The Experts below are selected from a list of 4155 Experts worldwide ranked by ideXlab platform

Michael S Brown - One of the best experts on this subject based on the ideXlab platform.

  • Eurographics (Short Papers) - Seam-Driven Image Stitching
    2020
    Co-Authors: Yu Li, Tatjun Chin, Michael S Brown
    Abstract:

    Image Stitching computes geometric transforms to align Images based on the best fit of feature correspondences between overlapping Images. Seam-cutting is used afterwards to to hide misalignment artifacts. Interestingly it is often the seam-cutting step that is the most crucial for obtaining a perceptually seamless result. This motivates us to propose a seam-driven Image Stitching strategy where instead of estimating a geometric transform based on the best fit of feature correspondences, we evaluate the goodness of a transform based on the resulting visual quality of the seam-cut. We show that this new Image Stitching strategy can often produce better perceptual results than existing methods especially for challenging scenes.

  • As-Projective-As-Possible Image Stitching with Moving DLT
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
    Co-Authors: Julio Zaragoza, Tatjun Chin, Michael S Brown, Quoc-huy Tran, David Suter
    Abstract:

    The success of commercial Image Stitching tools often leads to the impression that Image Stitching is a “solved problem”. The reality, however, is that many tools give unconvincing results when the input photos violate fairly restrictive imaging assumptions; the main two being that the photos correspond to views that differ purely by rotation, or that the Imaged scene is effectively planar. Such assumptions underpin the usage of 2D projective transforms or homographies to align photos. In the hands of the casual user, such conditions are often violated, yielding misalignment artifacts or “ghosting” in the results. Accordingly, many existing Image Stitching tools depend critically on post-processing routines to conceal ghosting. In this paper, we propose a novel estimation technique called Moving Direct Linear Transformation (Moving DLT) that is able to tweak or fine-tune the projective warp to accommodate the deviations of the input data from the idealized conditions. This produces as-projective-as-possible Image alignment that significantly reduces ghosting without compromising the geometric realism of perspective Image Stitching. Our technique thus lessens the dependency on potentially expensive postprocessing algorithms. In addition, we describe how multiple as-projective-as-possible warps can be simultaneously refined via bundle adjustment to accurately align multiple Images for large panorama creation.

  • seam driven Image Stitching
    Eurographics, 2013
    Co-Authors: Yu Li, Tatjun Chin, Michael S Brown
    Abstract:

    Image Stitching computes geometric transforms to align Images based on the best fit of feature correspondences between overlapping Images. Seam-cutting is used afterwards to to hide misalignment artifacts. Interestingly it is often the seam-cutting step that is the most crucial for obtaining a perceptually seamless result. This motivates us to propose a seam-driven Image Stitching strategy where instead of estimating a geometric transform based on the best fit of feature correspondences, we evaluate the goodness of a transform based on the resulting visual quality of the seam-cut. We show that this new Image Stitching strategy can often produce better perceptual results than existing methods especially for challenging scenes.

Jun Chen - One of the best experts on this subject based on the ideXlab platform.

  • UAV Remote Sensing Image Stitching
    Advances in Natural Computation Fuzzy Systems and Knowledge Discovery, 2020
    Co-Authors: Hui Wu, Jun Chen
    Abstract:

    The majority of Image Stitching (include UAV remote sensing Images Stitching) models are homography matrix transformation function, which could effectively simulate the rigid transformation of 2D Images in 3D coordinate system. In order to prevent the accumulation of alignment errors (drift) and the projection distortion in the multi-Image Stitching task, we proposes a novel UAV remote sensing Image Stitching access consisting of homography transformation and Helmert transformation. In the overlapping and non-overlapping region we utility homography transformation and Helmert transformation respectively. With proposed method the UAV remote sensing Image Stitching result has fewer alignment errors and less projection distortion.

  • ICNC-FSKD - UAV Remote Sensing Image Stitching
    Advances in Natural Computation Fuzzy Systems and Knowledge Discovery, 2019
    Co-Authors: Hui Wu, Jun Chen
    Abstract:

    The majority of Image Stitching (include UAV remote sensing Images Stitching) models are homography matrix transformation function, which could effectively simulate the rigid transformation of 2D Images in 3D coordinate system. In order to prevent the accumulation of alignment errors (drift) and the projection distortion in the multi-Image Stitching task, we proposes a novel UAV remote sensing Image Stitching access consisting of homography transformation and Helmert transformation. In the overlapping and non-overlapping region we utility homography transformation and Helmert transformation respectively. With proposed method the UAV remote sensing Image Stitching result has fewer alignment errors and less projection distortion.

Guixu Zhang - One of the best experts on this subject based on the ideXlab platform.

