feature sub-regions and projecting feature vectors to radial direction. The MRLSD Descriptor achieves scale invariance by adjusting the radius of circular feature region according to the scale. Experimental results indicate that the proposed method achieves higher precision and repeatability than several state-of-the-art local feature-based multimodality matching methods, and also demonstrate its robustness to multimodal images.
Chunyang Zhao - One of the best experts on this subject based on the ideXlab platform.
-
multimodal image matching based on multimodality robust line Segment Descriptor
Neurocomputing, 2016Co-Authors: Chunyang Zhao, Huaici Zhao, Shijie SunAbstract:Although a number of local feature-based methods have been proposed, the multimodality matching is still a challenging problem in object recognition, remote sensing and medical image processing where the image contrast is significantly different. The local feature-based multimodality matching method is usually intensity-based, so the matching performance is not good enough because intensity-based method is sensitive to contrast variations. In order to solve these problems, we propose a novel Multimodality Robust Line Segment Descriptor (MRLSD) and develop a MRLSD matching method. The proposed method generates MRLSD Descriptors based on extracted highly equivalent corners and line Segments for two multimodal images, and then performs image matching by measuring the similarity of corresponding Descriptors over two images. The proposed corner and line Segment extraction method is based on local phase and direction information, and is insensitive to contrast variations, so the MRLSD Descriptor is robust to modality variations. The MRLSD Descriptor is rotation invariant by selecting circular feature sub-regions and projecting feature vectors to radial direction. The MRLSD Descriptor achieves scale invariance by adjusting the radius of circular feature region according to the scale. Experimental results indicate that the proposed method achieves higher precision and repeatability than several state-of-the-art local feature-based multimodality matching methods, and also demonstrate its robustness to multimodal images.
Cesar Junior, Roberto Marcondes - One of the best experts on this subject based on the ideXlab platform.
-
Reconstrução tridimensional por ajuste de superficies parametricas
[s.n.], 2018Co-Authors: Cesar Junior, Roberto MarcondesAbstract:Orientador : Roberto de Alencar LotufoDissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia EletricaResumo: Este trabalho apresenta os principais aspectos sobre uma abordagem de reconstrução tridimensional (3D) de objetos por ajuste de superfícies paramétricas. A reconstrução 3D se insere como um tópico da visualização volumétrica. o processo de reconstrução 3D por pode ser dividido em 3 etapas gerais: Segmentação de contornos; casamento de Segmentos entre contornos; e interpolação ou aproximação da superfície paramétrica. Cada uma dessas etapas é apresentada e discutida. São apresentados os detalhes do desenvolvimento e implementação de um método de reconstrução 3D por superfícies de Coons. A etapa de Segmentação e representação de contornos é feita com auxíliode curvas B-Spline. Para a descrição dos Segmentos, foi criado um descritor que é calculado a partir do polígono de controle de cada Segmento. O casamento de Segmentos é feito por um método baseado no algoritmo de busca em grafos conhecido como A*. O ajuste de superfícies é feito por "patches" de Coons. Esta dissertação contribui em 3 aspectos principais: melhoria do método de Segmentação de contornos proposto por Medioni, criação de um descritor para Segmentos de B-Spline e desenvolvimento de um método de casamento de Segmentos que se baseia no algoritmo A* de busca em grafos. São apresentados os resultados utilizando imagens sintéticas e experimentais, obtidas por digitalização por "scanner" e por um processo de tomografia Computadorizada de raio-xAbstract: An approach to three-dimensional (3D) reconstruction of objects by parametric surfaces, a topic from volume visualization, is described. The parametric surface 3D reconstruction can be divided in three steps : contour Segmentation; Segment matching; and parametric surface formation. These steps are presented and discussed. A method for 3D reconstruction by Coons surfaces is developed and presented. B-Splines are used for contour Segmentation and representation. The guiding-polygon is used for contour description. Segment matching is achieved by an algorithm based on the A* graph search method. Surface formation is performed by Coons's blending. This thesis contributes in 3 main aspects: improvement of the contours Segmentation method proposed by Medioni, definition of a B-Spline Segment Descriptor, and developement of a Segment matching method, based on the A* graph search method. Some results from both synthetic and experimental images are presented.MestradoAutomaçãoMestre em Engenharia Elétric
Roberto Marcondes Cesar - One of the best experts on this subject based on the ideXlab platform.
