Harris Detector Research Articles

A New Method of Efficient Measurement for Sub-pixel Image Motion of Space Camera

In order to measure the sub-pixel image motion of space camera which is caused by satellite attitude's instability or vibration, a method for image motion detection based on combination of corner detection and improved phase correlation is proposed in this paper. Firstly, it extracts feature points from the serial images using Harris detector. Then, the corners are used to construct a binary matrix. After that, the phase correlation for the constructed image is processed to get the relative output by taking the advantage of Fourier transform symmetry. Simultaneously, Blackman window function is taken to inhibit spectrum leakage caused by truncation for the output image. Finally, the sub-motion vector is calculated with centroid of mass calculation. On the basis of the theory proposed for measuring image motion, experiments for different sub-images with different image motions are carried out. Compared with other motion vector detection technology by soft algorithm, the simulations results show that this method not only inhibits the boundary effect but also avoids bringing truncation error, which improves the accuracy of estimation of image motion. Besides, this method effectively reduces the cost of computation and storage, improving the output SNR with good unimodality and real time property. The measure accuracy is good when the sub-image size is larger than 128128. The accuracy does not change with different scene of input images. The RMS error of image motion measurement can be controlled below 0.1 pixels, which meets the requirement of the space camera. Copyright © 2015 Binary Information Press.

Partial shoeprint retrieval using multiple point-of-interest detectors and SIFT descriptors

Shoeprint evidence collected from crime scenes can play an important role in forensic investigations. Usually, the analysis of shoeprints is carried out manually and is based on human expertise and knowledge. As well as being error prone, such a manual process can also be time consuming; thus affecting the usability and suitability of shoeprint evidence in a court of law. Thus, an automatic system for classification and retrieval of shoeprints has the potential to be a valuable tool. This paper presents a solution for the automatic retrieval of shoeprints which is considerably more robust than existing solutions in the presence of geometric distortions such as scale, rotation and scale distortions. It addresses the issue of classifying partial shoeprints in the presence of rotation, scale and noise distortions and relies on the use of two local point-of-interest detectors whose matching scores are combined. In this work, multiscale Harris and Hessian detectors are used to select corners and blob-like structures in a scale-space representation for scale invariance, while Scale Invariant Feature Transform (SIFT) descriptor is employed to achieve rotation invariance. The proposed technique is based on combining the matching scores of the two detectors at the score level. Our evaluation has shown that it outperforms both detectors in most of our extended experiments when retrieving partial shoeprints with geometric distortions, and is clearly better than similar work published in the literature. We also demonstrate improved performance in the face of wear and tear. As matter of fact, whilst the proposed work outperforms similar algorithms in the literature, it is shown that achieving good retrieval performance is not constrained by acquiring a full print from a scene of crime as a partial print can still be used to attain comparable retrieval results to those of using the full print. This gives crime investigators more flexibility is choosing the parts of a print to search for in a database of footwear.

Automatic Segmentation of Nature Object Using Salient Edge Points Based Active Contour

Natural image segmentation is often a crucial first step for high-level image understanding, significantly reducing the complexity of content analysis of images. LRAC may have some disadvantages. (1) Segmentation results heavily depend on the initial contour selection which is a very skillful task. (2) In some situations, manual interactions are infeasible. To overcome these shortcomings, we propose a novel model for unsupervised segmentation of viewer’s attention object from natural images based on localizing region-based active model (LRAC). With aid of the color boosting Harris detector and the core saliency map, we get the salient object edge points. Then, these points are employed as the seeds of initial convex hull. Finally, this convex hull is improved by the edge-preserving filter to generate the initial contour for our automatic object segmentation system. In contrast with localizing region-based active contours that require considerable user interaction, the proposed method does not require it; that is, the segmentation task is fulfilled in a fully automatic manner. Extensive experiments results on a large variety of natural images demonstrate that our algorithm consistently outperforms the popular existing salient object segmentation methods, yielding higher precision and better recall rates. Our framework can reliably and automatically extract the object contour from the complex background.

