Article
Computer Science, Artificial Intelligence
Qinyan Dai, Faming Fang, Juncheng Li, Guixu Zhang, Aimin Zhou
Summary: This paper introduces a new end-to-end deep learning framework named EGCNet for the composition stage in image stitching, which utilizes perceptual edges to guide the network in generating seamless stitched images. Extensive experiments show that EGCNet produces excellent results in handling parallax and object motions, outperforming traditional methods.
PATTERN RECOGNITION
(2021)
Article
Geochemistry & Geophysics
Qiang Xiong, Shenghui Fang, Xiaojuan Liu, Xueqin Jiang, Yongfei Lv
Summary: This letter proposes a novel descriptor for multispectral image matching, which combines phase consistency gradient and log-polar coordinates to eliminate nonlinear radiation differences and extract more robust features. Experimental results demonstrate that this method outperforms traditional feature matching methods.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Chemistry, Multidisciplinary
Ting Wang, Huiqin Wang, Ke Wang, Zhe Yang
Summary: This paper proposes a stitching method based on image edge position feature matching to improve the accuracy of image stitching by matching feature points based on the position of the image edge pixel, solving the accurate stitching of broken edge contour.
APPLIED SCIENCES-BASEL
(2023)
Article
Physics, Multidisciplinary
Mengying Yan, Danyang Qin, Gengxin Zhang, Huapeng Tang, Lin Ma
Summary: Image stitching technology is of great practical importance in the fields of security monitoring and intelligent driving at night. Due to uneven brightness distribution and dark areas in night images, there is a problem of insufficient line feature extraction in image stitching. Therefore, a nighttime image stitching method based on image decomposition enhancement is proposed, which enhances luminance in the structural layer, smooths image noise in the texture layer using a denoising algorithm, and complements texture using an edge enhancement algorithm. The proposed method improves image quality and increases the extraction of line features.
Article
Environmental Sciences
Liyao Song, Haiwei Li, Tieqiao Chen, Junyu Chen, Song Liu, Jiancun Fan, Quan Wang
Summary: The study proposed an integrated solution for acquiring and correcting UAV-borne hyperspectral images, including radiation and geometric correction, image registration, and multi-strip stitching. By introducing an improved method, the accuracy of radiation correction was enhanced, and the error of large-scale image stitching was controlled.
Article
Environmental Sciences
Agnieszka Jenerowicz, Damian Wierzbicki, Michal Kedzierski
Summary: This article provides a brief overview of existing techniques for radiometric correction of multispectral images. Radiometric correction is crucial in various applications, particularly in precision farming, forestry, and climate analysis. The paper introduces a new relative approach for obtaining baseline data by considering the terrain's inclination angle and the angle of incidence of electromagnetic radiation. The developed method enables accurate mapping and classification of terrestrial coverage based on spectral reflection characteristics, with an accuracy of over 95%.
Article
Optics
Joydeep Chatterjee, Semanti Chakraborty, Kanik Palodhi
Summary: This paper presents a method for selective edge enhancement using Walsh filters, which can be applied to different types of images and rotated for enhancing edges in various radial directions, making it superior in providing both selective and overall edge enhancements.
Article
Geochemistry & Geophysics
Yuxuan Zheng, Jiaojiao Li, Yunsong Li, Jie Guo, Xianyun Wu, Yanzi Shi, Jocelyn Chanussot
Summary: This study proposes a novel edge-conditioned feature transform network, composed of three parts, to successfully address the challenges encountered in reconstructing high-spatial-resolution HSI, achieving more accurate spatial details and less spectral distortions.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Optics
Jiaxun Zhang, Jianxin Li
Summary: This study proposes a spectral shift correction method using high-chroma color patches for calibration, significantly reducing color differences. Additionally, a method is developed for adaptively selecting wavebands based on pre-estimated spectral reflectance to effectively reduce color differences.
OPTICS AND LASERS IN ENGINEERING
(2021)
Article
Geochemistry & Geophysics
Quan Wu, Shipeng Zhu
Summary: This letter introduces a robust and efficient image-matching method for addressing the issue of nonlinear intensity changes in multispectral image matching. By identifying control-point candidates, proposing the novel feature descriptor HGEO, and conducting bilateral matching process, the method has been successfully applied to various multispectral remote sensing images with superior performance compared to many currently used methods.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Medha Gupta, Vishwas Rathi, Puneet Goyal
Summary: This paper proposes an adaptive and progressive MSFA demosaicking method for multispectral images, which improves image quality and computational efficiency through the design of MSFA patterns and interpolation of the middle band.
IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING
(2022)
Article
Computer Science, Artificial Intelligence
Wei Tang, Fangxiu Jia, Xiaoming Wang
Summary: In many computer vision applications, such as motion detection, virtual reality, panoramic photography, and virtual tours, it is important to stitch two images together into a panorama. This article proposes an improved mesh-based image stitching model that preserves local details and reduces artifacts. By using matched feature points and uniform points as grid vertices, constraints on deformed vertices are strengthened. An improved energy function and color similarity term are used for alignment. The proposed method achieves more accurate image stitching with reduced ghosting effects and more natural results in non-overlapping areas.
FRONTIERS IN NEUROROBOTICS
(2023)
Article
Geochemistry & Geophysics
Zhenqiang Qin, Xian Li, Yanfeng Gu
Summary: In this article, a physics-based method is proposed to estimate and compensate illumination for the radiometric correction of UAV multispectral images (MSIs). The proposed method builds an illumination estimation model based on intraimage and interimage consistency hypotheses, and utilizes the physical imaging principle to alleviate the influence of varying illumination. Numerical experiments on three UAV datasets demonstrate that the proposed method outperforms current methods and significantly reduces the normalized root mean square error (NRMSE).
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Jiamin Du, Xiubin Yang, Meili Zhou, Ziming Tu, Shaoen Wang, Xingyu Tang, Lijie Cao, Xindong Zhao
Summary: This article establishes a rigorous velocity vector field model to achieve fast alignment and fusion of color images captured by an agile satellite, and to correct distortion.
IEEE SENSORS JOURNAL
(2022)
Article
Chemistry, Analytical
Cuizhen Wang
Summary: The rapid advancement of drone technology has enabled quantitative applications in agriculture, such as assessing crop healthiness using drones mounted with MicaSense RedEdge cameras. A proposed radiometric correction model effectively reduces local impacts to the extracted surface reflectance, improving accuracy. Additionally, the red edge NDVI proposed in this study shows promise for assessing vegetation healthiness with a wider range of values.