Panoramic Image Stitching Research Articles

360-Degree Panoramic Image Stitching for Un-ordered Images Based on Harris Corner Detection

Objectives: This work aims to provide a system to arrange images automatically and produce the High-resolution panoramic images of a 360-degree wide range. Methods: This work consists of many stages which start by arranging the set of unordered input images. The Harris corner detector is used in the process of detecting key-points. Euclidean distance measure is used to compute the distance between points and determine matches. The stage of stitching consists of several steps which are detecting key-points, matching, estimating the shifting matrix between images by using Random Sample Consensus (RANSAC) algorithm, aligning, and blending. Findings: Experiments show that this method is able to arrange different sets of images, where samples taken are between 15–18 images. Depending on the threshold values in the verification process applied to the matched points, which range from (0.4 to 0.6), the number of extracted features and the degree of accuracy can be controlled. Also, the process of blending images based on the taking of a different percentage of the overlapping areas according to the proximity to the contact line gave a distinctive blending result. Application: Production of panoramic images are used in real estate photography, the creation of an attractive experience on viewing all location details, and lots of other uses. Keywords: Blending, Harris Corner Detector, Image Stitching, Panorama

Research of Panoramic Image Generation Using IoT Device with Camera for Cloud Computing Environment

Recently, interest in internet of things (IoT) has increased, and a lot of technologies are being developed, especially using cameras. However, normal cameras used in the IoT have limited viewing angles and can not acquire a wide range of high resolution images. Image stitching in IoT devices has a problem that requires a large amount of computation. Therefore, we propose a method to distribute the high computational load by transmitting the individual image transmitted from the IoT device with the camera to the cloud and computing the homography information necessary for stitching the image and transmitting the information to the client. In addition, we propose an improved feature point descriptor extraction technique to reduce the amount of stitching computation for real-time processing. Experimental results show that the speed of panoramic image stitching can be improved by dispersing the computational complexity, and smooth panoramic images can be generated.

Color and luminance corrections for panoramic image stitching

The article gives a detailed analysis of seamless image stitching methods into a panorama from an overlapping image set. Source images usually have varying colors and luminance due to cameras` position changing. Various approaches of blending and color correction algorithms for source images are presented. This paper illustrates the optimal technic for parallel evaluation of color correction coefficients in all overlapping areas. High quality of our blending method is confirmed by color and structure similarities based on PSNR and SSIM indexes accordingly.

Night panoramic image stitching algorithm based on cyclic symmetric structure

Aiming at the problem that the current stitching image has poor visual effect and low stitching efficiency when performing the night panoramic image stitching task, a night panoramic image stitching algorithm based on cyclic symmetric structure is proposed. In this algorithm, appropriate image acquisition method is used and the image obtained by the acquisition is smoothed, edge sharpened, geometrically corrected, etc. The position of the key point of the preprocessed image and the corresponding scale are determined by Gaussian function, and the direction value is assigned to the feature point to generate the feature descriptor, so as to realize the image edge feature extraction; on this basis, the edge feature points are hierarchically segmented according to the topological structure of the edge feature point set of target image, and the edge feature point registration of night panoramic image is completed; the cyclic symmetric structure is used to make the discrete Fourier transform of the target image, in order to reduce the amount of calculation; according to the gradient value and correlation coefficient of each pixel neighborhood in the overlapping region, the stitching line is searched to overcome the ghost image of the image after registration and realize seamless stitching of night panoramic image. The experimental results show that the proposed algorithm can effectively preserve the texture information of the original image while eliminating the smooth transition of the stitching seam, and at the same time, it has better stitching effect and stitching efficiency for the images under different conditions.

Panoramic Image Stitching based on Feature Extraction and Correlation

Panoramic Image Stitching based on Feature Extraction and Correlation

Panoramic Image Stitching for Arbitrarily Shaped Tunnel Lining Inspection

AbstractThis article presents a low‐cost panoramic image stitching system for tunnel lining inspection. The system can produce a high‐quality layout panorama of the target lining using photographs taken freely in a tunnel with a hand‐held camera and the tunnel design information as inputs. The three‐dimensional (3D) freeform shape corresponding to the tunnel design geometry is used as the warping surface for photograph rectification. A newly designed random sample consensus algorithm is used to estimate the freeform tunnel shape from the 3D reconstructed point cloud, which can perform the registration between point sets with different sizes. These processes can make full use of the geometry information of a real tunnel and the reconstructed scene; thus, the photographs can be precisely rectified, and a planar motion stitching can composite them together. Two field applications demonstrate that the system can create a tunnel layout panorama with sufficient accuracy in tunnel lining inspection and that it is applicable to noncircular‐shaped tunnels.

