Showing papers on "Corner detection published in 2013"

Efficient Salient Region Detection with Soft Image Abstraction

Abstract: Detecting visually salient regions in images is one of the fundamental problems in computer vision. We propose a novel method to decompose an image into large scale perceptually homogeneous elements for efficient salient region detection, using a soft image abstraction representation. By considering both appearance similarity and spatial distribution of image pixels, the proposed representation abstracts out unnecessary image details, allowing the assignment of comparable saliency values across similar regions, and producing perceptually accurate salient region detection. We evaluate our salient region detection approach on the largest publicly available dataset with pixel accurate annotations. The experimental results show that the proposed method outperforms 18 alternate methods, reducing the mean absolute error by 25.2% compared to the previous best result, while being computationally more efficient.

A Generalized Laplacian of Gaussian Filter for Blob Detection and Its Applications

Abstract: In this paper, we propose a generalized Laplacian of Gaussian (LoG) (gLoG) filter for detecting general elliptical blob structures in images. The gLoG filter can not only accurately locate the blob centers but also estimate the scales, shapes, and orientations of the detected blobs. These functions can be realized by generalizing the common 3-D LoG scale-space blob detector to a 5-D gLoG scale-space one, where the five parameters are image-domain coordinates (x, y), scales (σx, σy), and orientation (θ), respectively. Instead of searching the local extrema of the image's 5-D gLoG scale space for locating blobs, a more feasible solution is given by locating the local maxima of an intermediate map, which is obtained by aggregating the log-scale-normalized convolution responses of each individual gLoG filter. The proposed gLoG-based blob detector is applied to both biomedical images and natural ones such as general road-scene images. For the biomedical applications on pathological and fluorescent microscopic images, the gLoG blob detector can accurately detect the centers and estimate the sizes and orientations of cell nuclei. These centers are utilized as markers for a watershed-based touching-cell splitting method to split touching nuclei and counting cells in segmentation-free images. For the application on road images, the proposed detector can produce promising estimation of texture orientations, achieving an accurate texture-based road vanishing point detection method. The implementation of our method is quite straightforward due to a very small number of tunable parameters.

Scale Selection Properties of Generalized Scale-Space Interest Point Detectors

Abstract: Scale-invariant interest points have found several highly successful applications in computer vision, in particular for image-based matching and recognition. This paper presents a theoretical analy ...

Hybrid method based on topography for robust detection of iris center and eye corners

Abstract: A multistage procedure to detect eye features is presented. Multiresolution and topographic classification are used to detect the iris center. The eye corner is calculated combining valley detection and eyelid curve extraction. The algorithm is tested in the BioID database and in a proprietary database containing more than 1200 images. The results show that the suggested algorithm is robust and accurate. Regarding the iris center our method obtains the best average behavior for the BioID database compared to other available algorithms. Additional contributions are that our algorithm functions in real time and does not require complex post processing stages.

Corner Detection and Classification Using Anisotropic Directional Derivative Representations

Abstract: This paper proposes a corner detector and classifier using anisotropic directional derivative (ANDD) representations. The ANDD representation at a pixel is a function of the oriented angle and characterizes the local directional grayscale variation around the pixel. The proposed corner detector fuses the ideas of the contour- and intensity-based detection. It consists of three cascaded blocks. First, the edge map of an image is obtained by the Canny detector and from which contours are extracted and patched. Next, the ANDD representation at each pixel on contours is calculated and normalized by its maximal magnitude. The area surrounded by the normalized ANDD representation forms a new corner measure. Finally, the nonmaximum suppression and thresholding are operated on each contour to find corners in terms of the corner measure. Moreover, a corner classifier based on the peak number of the ANDD representation is given. Experiments are made to evaluate the proposed detector and classifier. The proposed detector is competitive with the two recent state-of-the-art corner detectors, the He & Yung detector and CPDA detector, in detection capability and attains higher repeatability under affine transforms. The proposed classifier can discriminate effectively simple corners, Y-type corners, and higher order corners.

A Survey on Image Mosaicing Techniques

Abstract: Image Mosaicing is a method of assembling multiple overlapping images of the same scene into a larger image. The output of the image mosaic will be the union of two input images. Image-mosaicing algorithms are used for obtaining a mosaiced image. There are five steps used in image mosaicing which includes; Feature extraction, Image registration, Computing homography, Warping and Blending. Feature extraction is an Image mosaicing technique which is done by using various corner detection algorithm. This corner detection algorithm produces an efficient and informative output mosaiced image. Importance of Image mosaicing can be seen in the field of medical imaging, computer vision, data from satellites, military automatic target recognition.

