Hamid Ebadi

Uniform Robust Scale-Invariant Feature Matching for Optical Remote Sensing Images

Extracting well-distributed, reliable, and precisely aligned point pairs for accurate image registration is a difficult task, particularly for multisource remote sensing images that have significant illumination, rotation, and scene differences. The scale-invariant feature transform (SIFT) approach, as a well-known feature-based image matching algorithm, has been successfully applied in a number of automatic registration of remote sensing images. Regardless of its distinctiveness and robustness, the SIFT algorithm suffers from some problems in the quality, quantity, and distribution of extracted features particularly in multisource remote sensing imageries. In this paper, an improved SIFT algorithm is introduced that is fully automated and applicable to various kinds of optical remote sensing images, even with those that are five times the difference in scale. The main key of the proposed approach is a selection strategy of SIFT features in the full distribution of location and scale where the feature qualities are quarantined based on the stability and distinctiveness constraints. Then, the extracted features are introduced to an initial cross-matching process followed by a consistency check in the projective transformation model. Comprehensive evaluation of efficiency, distribution quality, and positional accuracy of the extracted point pairs proves the capabilities of the proposed matching algorithm on a variety of optical remote sensing images.

Automatic urban building boundary extraction from high resolution aerial images using an innovative model of active contours

To present a new method for building boundary detection and extraction based on the active contour model, is the main objective of this research. Classical models of this type are associated with several shortcomings; they require extensive initialization, they are sensitive to noise, and adjustment issues often become problematic with complex images. In this research a new model of active contours has been proposed that is optimized for the automatic building extraction. This new active contour model, in comparison to the classical ones, can detect and extract the building boundaries more accurately, and is capable of avoiding detection of the boundaries of features in the neighborhood of buildings such as streets and trees. Finally, the detected building boundaries are generalized to obtain a regular shape for building boundaries. Tests with our proposed model demonstrate excellent accuracy in terms of building boundary extraction. However, due to the radiometric similarity between building roofs and the image background, our system fails to recognize a few buildings.

An improved snake model for automatic extraction of buildings from urban aerial images and LiDAR data

Automatic extraction of objects from images has been a topic of research for decades. The main aim of these researches is to implement a numerical algorithm in order to extract the planar objects such as buildings from high resolution images and altitudinal data. Active contours or snakes have been extensively utilized for handling image segmentation and classification problems. Parametric active contour (snake) is defined as an energy minimizing spline guided by external constraint forces and influenced by image forces that pull it toward features such as lines or edges. The snake deforms itself from its initial position into conformity with the nearest dominant feature by minimizing the snake energy. The snake energy consists of two main forces, namely: internal and external forces. The coefficients of internal and external energy in snake models have important effects on extraction accuracy. These coefficients together control the weights of the internal and external energy. The coefficients also control the snake’s tension, rigidity, and attraction, respectively. In traditional methods, these weight coefficients are adjusted according to the user’s emphasis. This paper proposes an algorithm for optimization of these parameters using genetic algorithm. Here, we attempt to present the effectiveness of Genetic Algorithms based on active contour, with fitness evaluation by snake model. Compared with traditional methods, this algorithm can converge to the true coefficients more quicker and more stable, especially in complex urban environments. Experimental results from used dataset have 96% of overall accuracy, 98.9% of overall accuracy and 89.6% of k-Factor.

Remote Sensing Image Matching Based on Adaptive Binning SIFT Descriptor

Image matching based on local invariant features is crucial for many photogrammetric and remote sensing applications such as image registration and image mosaicking. In this paper, a novel local feature descriptor named adaptive binning scale-invariant feature transform (AB-SIFT) for fully automatic remote sensing image matching that is robust to local geometric distortions is proposed. The main idea of the proposed method is an adaptive binning strategy to compute the local feature descriptor. The proposed descriptor is computed on a normalized region defined by an improved version of the prominent Hessian affine feature extraction algorithm called the uniform robust Hessian affine algorithm. Unlike common distribution-based descriptors, the proposed descriptor uses an adaptive histogram quantization strategy for both location and gradient orientations, which is robust and actually resistant to a local viewpoint distortion and extremely increases the discriminability and robustness of the final AB-SIFT descriptor. In addition to the SIFT descriptor, the proposed adaptive quantization strategy can be easily extended for other distribution-based descriptors. Experimental results on both synthetic and real image pairs show that the proposed AB-SIFT matching method is more robust and accurate than state-of-the-art methods, including the SIFT, DAISY, the gradient location and orientation histogram, the local intensity order pattern, and the binary robust invariant scale keypoint.