Efficient Video Panoramic Image Stitching Based on an Improved Selection of Harris Corners and a Multiple-Constraint Corner Matching

Video panoramic image stitching is extremely time-consuming among other challenges. We present a new algorithm: (i) Improved, self-adaptive selection of Harris corners. The successful stitching relies heavily on the accuracy of corner selection. We fragment each image into numerous regions and select corners within each region according to the normalized variance of region grayscales. Such a selection is self-adaptive and guarantees that corners are distributed proportional to region texture information. The possible clustering of corners is also avoided. (ii) Multiple-constraint corner matching. The traditional Random Sample Consensus (RANSAC) algorithm is inefficient, especially when handling a large number of images with similar features. We filter out many inappropriate corners according to their position information, and then generate candidate matching pairs based on grayscales of adjacent regions around corners. Finally we apply multiple constraints on every two pairs to remove incorrectly matched pairs. By a significantly reduced number of iterations needed in RANSAC, the stitching can be performed in a much more efficient manner. Experiments demonstrate that (i) our corner matching is four times faster than normalized cross-correlation function (NCC) rough match in RANSAC and (ii) generated panoramas feature a smooth transition in overlapping image areas and satisfy real-time human visual requirements.

A Fast Image Stitching Algorithm via Multiple-Constraint Corner Matching

Video panoramic image stitching is in general challenging because there is small overlapping between original images, and stitching processes are therefore extremely time consuming. We present a new algorithm in this paper. Our contribution can be summarized as a multiple-constraint corner matching process and the resultant faster image stitching. The traditional Random Sample Consensus (RANSAC) algorithm is inefficient, especially when stitching a large number of images and when these images have quite similar features. We first filter out many inappropriate corners according to their position information. An initial set of candidate matching-corner pairs is then generated based on grayscales of adjacent regions around each corner. Finally we apply multiple constraints, e.g., their midpoints, distances, and slopes, on every two candidate pairs to remove incorrectly matched pairs. Consequently, we are able to significantly reduce the number of iterations needed in RANSAC algorithm so that the panorama stitching can be performed in a much more efficient manner. Experimental results demonstrate that (i) our corner matching is three times faster than normalized cross-correlation function (NCC) rough match in traditional RANSAC algorithm and (ii) panoramas generated from our algorithm feature a smooth transition in overlapping image areas and satisfy human visual requirements.

New algorithms for convex cost tension problem with application to computer vision

Motivated by various applications to computer vision, we consider the convex cost tension problem, which is the dual of the convex cost flow problem. In this paper, we first propose a primal algorithm for computing an optimal solution of the problem. Our primal algorithm iteratively updates primal variables by solving associated minimum cut problems. We show that the time complexity of the primal algorithm is O ( K ⋅ T ( n , m ) ) , where K is the range of primal variables and T ( n , m ) is the time needed to compute a minimum cut in a graph with n nodes and m edges. We then develop an improved version of the primal algorithm, called the primal–dual algorithm, by making good use of dual variables in addition to primal variables. Although its time complexity is the same as that of the primal algorithm, we can expect a better performance in practice. We finally consider an application to a computer vision problem called the panoramic image stitching.

Automatic Panoramic Image Stitching using Invariant Features

This paper concerns the problem of fully automated panoramic image stitching. Though the 1D problem (single axis of rotation) is well studied, 2D or multi-row stitching is more difficult. Previous approaches have used human input or restrictions on the image sequence in order to establish matching images. In this work, we formulate stitching as a multi-image matching problem, and use invariant local features to find matches between all of the images. Because of this our method is insensitive to the ordering, orientation, scale and illumination of the input images. It is also insensitive to noise images that are not part of a panorama, and can recognise multiple panoramas in an unordered image dataset. In addition to providing more detail, this paper extends our previous work in the area (Brown and Lowe, 2003) by introducing gain compensation and automatic straightening steps.

Panoramic imaging—a review

Panoramic imaging has important implications in robotics, computer vision and virtual reality. This paper reviews representative work in the design and development of 2D/3D panoramic image capturing systems, the advancement of auto-calibration, registration and corresponding techniques, stereo vision, 3D reconstruction and image-based rendering. The paper discusses the above work within four parts of the panoramic imaging process: capturing system, image processing for panoramic imaging, image stitching and 3D reconstruction, image-based rending and visualisation. The design and development of a panoramic system pays careful attention to the following issues: image capturing, image registration, camera calibration, feature extraction, image understanding and image stitching. The objective of this review paper is to summarise and compare some of the methods in the various stages and identify research topics and applications, which are at the forefront of this exciting and challenge field.