IEEE Transactions on Image Processing · 2010 · 72 citations · 38 references
ComputingComputer ScienceComputer VisionDigital ImagingRemote SensingDigital Image ProcessingImage AnalysisImage RegistrationImage SegmentationRemote Sensing Image AnalysisShape AnalysisAutomated Image RegistrationFractal DimensionFractal Dimension TheoryHistogram AnalysisImage MatchingRemote Sensing AnalysisRemote Sensing Segmentation
Automatic image registration remains a challenge across fields, including remote sensing, despite recent advances. This paper proposes HAIRIS, a histogram‑based image segmentation method for automatic registration. HAIRIS combines multiple segmentations guided by a relaxation parameter on histogram modes, characterizes objects via area, ellipse ratio, perimeter, fractal dimension, and matches them with a robust statistical procedure, demonstrated on simulated and real remote‑sensing data. HAIRIS achieves sub‑pixel translation accuracy and rotation error below 1°, enabling registration of multitemporal, multisensor images with small spectral differences.
Automatic image registration is still an actual challenge in several fields. Although several methods for automatic image registration have been proposed in the last few years, it is still far from a broad use in several applications, such as in remote sensing. In this paper, a method for automatic image registration through histogram-based image segmentation (HAIRIS) is proposed. This new approach mainly consists in combining several segmentations of the pair of images to be registered, according to a relaxation parameter on the histogram modes delineation (which itself is a new approach), followed by a consistent characterization of the extracted objects--through the objects area, ratio between the axis of the adjust ellipse, perimeter and fractal dimension--and a robust statistical based procedure for objects matching. The application of the proposed methodology is illustrated to simulated rotation and translation. The first dataset consists in a photograph and a rotated and shifted version of the same photograph, with different levels of added noise. It was also applied to a pair of satellite images with different spectral content and simulated translation, and to real remote sensing examples comprising different viewing angles, different acquisition dates and different sensors. An accuracy below 1° for rotation and at the subpixel level for translation were obtained, for the most part of the considered situations. HAIRIS allows for the registration of pairs of images (multitemporal and multisensor) with differences in rotation and translation, with small differences in the spectral content, leading to a subpixel accuracy.
38
Image registration methods: a survey
Jan Flusser · Image and Vision Computing · 2003 · 6.4K citations