Unsupervised Detection of Built-Up Areas From Multiple High-Resolution Remote Sensing Images

Abstract: Given a set of high-resolution remote sensing images covering different scenes, we propose an unsupervised approach to simultaneously detect possible built-up areas from them. The motivation behind is that the frequently recurring appearance patterns or repeated textures corresponding to common objects of interest (e.g., built-up areas) in the input image data set can help us discriminate built-up areas from others. With this inspiration, our method consists of two steps. First, we extract a large set of corners from each input image by an improved Harris corner detector. Afterward, we incorporate the extracted corners into a likelihood function to locate candidate regions in each input image. Given a set of candidate build-up regions, in the second stage, we formulate the problem of build-up area detection as an unsupervised grouping problem. The candidate regions are modeled through texture histogram, and the grouping problem is solved by spectrum clustering and graph cuts. Experimental results show that the proposed approach outperforms the existing algorithms in terms of detection accuracy.

Human recognition based on retinal images and using new similarity function

Abstract: This paper presents a new human recognition method based on features extracted from retinal images. The proposed method is composed of some steps including feature extraction, phase correlation technique, and feature matching for recognition. In the proposed method, Harris corner detector is used for feature extraction. Then, phase correlation technique is applied to estimate the rotation angle of head or eye movement in front of a retina fundus camera. Finally, a new similarity function is used to compute the similarity between features of different retina images. Experimental results on a database, including 480 retinal images obtained from 40 subjects of DRIVE dataset and 40 subjects from STARE dataset, demonstrated an average true recognition accuracy rate equal to 100% for the proposed method. The success rate and number of images used in the proposed method show the effectiveness of the proposed method in comparison to the counterpart methods.

Pedestrian Detection Based on Blob Motion Statistics

Abstract: Pedestrian detection based on video analysis is a key functionality in automated surveillance systems. In this paper, we present efficient detection metrics that consider the fact that human movement presents distinctive motion patterns. Contrary to several methods that perform an intrablob analysis based on motion masks, we approach the problem without necessarily considering the periodic pixel motion inside the blob. As such, we do not analyze periodicity in the pixel luminances, but in the motion statistics of the tracked blob as a whole. For this, we propose the use of the following cues: 1) a cyclic behavior in the blob trajectory, and 2) an in-phase relationship between the change in blob size and position. In addition, we also exploit the relationship between blob size and vertical position, assuming that the camera is positioned sufficiently high. If the homography between the camera and the ground is known, the features are normalized by transforming the blob size to the real person size. For improved performance, we combine these features using the Bayes classifier. We also present a theoretical statistical analysis to evaluate the system performance in the presence of noise. We perform online experiments in a real industrial scenario and also with videos from well-known databases. The results illustrate the applicability of the proposed features.

Pipelining Harris corner detection with a tiny FPGA for a mobile robot

Abstract: With their parallelizable inner structures, field programmable gate array (FPGA) are increasing their popularity in today's embedded systems. In this paper, we present an implemented, unique and pipelined FPGA architecture designed with Verilog HDL to be used on a mobile robot for detecting corners in colored stereo images using Harris corner detection (HCD) algorithm in real time. The architecture consists of 3 pipelined modules and processes RGB555 formatted images in 640×480 resolution. The design is implemented on Xilinx's ML501 board having a XC5VLX50 FPGA, one of the smallest FPGAs of Virtex-5 series. Raw and processed data are stored into a single DDR2 memory of Micron, MT4HTF3264HY on the board, allowing only a single read or write operation at a time. By using less than 75% of FPGA resources and a 100MHz system clock, we achieved a corner detection rate of 0.33 pixels per clock cycle (ppcc) corresponding to a corner detection frequency of 54Hz for the stereo images.

A Review Paper on Various Approaches for Image Mosaicing

Abstract: Image mosaicing is one of the most important subject of research in computer vision. Image mosaicing requires the integration of direct methods and feature based methods. Direct methods are found to be useful for mosaicing large overlapping regions, small translations and rotations while feature based methods are useful for small overlapping regions. Feature based image mosaicing is combination of corner detection, corner matching, motion parameters estimation and image stitching. In this paper we present a review on different approaches for image mosaicing and the literature over the past in the field of image mosaicing methods. We take an overview on the various methods for image mosaicing.

Multiobjective Discrete Particle Swarm Optimization for Multisensor Image Alignment

Abstract: A new technique is proposed for multisensor image registration by matching the features using discrete particle swarm optimization (DPSO). The feature points are first extracted from the reference and sensed image using improved Harris corner detector available in the literature. From the extracted corner points, DPSO finds the three corresponding points in the sensed and reference images using multiobjective optimization of distance and angle conditions through objective switching technique. By this, the global best matched points are obtained which are used to evaluate the affine transformation for the sensed image. The performance of the image registration is evaluated and concluded that the proposed approach is efficient.

