Journal of Geomatics Science and Technology

fa تناظریابی پایدار بر مبنای عوارض Hessian-Affine و توصیفگر MROGH Reliable Image Matching Based On Hessian-Affine Detector and MROGH Descriptor فتوگرامتری و سنجش از دور Photo&RS پژوهشي Research <div style="text-align: justify;">تناظریابی یکی از فرآیندهای اساسی و مهم در فتوگرامتری است. در این مقاله یک روش دقیق و پایدار برای تناظریابی اتوماتیک تصاویری که دارای اختلافات هندسی زیاد ناشی از تغییر نقطه‌ی دید تصویربرداری هستند، ارائه شده‌است. روش پیشنهادی از سه مرحله‌ اصلی تشکیل شده‌است. در مرحله اول یک مجموعه از عوارض پایدار تصویر با بهره‌گیری از الگوریتم Hessian-Affine و با استفاده از دو قید توزیع مکانی و مقیاس استخراج می‌شوند. در مرحله دوم برای هر عارضه‌ی مستخرج، یک توصیفگر بسیار متمایز با استفاده از الگوریتم MROGH (Multisupport Region Order-Based Gradient Histogram) بر مبنای رتبه‌بندی درجات خاکستری و ادغام هیستوگرام‌های تو در تو ایجاد می‌شود. در نهایت در مرحله سوم فرآیند مطابقت میان عوارض با استفاده از روش نزدیکترین نسبت همسایگی دو جانبه انجام شده و تناظرهای اشتباه احتمالی با کنترل سازگاری نقاط با استفاده از قید هندسی اپی‌پولار و در یک روند تکراری شناسایی و حذف می‌شوند. روش پیشنهادی بر روی 6 جفت تصویر برد کوتاه با اختلافات هندسی زیاد پیاده‌سازی شده و نتایج با سه الگوریتم MSER-SIFT، UR-SIFT و A-SIFT مقایسه‌ شده است. نتایج آزمایشات برای سه معیار تعداد تناظرهای درست، Recall و دقت مکانی، بیانگر قابلیت بالای روش پیشنهادی برای تناظریابی دقیق و پایدار در تصاویر با اختلافات هندسی زیاد است. به طور متوسط میزان معیارهای تعداد تناظرهای درست، Recall و دقت مکانی برای روش پیشنهادی به ترتیب برابر 456 عدد، 37% و 0.6 پیکسل است.</div> Reliable image matching is a vital step in many photogrammetric processes. Most image matching methods are based on the local feature algorithms because of their robustness to significant geometric and radiometric differences. A local feature is generally deﬁned as a distinct structure with properties differing from its immediate neighbourhood. Generally, local-feature-based image matching methods consist of three main steps, including feature detection, feature description and feature correspondence. In the feature detection step, distinctive structures are extracted from images. In the feature description step, extracted features are represented with descriptors to characterize them. Finally in the correspondence step, the extracted features from two images are matched using particular similarity measures. <div style="text-align: justify;">n this paper, an automatic image matching approach based on the affine invariant features is proposed for wide-baseline images with significant viewpoint differences. The proposed approach consists of three main steps. In the ﬁrst step, well-known Hessian-affine feature detector is used to extract local affine invariant features in the image pair. In Hessian-affine detector a multi-scale representation and an iterative afﬁne shape adaption are used to deal with signiﬁcant viewpoint differences including large scale changes. To improve the Hessian-afﬁne detector capability, an advanced strategy based on the well-known UR-SIFT (uniform robust scale invariant feature transform) algorithm is applied to extract effective, robust, reliable, and uniformly distributed elliptical local features. For this purpose, a selection strategy based on the stability and distinctiveness constraints is used in the full distribution of the location and the scale. In the second step, a distinctive descriptor based on MROGH (Multisupport Region Order-Based Gradient Histogram) method, which is robust to significant geometrical distortions, is generated for each extracted feature. The main idea of the MROGH method is to pool rotation invariant local features based on intensity orders. Instead of assigning a main orientation to each feature, a locally rotation invariant schema is used. For this purpose a rotation invariant coordinate system is used to compute the pixels gradient. To compute descriptor, the pixels in the feature region are partitioned into several groups based on their intensity orders. Then, a speciﬁc histogram based on the pixels gradient magnitude and orientation is calculated for each group. Finally, the MROGH descriptor is generated by combining the values of all the gradient histogram from all groups into a single feature vector. Finally, feature correspondence and blunder detection process is performed using epipolar geometry based on fundamental matrix. The initial matched features that are not consistent with the estimated fundamental matrix are identified as false matches and eliminated. A distance threshold TE = 1 pixel between each feature point and its epipolar line is considered as elimination condition. The experimental results using six close-range images show that the proposed method improves the matching performance compared with several state-of-the-art methods, including the MSER-SIFT, UR-SIFT and A-SIFT, in terms of the number of correct matched features, recall and positional accuracy. Based on the matching results, the proposed integrated method can be easily applied to a variety of photogrammetric and computer vision applications such as relative orientation, bundle adjustment, structure from motion and simultaneous localization and mapping (SLAM).  </div> تناظریابی, عوارض Hessian-Affine, توصیفگر MROGH, ماتریس کواریانس, تصاویر برد کوتاه Image Matching, Hessian Affine, MROGH, Covariance Matrix, Close Range Images 1 15 http://jgst.issgeac.ir/browse.php?a_code=A-10-515-1&slc_lang=fa&sid=1 A. Sedaghat امین صداقت am.sedaghat@gmail.com 10031947532846005331 10031947532846005331 Yes دانشگاه تبریز N. Mohammadi نازیلا محمدی nazila.mohamadi@gmail.com 10031947532846005332 10031947532846005332 No دانشگاه تبریز