Rational function optimization using genetic algorithms

In the absence of either satellite ephemeris information or camera model, rational functions are introduced by many investigators as mathematical model for image to ground coordinate system transformation. The dependency of this method on many ground control points (GCPs), numerical complexity, particularly terms selection, can be regarded as the most known disadvantages of rational functions. This paper presents a mathematical solution to overcome these problems. Genetic algorithms are used as an intelligent method for optimum rational function terms selection. The results from an experimental test carried out over a test field in Iran are presented as utilizing an IKONOS Geo image. Different numbers of GCPs are fed through a variety of genetic algorithms (GAs) with different control parameter settings. Some initial constraints are introduced to make the process stable and fast. The residual errors at independent check points proved that sub-pixel accuracies can be achieved even when only seven and five GCPs are used. GAs could select rational function terms in such a way that numerical problems are avoided without the need to normalize image and ground coordinates.

Optimization of road detection from high-resolution satellite images using texture parameters in neural network classifiers

The aim of road detection is to discriminate between road and background pixels. This discrimination is considered to be the most important stage in automatic road network extraction from satellite imagery. In this paper, neural networks are applied to high-resolution IKONOS and QuickBird images for road detection. This paper has endeavored to optimize the functionality of neural networks using a variety of texture parameters. These parameters had different window sizes and gray level numbers, not only from the source but also from the preclassified image. It was discovered that using texture parameters from a preclassified image accompanied by primary spectral information in reclassifying the source image could improve both road and background detection ability of the neural network. Accuracy assessment parameters were evaluated on several pan-sharpened IKONOS and QuickBird images. The obtained results attest to the efficiency of the proposed method.

Accurate Affine Invariant Image Matching Using Oriented Least Square

Abstract Image matching is a vital process for many photogrammetric and remote sensing applications such as image registration and aerial triangulation. In this paper, an accurate affine invariant image matching approach is presented. The proposed approach consists of three main steps. In the first step, two affine invariant feature detectors, including MSER and Harris-Affine features are applied for feature extraction. In the second step, initial corresponding features are selected using Euclidean distance between feature descriptors, followed by a consistency check process. Finally to overcome low positional accuracy of the local affine feature, an advanced version of the least square matching (LSM) namely, Oriented Least Square Matching (OLSM) is developed. Wellknown LSM method has been widely accepted as one of the most accurate methods to obtain high reliable corresponding points from a stereo image pair. However, it is sensitive to significant geometric distortion and requires very good initial approximation. In the proposed OLSM method, shape and size of the matching window are appropriately approximated using obtained affine shape information of the initial elliptical feature pairs. The proposed method was successfully applied for matching various synthetic and real close range and satellite images. Results demonstrate its accuracy and capability compared to standard LSM method.

Design and implementation of an expert interface system for integration of photogrammetric and Geographic Information Systems for intelligent preparation and structuring of spatial data

Preparation of spatial data for Geographic Information System (GIS) simultaneously during feature digitizing process from photogrammetric models reduces data editing phases after feature digitizing process. Therefore, the problems, caused by separating spatial data production process from preparation of this data, are overcome as far as possible. To achieve this purpose, specialty and expertise required for spatial data structuring and preparation for GIS, should be available in an interface system which establishes a direct connection between photogrammetric and GIS systems. In this case, when a user digitizes a feature from a photogrammetric model, decision making process about the method of editing, structuring, layering, and storing of the feature in GIS database, can be carried out by such an interface system. Thus, according to the capabilities of expert systems for modeling the knowledge and deduction methods of experts, generating an expert interface system between photogrammetric and GIS systems, offers a suitable solution for this integration. In this paper, the capabilities of expert systems for intelligent spatial data structuring and preparation simultaneously during feature digitizing process from photogrammetric models, have been investigated. Also, design, implementation and test of an expert interface system for integration of photogrammetric and GIS systems in order to take advantages of capabilities of both systems simultaneously as one integrated system, has been described.

A survey on player tracking in soccer videos

Abstract There is a growth of demand for automatically analyzing soccer matches and tactics. Since players are the focus of attentions in soccer matches, player tracking is a fundamental element in most soccer video analysis. The aim of player tracking is to extract the trajectories of players, and its input is provided through some preprocessing steps including playfield detection, player detection, player labeling, occlusion handling and player appearance modeling. Soccer player tracking is a complex and challenging task due to difficulties such as blur, illumination change and heavy occlusions. This paper presents the state-of-the-art in preprocessing and processing methods for soccer player tracking. We categorize different approaches, analyze their strengths and weaknesses, review evaluation criteria and conclude future research directions.

An Innovative Image Space Clustering Technique for Automatic Road Network Vectorization

Binary road image space clustering techniques, which are used to determine key points on the road, are expanded to a more accurate and reliable algorithm, the Increasing Ellipse Clustering technique. Accurate noise cluster recognition and omission are 2 strengths of the proposed algorithm. In order to establish the true connections between predetermined key points on the road, a very fast, novel, and reliable fuzzy ellipse-shaped clustering methodology is introduced. Different accuracy assessment parameters are established and evaluated based on results obtained for simulated and real road binary images. The sub-pixel geometric accuracy of the extracted road network, with a completeness of more than 80%, demonstrates the promising results of the vectorization algorithm presented in this paper.