Automatically calibration method based on black and white grid corner matching

Abstract: The invention discloses an automatically calibration method based on black and white grid corner matching. The method includes adopting black and white calibrating cloth as a calibrating model, respectively detecting image corners by an improved harris corner detection calculation, building position relations between corners and forming a corner network; performing distortion correction and matching to images; calculating corner position in non-distorting images and homographic matrix of corner real position in final virtual full view bird's-eye view; and performing view changing according to virtual bird's-eye view camera position and homographic matrix, calculating corresponding relation between image points in the coordinate system and the original images, and then forming a lookup table. The automatically calibration method adopting the improved harris corner detection calculation is simple and practical, can well judge corner position relation, and forms a correct corner network; and the automatically calibration method adopting lookup table function can generate output images after the images are calibrated, is fast, and can well meet real-time need.

Parameter calibration method and device

Abstract: Disclosed in an embodiment of the present invention is a parameter calibration method, the method comprising: acquiring a calibration template image obtained by photographing a calibration template; conducting corner detection on the calibration template image to extract an image corner; calculating radial distortion parameters according to the extracted image corners; correcting the radial distortion according to the calculated radial distortion parameters, so as to reconstruct a distortion-corrected image; and according to the perspective projection relationship between the calibration template and the reconstructed distortion-corrected image, calculating an internal parameter and an external parameter to achieve parameter calibration, the internal and external parameters containing: an internal parameter matrix, a rotating vector and a translation vector Also provided in the embodiment of the present invention is a parameter calibration device The present invention can be applied to the parameter calibration of imaging devices such as a video camera or a camera under high distortion, and is of simple operation and high precision

Image processing device, projector, and method of controlling projector

Abstract: An image processing device used for a projector displays an image by projecting the image on a projection surface A detection image generation section adapted to generate a detection image, which is an image adapted to detect a state of a projection image displayed on the projection surface, and includes a plurality of detection image parts is provided Each of the detection image parts includes a plurality of regions having respective luminance values different from each other The detection image generation section changes the luminance distribution of each of the detection image parts of the detection image to be generated so that the maximum luminance values of the detection image parts included in the taken detection image obtained by taking the detection image projected on the projection surface fall within an allowable range

Moving Object Detection and Tracking in Videos

Abstract: This chapter provides four sections. The first section introduces the moving object D&T infrastructure and basis of some methods for object detection and tracking (D&T) in videos. In object D&T applications, there is manual or automatic D&T process. Also, the image features, such as color, shape, texture, contours, and motion can be used to track the moving object(s) in videos. The detailed information for moving object detection and well-known trackers are presented in this section as well. In second section, the background subtraction (BS) method and its applications are given in details. The third section declares the details for Mean-shift (MS), Mean-shift filtering (MSF), and continuously adaptive Mean-shift (CMS or CAMShift) methods and their applications. In fourth section, the details for the optical flow (OF), the corner detection through feature points, and OF-based trackers are given in details.

Building detection in high resolution satellite urban image using segmentation, corner detection combined with adaptive windowed Hough Transform

Abstract: The building detection is one of the most challenging issues in remote sensing image processing. In this paper, a novel approach for building detection using corner detection, segmentation and adaptive windowed Hough Transform is presented. In the first, the Mean shift segmentation is used to split the image into a numbers of classes. In the second step, the scale invariant feature transform (SIFT) is used to extract the corners in the original image. In the third step the corners are used as one of the evidences to verify the presence of buildings. In the Mean shift segmentation result image, around the corners detected by SIFT algorithm, the approximate boundary of the buildings is extracted. With the help of approximate boundary of the buildings, the size of the building can be estimate. Finally, in order to extract the precise building roof boundary, the adaptive windowed Hough Transform is used to extract the straight line of the building boundary. Preliminary experimental results indicate that the proposed method produced promising results.