그레디언트 행렬 고유치의 기하 평균을 이용한 특징점 검출

동일 대상에 대한 두 영상의 등록을 위해서는 두 영상에 공통적으로 존재하는 특징점을 검출하고 검출된 특징점 간의 대응관계를 찾는 과정이 필수적이다. 본 논문에서는 화소의 밝기 변화를 측정할 수 있는 그레디언트 행렬의 고유치 기하평균에 기반한 새로운 특징점 검출기를 제안한다. 제안하는 특징점 검출기는 그레디언트 행렬의 두 고유치의 기하평균 크기에 비례하고 기하 평균 크기가 동일한 경유 두 고유치의 상대적인 차이에 비례하여 가변적으로 변하는 특성을 가진다. 제안한 특징점 검출기의 성능 평가를 위해 다양한 종류의 코너가 존재하는 합성 영상과 항공 영상을 기준 영상으로 사용하여 코너 검출의 위치 오차를 분석하였다. 제안한 검출기의 위치 오차는 Gaussian smoothing scale 조건하에서 대표적인 코너 검출기인 Harris detector의 위치 오차보다 작은 결과가 얻어졌다. It is necessary to detect the feature points existing simultaneously in both images and then find the corresponding relationship between the detected feature points. We propose a new feature detector based on geometric mean of two eigenvalues of gradient matrix which is able to measure the change of pixel intensities. The corner response of the proposed detector is proportional to the geometric mean and also the difference of two eigenvalues in the case of same geometric mean. We analyzed the localization error of the feature detection using aerial image and artificial image with various types of corners. The localization error of the proposed detector was smaller than that of the typical corner detector, Harris detector.

Improved Image Alignment Algorithm Based on Projective Invariant for Aerial Video Stabilization

In many moving object detection problems of an aerial video, accurate and robust stabilization is of critical importance. In this paper, a novel accurate image alignment algorithm for aerial electronic image stabilization (EIS) is described. The feature points are first selected using optimal derivative filters based Harris detector, which can improve differentiation accuracy and obtain the precise coordinates of feature points. Then we choose the Delaunay Triangulation edges to find the matching pairs between feature points in overlapping images. The most “useful” matching points that belong to the background are used to find the global transformation parameters using the projective invariant. Finally, intentional motion of the camera is accumulated for correction by Sage-Husa adaptive filtering. Experiment results illustrate that the proposed algorithm is applied to the aerial captured video sequences with various dynamic scenes for performance demonstrations.

DETECÇÃO E RECONHECIMENTO DE OBJETOS EM IMAGENS UTILIZANDO ALGORITMOS DE EXTRAÇÃO DE PONTOS CHAVE

This paper presentsa comparative studyof descriptors keypoint algorithms doinga combinationof detectors anddescriptors. We combined the SIFT, SURF and Harris detector algorithms with the SIFT and SURF descriptor algorithms.Three experimentswith images withdifferent characteristicswere performed,intwo of theseexperimentswere usedimages of realobjects, in athird experiment, some degradationin an imagesuch asscale reduction, rotation, blurring, darkening andaddition ofnoisehave beenperformed, to analyze the behaviorof the algorithms. Experiments were also performed withalldegradationstogether.Toanalyze theproposedcombination, we extractedprocessing timeand the number ofinliers. This workcontributes toapplicationsthat requireusing keypoint descriptors algorithms in detection andrecognitionof objects inimages.

Histogram modification based image watermarking resistant to geometric distortions

A geometrically invariant digital image watermarking scheme based on histogram modification is proposed in this paper. The feature extraction method called Adaptive Harris Detector with Simulated Attacks is proposed and employed, which adjusts and ranks the response threshold value of the traditional Harris Corner Detector, and trains the input image with several simulated attacks, to extract the most reliable feature points for watermark data bits embedding and extraction. The watermark embedding regions are then found as square patches centering at the selected geometric invariant feature points. In each region, the intensity-level histogram is modified by moving some pixels to form a specific pattern according to the corresponding watermark bit. For watermark extraction, the proposed Adaptive Harris Detector with Simulated Attacks is proposed to restore the watermarked image to its original position if any geometric attack exists, and to retrieve the watermarked regions. According to the pattern of intensity-level histogram distribution in these regions, a sequence of watermark bits is then extracted. Experimental results show that the proposed scheme is robust against both the geometric attacks and common signal processing, such as rotation, scaling, cropping, JPEG compression, median filtering, low-pass Gaussian filtering and also noise pollution.