-
Reconstrução tridimensional por ajuste de superficies parametricas
2017Co-Authors: Roberto Marcondes CesarAbstract:Resumo: Este trabalho apresenta os principais aspectos sobre uma abordagem de reconstrução tridimensional (3D) de objetos por ajuste de superfícies paramétricas. A reconstrução 3D se insere como um tópico da visualização volumétrica.o processo de reconstrução 3D por pode ser dividido em 3 etapas gerais: Segmentação de contornos; casamento de Segmentos entre contornos; e interpolação ou aproximação da superfície paramétrica. Cada uma dessas etapas é apresentada e discutida. São apresentados os detalhes do desenvolvimento e implementação de um método de reconstrução 3D por superfícies de Coons. A etapa de Segmentação e representação de contornos é feita com auxíliode curvas B-Spline. Para a descrição dos Segmentos, foi criado um descritor que é calculado a partir do polígono de controle de cada Segmento. O casamento de Segmentos é feito por um método baseado no algoritmo de busca em grafos conhecido como A*. O ajuste de superfícies é feito por "patches" de Coons. Esta dissertação contribui em 3 aspectos principais: melhoria do método de Segmentação de contornos proposto por Medioni, criação de um descritor para Segmentos de B-Spline e desenvolvimento de um método de casamento de Segmentos que se baseia no algoritmo A* de busca em grafos. São apresentados os resultados utilizando imagens sintéticas e experimentais, obtidas por digitalização por "scanner" e por um processo de tomografia Computadorizada de raio-xAbstract: An approach to three-dimensional (3D) reconstruction of objects by parametric surfaces, a topic from volume visualization, is described. The parametric surface 3D reconstruction can be divided in three steps : contour Segmentation; Segment matching; and parametric surface formation. These steps are presented and discussed. A method for 3D reconstruction by Coons surfaces is developed and presented. B-Splines are used for contour Segmentation and representation. The guiding-polygon is used for contour description. Segment matching is achieved by an algorithmbased on the A* graph search method. Surface formation is performed by Coons's blending. This thesis contributes in 3 main aspects: improvement of the contours Segmentation method proposed by Medioni, definition of a B-Spline Segment Descriptor, and developement of a Segment matching method, based on the A* graph search method. Some results from both synthetic and experimental images are presente
Victor Lempitsky - One of the best experts on this subject based on the ideXlab platform.
-
learnable line Segment Descriptor for visual slam
IEEE Access, 2019Co-Authors: Alexander Vakhitov, Victor LempitskyAbstract:Traditionally, the indirect visual motion estimation and simultaneous localization and mapping (SLAM) systems were based on point features. In recent years, several SLAM systems that use lines as primitives were suggested. Despite the extra robustness and accuracy brought by the line Segment matching, the line Segment Descriptors used in such systems were hand-crafted, and therefore sub-optimal. In this paper, we suggest applying Descriptor learning to construct line Segment Descriptors optimized for matching tasks. We show how such Descriptors can be constructed on top of a deep yet lightweight fully-convolutional neural network. The coefficients of this network are trained using an automatically collected dataset of matching and non-matching line Segments. The use of the fully-convolutional network ensures that the bulk of the computations needed to compute Descriptors is shared among the multiple line Segments in the same image, enabling efficient implementation. We show that the learned line Segment Descriptors outperform the previously suggested hand-crafted line Segment Descriptors both in isolation (i.e., for the subtask of distinguishing matching and non-matching line Segments), but also when built into the SLAM system. We construct a new line based SLAM pipeline built upon a state-of-the-art point-only system. We demonstrate generalization of the learned parameters of the Descriptor network between two well-known datasets for autonomous driving and indoor micro aerial vehicle navigation.