  • Superpixel-Based Seamless Image Stitching for UAV Images
    IEEE Transactions on Geoscience and Remote Sensing, 1
    Co-Authors: Yiting Yuan, Faming Fang, Guixu Zhang
    Abstract:

    Image Stitching aims to generate a natural seamless high-resolution panoramic Image free of distortions or artifacts as fast as possible. In this article, we propose a new seam cutting strategy based on superpixels for unmanned aerial vehicle (UAV) Image Stitching. Explicitly, we decompose the issue into three steps: Image registration, seam cutting, and Image blending. First, we employ adaptive as-natural-as-possible (AANAP) warps for registration, obtaining two aligned Images in the same coordinate system. Then, we propose a novel superpixel-based energy function that integrates color difference, gradient difference, and texture complexity information to search a perceptually optimal seam located in continuous areas with high similarity. We apply the graph cut algorithm to solve the problem and thereby conceal artifacts in the overlapping area. Finally, we utilize a superpixel-based color blending approach to eliminate visible seams and achieve natural color transitions. Experimental results demonstrate that our method can effectively and efficiently realize seamless Stitching, and is superior to several state-of-the-art methods in UAV Image Stitching.

Tatjun Chin - One of the best experts on this subject based on the ideXlab platform.

  • Eurographics (Short Papers) - Seam-Driven Image Stitching
    2020
    Co-Authors: Yu Li, Tatjun Chin, Michael S Brown
    Abstract:

    Image Stitching computes geometric transforms to align Images based on the best fit of feature correspondences between overlapping Images. Seam-cutting is used afterwards to to hide misalignment artifacts. Interestingly it is often the seam-cutting step that is the most crucial for obtaining a perceptually seamless result. This motivates us to propose a seam-driven Image Stitching strategy where instead of estimating a geometric transform based on the best fit of feature correspondences, we evaluate the goodness of a transform based on the resulting visual quality of the seam-cut. We show that this new Image Stitching strategy can often produce better perceptual results than existing methods especially for challenging scenes.

  • As-Projective-As-Possible Image Stitching with Moving DLT
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
    Co-Authors: Julio Zaragoza, Tatjun Chin, Michael S Brown, Quoc-huy Tran, David Suter
    Abstract:

    The success of commercial Image Stitching tools often leads to the impression that Image Stitching is a “solved problem”. The reality, however, is that many tools give unconvincing results when the input photos violate fairly restrictive imaging assumptions; the main two being that the photos correspond to views that differ purely by rotation, or that the Imaged scene is effectively planar. Such assumptions underpin the usage of 2D projective transforms or homographies to align photos. In the hands of the casual user, such conditions are often violated, yielding misalignment artifacts or “ghosting” in the results. Accordingly, many existing Image Stitching tools depend critically on post-processing routines to conceal ghosting. In this paper, we propose a novel estimation technique called Moving Direct Linear Transformation (Moving DLT) that is able to tweak or fine-tune the projective warp to accommodate the deviations of the input data from the idealized conditions. This produces as-projective-as-possible Image alignment that significantly reduces ghosting without compromising the geometric realism of perspective Image Stitching. Our technique thus lessens the dependency on potentially expensive postprocessing algorithms. In addition, we describe how multiple as-projective-as-possible warps can be simultaneously refined via bundle adjustment to accurately align multiple Images for large panorama creation.

  • seam driven Image Stitching
    Eurographics, 2013
    Co-Authors: Yu Li, Tatjun Chin, Michael S Brown
    Abstract:

    Image Stitching computes geometric transforms to align Images based on the best fit of feature correspondences between overlapping Images. Seam-cutting is used afterwards to to hide misalignment artifacts. Interestingly it is often the seam-cutting step that is the most crucial for obtaining a perceptually seamless result. This motivates us to propose a seam-driven Image Stitching strategy where instead of estimating a geometric transform based on the best fit of feature correspondences, we evaluate the goodness of a transform based on the resulting visual quality of the seam-cut. We show that this new Image Stitching strategy can often produce better perceptual results than existing methods especially for challenging scenes.

Changlong Miao - One of the best experts on this subject based on the ideXlab platform.

  • RCAR - Real-Time Image Stitching with Convolutional Neural Networks
    2019 IEEE International Conference on Real-time Computing and Robotics (RCAR), 2019
    Co-Authors: Canwei Shen, Xiangyang Ji, Changlong Miao
    Abstract:

    Traditional Image Stitching methods are designed manually and time-consuming, while Convolutional Neural Networks based methods can solve the problem end to end automatically and stitch Images in real time after training. However, there is still no suitable dataset for Image Stitching. Now, we propose a novel approach to capture the Images to be stitched and the corresponding ground truth, and make a dataset generated by the proposed method. We also propose a network to verify our dataset experimentally and propose the quantitative metric based on our dataset. It will make progresses for real time Image Stitching.

  • Real-Time Image Stitching with Convolutional Neural Networks
    2019 IEEE International Conference on Real-time Computing and Robotics (RCAR), 2019
    Co-Authors: Canwei Shen, Xiangyang Ji, Changlong Miao
    Abstract:

    Traditional Image Stitching methods are designed manually and time-consuming, while Convolutional Neural Networks based methods can solve the problem end to end automatically and stitch Images in real time after training. However, there is still no suitable dataset for Image Stitching. Now, we propose a novel approach to capture the Images to be stitched and the corresponding ground truth, and make a dataset generated by the proposed method. We also propose a network to verify our dataset experimentally and propose the quantitative metric based on our dataset. It will make progresses for real time Image Stitching.