A new method for the detection and classification of weave pattern repeat

A novel method combining the characteristics of corner information and second-order statistics of fabric images is proposed for analyzing the repeat size and identifying the weave type of fabrics. The analysis method is formulated in a research framework of near regular texture analysis. Firstly, the original fabric image is split into two components: the geometric component and the textural component, in which low-level cues of corners are detected by the Harris detector. Secondly, clustering techniques are used to cluster interest points by image patch appearance. Thirdly, a Markov Random Field (MRF) model is adopted for inferring the location of texture elements, and their shape is then used for classifying the weave patterns. The experimental results show that the main disadvantages and difficulties of using structural and frequency methods in texture classifications have been overcome by the proposed method.

An Application of 3-D Harris Operator in Video Frame Feature Detection

In order to solve the problem of image matching, the points matching in the fields of digital photogrammetry and computer vision is researched very deeply. The accuracy of the feature points plays an important role in making right matching results. The paper introduces a method of 3-D Harris detector. An algorithm of Gaussian smoothing is applied for eliminating sudden gray change. Corners of all pixels are detected in a video using Harris. The results of experiments show that the 3-D Harris detector is accuracy and efficient.

Speed up junction detector based on azimuth consensus by Harris corner

Compared with common corner, junction point includes much structural data of branch edges. Due to its complicated computation, it prevents the wide use in many computer vision applications. In this paper, we propose a fast and effective junction point detection method based on Harris detector and azimuth consensus. To accelerate the process of the junction detection, we adopt Harris detector to filter out most pixels of the flat region and choose candidate junction set. Comparisons are made with other known detectors including CPDA, JUDOCA, and Lian’s method. The experimental results show our method has high-accuracy in location and branch edges’ orientation and good robustness for noise and contrast impact; what’s more, its computation time is reduced at high speed. Especially for real world image sets, our method can be more than 8 times faster than Lian’s and 1.58 times faster than JUDOCA.

Euclidean 3D Reconstruction of Unknown Objects from Multiple Images

In this paper, we are interested in the problem of Euclidean 3D reconstruction of unknown objects by passive stereo vision method. Our method is based on the combination between Harris and Sift interest point detectors, to take advantage of the power of these two detectors, which will be useful when matching step, as a key step for 3D reconstruction, In order to have a sufficient number of matches distributed on the images. These matches will be used to estimate the 3D points (the projection matrices will be estimated after calibration using 3D Calibration Pattern). Finally, a 3D mesh is constructed by 3D Delaunay triangulation, applied to the 3D points reconstructed. Experimental results prove that this method is practical and gives satisfying results without going through the propagation step.

Enhanced low-complexity pruning for corner detection

Low-complexity corner detection is essential for many real-time computer vision applications that need to be executed on low-cost/low-power embedded platforms such as robots. The widely used Shi---Tomasi and Harris corner detectors become prohibitive in such platforms due to their high computational complexity, which is attributed to the need to apply a complex corner measure on the entire image. In this paper, we introduce a novel and computationally efficient technique to accelerate the Shi---Tomasi and Harris corner detectors. The proposed technique consists of two steps. In the first step, the complex corner measure is replaced with simple approximations to quickly prune away non-corners. In the second step, the complex corner measure is applied to a small corner candidate set obtained after pruning. Evaluations using standard image benchmarks show that the proposed pruning technique achieves up to 75 % speedup on the Nios-II platform, while yielding corners with comparable or better accuracy than the conventional Shi---Tomasi and Harris detectors.

Comparing Effectiveness of Feature Detectors in Obstacles Detection from a Video

We have already proposed an obstacles detection method using a video taken by a vehicle-mounted monocular camera. In this method, correct obstacles detection depends on whether we can accurately detect and match feature points. In order to improve the accuracy of obstacles detection, in this paper, we make comparison among four most commonly used feature detectors; Harris, SIFT, SURF and FAST detectors. The experiments are done using our obstacles detection method. The experimental results are compared and discussed, and then we find the most suitable feature point detector for our obstacles detection method.

A novel algorithm in buildings/shadow detection based on Harris detector

A novel method based on corner detectors is proposed in detecting shadow and buildings in this paper. Its most outstanding point is employing Harris corner detector in region-based detection, despite that Harris detector traditionally used to select pixels as final results. Different densities of buildings are generally influenced by different features for recognition. First time, images are self-grouped into two groups according to the distribution of buildings, and two specifical algorithms are ready for detection specifically. A region-based method is used in comparison with our algorithm, and the results indicate that the new idea works not only more robustly, but also more effectively. It is a fast and simple method, which needs average 3.28×10−5s to run per square image.