Visible watermarking within the region of non -interest of medical images based on fuzzy c-means and harris corner detection

Abstract: Transfer of medical information amongst various hospitals and diagnostic centers for mutual availability of diagnostic and therapeutic case studies is a very common process. Watermarking is adding “ownership” information in multimedia contents to verify signal integrity, prove authenticity and achieve control over the copy process. Distortion in Region of Interest (ROI) of a bio-medical image caused by watermarking may lead to wrong diagnosis and treatment. Therefore, proper selection of Region of Non-Interest (RONI) in a medical image is very crucial for adding watermark. First part of the present work proposes proper selection of Region of Non-Interest based on Fuzzy C-Means segmentation and Harris corner detection, to improve retention of diagnostic value lost in embedding ownership information. The second part of the work presents watermark embedding in the selected area of RONI based on alpha blending technique. In this approach, the generated watermarked image having an acceptable level of imperceptibility and distortion is compared to the original image. The Peak Signal to Noise Ratio (PSNR) of the original image vs. watermarked image is calculated to prove the efficacy of the proposed method.

Improved Harris sub-pixel corner detection algorithm for chessboard image

Abstract: Control point image locating accuracy of calibration plate is one of the major factors which determine the accuracy of camera calibration. Thus we can improve determine the accuracy of camera calibration by improve the control point image locating accuracy of calibration plate. And an improved Harris sub-pixel corner detection algorithm is put forward to improve the control point image locating accuracy. Initial location of corner point using Harris corner detection algorithm is implemented at first, and then improved Harris corner detection algorithm is used to realize sub-pixel locating accuracy. Corner points' coordinate values are gotten by means of initial location and fine location. The result of examine show that corner detection precision is improved greatly through improved Harris sub-pixel corner detection algorithm of chessboard image, and realize the sub-pixel corner detection.

Fast moving object detection with non-stationary background

Abstract: The detection of moving objects under a free-moving camera is a difficult problem because the camera and object motions are mixed together and the objects are often detected into the separated components. To tackle this problem, we propose a fast moving object detection method using optical flow clustering and Delaunay triangulation as follows. First, we extract the corner feature points using Harris corner detector and compute optical flow vectors at the extracted corner feature points. Second, we cluster the optical flow vectors using K-means clustering method and reject the outlier feature points using Random Sample Consensus algorithm. Third, we classify each cluster into the camera and object motion using its scatteredness of optical flow vectors. Fourth, we compensate the camera motion using the multi-resolution block-based motion propagation method and detect the objects using the background subtraction between the previous frame and the motion compensated current frame. Finally, we merge the separately detected objects using Delaunay triangulation. The experimental results using Carnegie Mellon University database show that the proposed moving object detection method outperforms the existing other methods in terms of detection accuracy and processing time.

QR Code Image Correction based on Corner Detection and Convex Hull Algorithm

Abstract: Since the angular deviation produced when shooting a QR code image by a camera would cause geometric distortion of the QR code image, the traditional algorithm of QR code image correction would produce distortion. Therefore this paper puts forward the algorithm which combines corner detection with convex hull algorithm. Firstly, binaryzation of the collected QR code image with uneven light is obtained by the methods of local threshold and mathematical morphology. Next, the outline of the QR code and the dots on it are found and the distorted image is recovered by perspective collineation, according to the algorithm raised by this paper. Finally, experimental verification is made that the algorithm raised by this paper can correctly find the four apexes of QR code and achieves good effects of geometric correction. It will also significantly increase the recognition rate of seriously distorted QR code images

Real-time feature-based video mosaicing at 500 fps

Abstract: We conducted high-frame-rate (HFR) video mosaicing for real-time synthesis of a panoramic image by implementing an improved feature-based video mosaicing algorithm on a field-programmable gate array (FPGA)-based high-speed vision platform. In the implementation of the mosaicing algorithm, feature point extraction was accelerated by implementing a parallel processing circuit module for Harris corner detection in the FPGA on the high-speed vision platform. Feature point correspondence matching can be executed for hundreds of selected feature points in the current frame by searching those in the previous frame in their neighbor ranges, assuming that frame-to-frame image displacement becomes considerably smaller in HFR vision. The system we developed can mosaic 512×512 images at 500 fps as a single synthesized image in real time by stitching the images based on their estimated frame-to-frame changes in displacement and orientation. The results of an experiment conducted, in which an outdoor scene was captured using a hand-held camera-head that was quickly moved by hand, verify the performance of our system.

Classification based survey of image registration methods

Abstract: Image registration technique is useful for variety of applications ranging from surveillance to image mosaicing where task is to match two or more pictures taken, for example, at different times, from different sensors, or from different viewpoints. This paper is an attempt to make a survey of image registration techniques and provides overall source of recent as well as classic research. Scope of this paper is to explain, refer and compare researches done in last decade, on image registration. Classification of registration process is done on various basis including applications, dimensions and essential ideas. Each step of registration process is explained but more attention is given to feature matching and feature detection. Also an attempt is made to explain transformation and re-sampling involved in registration, thereby making this paper a single source (for future researchers) of process and research involved in the field of Image Registration.

Chessboard corner detection under image physical coordinate

Abstract: The existing chessboard corner detection algorithms cannot be used in complex scenes because distortion might occur as a result of overexposure or low resolution, among other factors. This distortion hinders the precise detection of the chessboard corners using the previous methods. To address this issue, we proposed a chessboard corner detector based on image physical coordinates and a round template. The physical coordinates allowed our detected chessboard corners to reach the subpixel-level after only one step. We first covered the distorted chessboard corners by utilising the morphological dilation. Then, we employed our round template to pass through the dilated image and ultimately determine the chessboard corner coordinate by analysing the grey distribution of the traversed round template and calculating the centroids of redundant points. The experimental results showed that our algorithm performs better than other algorithms in both simple backgrounds and complex scenes. By applying our detector to camera calibration, we obtained a smaller re-projection error, thereby proving the validity of our proposed detector.

Self-tunable transformation function for enhancement of high contrast color images

Abstract: A new image enhancement technique based on a self-tunable transformation function to improve the visual quality of images captured with low dynamic range devices in extreme lighting conditions is presented. This technique consists of four processes: histogram adjustment, dynamic range compression, contrast enhancement, and nonlinear color restoration. Histogram adjustment on each spectral band is performed to minimize the effect of illumination. Dynamic range compression is accomplished by a newly designed inverse sine nonlinear function that provides various nonlinear curvatures with an image dependent parameter. A nonlinear curve generated by this parameter is used to modify the intensity of each pixel in the luminance image. A nonlinear color restoration process based on the chromatic information and luminance of the original image is employed. The effectiveness of this technique is evaluated on various natural images and aerial images, and compared with other state-of the art techniques. A quantitative evaluation is performed by estimating the number of Harris corners and speeded up robust features on wide area motion imagery data. The application of the proposed algorithm on face detection is also demonstrated. The evaluation results demonstrate that the proposed method holds significant benefits for surveillance and security applications and also as a preprocessing technique for object detection and tracking applications.

Parameter calibration system of vehicle-mounted camera

Abstract: Disclosed is a parameter calibration method of a vehicle-mounted camera. The method includes steps of self-making a three-dimensional calibration board, and establishing a world coordinate system on the basis of the self-made three-dimensional calibration board; establishing a camera calibration model on the basis of the three-dimensional calibration board, acquiring world coordinates of chessboard corners of the three-dimensional calibration board, and extracting pixel coordinates of the chessboard corners on the basis of a corner detection algorithm; and using a least square method to calibrate inner and outer parameters of a camera in combination of the corner world coordinates and the pixel coordinates.

A Moving Object Detection Algorithm Based on a Combination of Optical Flow and Three-Frame Difference

Abstract: Moving objects detection is an important research of computer vision.Optical flow method is an important way,but it is limited to use because of its complexity.A moving object detection algorithm based on a combination of optical flow and the three-frame difference is proposed.The calculation of optical flow is simplified.Harris corners are detected,then the pixels are selected to compute optical flow information,which reduce the algorithm′s complexity.Because the detected moving target area is not complete,three-frame difference method is introduced as a supplement.The experimental results show that the algorithm can achieve real-time and have better results than anyone in these two separate algorithms.

Accurate image registration for MAP image super-resolution

Abstract: The accuracy of image registration plays a dominant role in image super-resolution methods and in the related literature, landmark-based registration methods have gained increasing acceptance in this framework. In this work, we take advantage of a maximum a posteriori (MAP) scheme for image super-resolution in conjunction with the maximization of mutual information to improve image registration for super-resolution imaging. Local as well as global motion in the low-resolution images is considered. The overall scheme consists of two steps. At first, the low-resolution images are registered by establishing correspondences between image features. The second step is to fine-tune the registration parameters along with the high-resolution image estimation, using the maximization of mutual information criterion. Quantitative and qualitative results are reported indicating the effectiveness of the proposed scheme, which is evaluated with different image features and MAP image super-resolution computation methods.

Edge and corner detection by color invariants

Abstract: Gray-based features are widely used in computer vision applications, while image color is a very important source, which can provide more feature information To fully exploit color data, a color saturation invariant based on dichromatic reflection model is first constructed The invariant is an object reflectance property independent of viewpoint and illumination direction The saturation invariant is then synthesized with existing hue invariant to detect edge and corner features in color image Experiments show that the detection method proposed here can more effectively tap into color information and achieve true target features due to its lower sensitivity to shadow, shading and highlight Moreover, when comparing with many other existing edges and corners detecting methods, experimental results demonstrate that the proposed method performs better in detection accurate and effective