Fault-Tolerant Building Change Detection From Urban High-Resolution Remote Sensing Imagery

This letter proposes a novel change detection model, focusing on building change information extraction from urban high-resolution imagery. It consists of two blocks: 1) building interest-point detection, using the morphological building index (MBI) and the Harris detector; and 2) multitemporal building interest-point matching and the fault-tolerant change detection. The proposed method is insensitive to the geometrical differences of buildings caused by different imaging conditions in the multitemporal high-resolution imagery and is able to significantly reduce false alarms. Experiments showed that the proposed method was effective for building change detection from multitemporal urban high-resolution images. Moreover, the effectiveness of the algorithm was validated by comparing with the morphological change vector analysis (CVA), parcel-based CVA, and MBI-based CVA.

A New Image Watermarking Algorithm Using NSCT and Harris Detector in Green Manufacturing

Based on multistage theory and NSCT, a new feature-based image watermarking scheme is proposed in this paper. Firstly, the multistage Harris detector is utilized to extract steady feature points from the host image; then, the local feature regions (LFR) are ascertained adaptively according to the feature scale theory, and they are scaled to a standard size; finally, the digital watermark are embedded into no subsample contour let low frequency area, in the low frequency regions made pseudo-Zernike moment calculation. Experimental results show that the proposed scheme is not only invisible and robust against common signals processing such as median filtering, sharpening, noise adding and JPEG compression et al, but also robust against the unclassified geometric attacks such as rotation, translation, scaling, row or column removal, shearing, local geometric distortion and combination attacks et al.

Fast 3-D Feature Point Detector Based on Harris

Image matching is a key a key technology to be solved in the fields of digital photogrammetry and computer vision. Matching based on points matching is most widely used now. How to locate the right feature points is vital. Only accurate feature points can make right matching results. The paper introduces a method of 3-D Harris detector. The two steps matching have been done in our works. The results of experiments show that the 3-D Harris detector is accuracy and efficient.

Recognition of Amazigh Characters using Visual Rotation Invariant Features

paper, we present a new method for Amazigh Character Recognition. It is based on the extraction of salient points from the Tifinagh characters using a visual detector and descriptor. The novelty of this work is, first, the development of a new detector descriptor having a high repeatability which outperforms other transforms like (SIFT, SURF, Harris), second, its application for the recognition of the Amazigh characters. Our method is called Rotation Invariant Detector (RID). We use steerable filters for representing the image in many scales and orientations, then, the Harris detector applied to each of the obtained images, because of its high speed in the detection operation. In order to recognize a character, we match our image test to the database of learnt characters. We present in this work two applications based on RID: , The visual recognition of handwritten Tifinagh Characters using the paradigm (learning, classification) The conversion of a handwritten character to a typed character with a computer 1. INTRODUCTION computer vision is the science of recognizing objects in the images and interpreting them. During the last decade, this discipline has been widely investigated because of its relation to other fields such as charactere treatment and image retrieval. In order to interpret an image, the analysis has to move from image processing tasks to object recognition and categorization. Consequently, the algorithms which are used should be faster and more complicated. The description of the images can be obtained with predifined kernels to obtain edges. Or by using more recent differential methods to extract

A Novel High Accuracy Sub-Pixel Corner Detection Algorithm for Camera Calibration

This paper presents a novel sub-pixel corner detection algorithm for camera calibration. In order to achieve high accuracy and robust performance, the pixel level candidate regions are firstly identified by Harris detector. Within these regions, the center of gravity (COG) method is used to gain sub-pixel corner detection. Instead of using the intensity value of the regions, we propose to use corner response function (CRF) as the distribution of the weights of COG. The results of camera calibration experiments show that the proposed algorithm is more accurate and robust than traditional COG sub-pixel corner detection methods.

ORIENTATION BASED BUILDING OUTLINE EXTRACTION IN AERIAL IMAGES

Abstract. The goal of this paper is to extract automatically the building contours regardless of shape. By extracting these contours, detection results will be more accurate, giving useful information about urban area, which is important for many tasks, like map updating and disaster management. First, we extract local feature points from the image, based on a modification of Harris detector's saliency function, which can represent urban area and building effectively. This point set is then used to define the main orientation of the buildings, which characterizes well an urban region and helps to define directions, where object contours have to be searched. Second, we applied shearlet approach to extract edges in the defined directions. This results in an edge map, which helps us to determine point subsets belonging to the same building. Convex hulls of the point subsets is used for contour initialization, then region based Chan-Vese Active Contour method is applied to extract the accurate building outlines.