Scale Invariant Feature Transform Keypoints Research Articles

Entropy-Based and Weighted Selective SIFT Clustering as an Energy Aware Framework for Supervised Visual Recognition of Man-Made Structures

Using local invariant features has been proven by published literature to be powerful for image processing and pattern recognition tasks. However, in energy aware environments, these invariant features would not scale easily because of their computational requirements. Motivated to find an efficient building recognition algorithm based on scale invariant feature transform (SIFT) keypoints, we present in this paper uSee, a supervised learning framework which exploits the symmetrical and repetitive structural patterns in buildings to identify subsets of relevant clusters formed by these keypoints. Once an image is captured by a smart phone, uSee preprocesses it using variations in gradient angle- and entropy-based measures before extracting the building signature and comparing its representative SIFT keypoints against a repository of building images. Experimental results on 2 different databases confirm the effectiveness of uSee in delivering, at a greatly reduced computational cost, the high matching scores for building recognition that local descriptors can achieve. With only 14.3% of image SIFT keypoints, uSee exceeded prior literature results by achieving an accuracy of 99.1% on the Zurich Building Database with no manual rotation; thus saving significantly on the computational requirements of the task at hand.

Generic Object Recognition Using Graph Embedding into A Vector Space

This paper describes a method for generic object recognition using graph structural expression. In recent years, generic object recognition by computer is finding extensive use in a variety of fields, including robotic vision and image retrieval. Conventional methods use a bag-of-features (BoF) approach, which expresses the image as an appearance fre-quency histogram of visual words by quantizing SIFT (Scale-Invariant Feature Transform) features. However, there is a problem associated with this approach, namely that the location information and the relationship between keypoints (both of which are important as structural information) are lost. To deal with this problem, in the proposed method, the graph is constructed by connecting SIFT keypoints with lines. As a result, the keypoints maintain their relationship, and then structural representation with location information is achieved. Since graph representation is not suitable for statistical work, the graph is embedded into a vector space according to the graph edit distance. The experiment results on two image datasets of multi-class showed that the proposed method improved the recognition rate.

Full Object Boundary Detection by Applying Scale Invariant Features in A Region Merging Segmentation Algorithm

Object detection is a fundamental task in computer vision and has many applications in image processing. This paper proposes a new approach for object detection by applying scale invariant feature transform (SIFT) in an automatic segmentation algorithm. SIFT is an invariant algorithm respect to scale, translation and rotation. The features are very distinct and provide stable keypoints that can be used for matching an object in different images. At first, an object is trained with different aspects for finding best keypoints. The object can be recognized in the other images by using achieved keypoints. Then, a robust segmentation algorithm is used to detect the object with full boundary based on SIFT keypoints. In segmentation algorithm, a merging role is defined to merge the regions in image with the assistance of keypoints. The results show that the proposed approach is reliable for object detection and can extract object boundary well.

A fast image registration approach based on SIFT key-points applied to super-resolution

An accurate image registration is a fundamental stage in many image processing problems. In this paper, a new and fast registration approach based on scale invariant feature transform (SIFT) key-points, under Euclidean transformation model, is proposed. The core idea of the proposed method is estimation of rotation angle and vertical and horizontal shifts using averaging of differences of SIFT key-point pairs locations. The method is simple but requires some tuning modules for accurate estimation. Orientation modification and compensation and shift compensation are some of the proposed modules. The proposed method is fast, about ive times faster than RANSAC method for model parameters estimation. The accuracy of the proposed method is compared with some popular registration methods. Various comparisons have been done with LIVE database images with known motion vectors. The experimental results over two real video sequences show the high performance of the proposed algorithm in a super-resolution application.

Super-resolution Reconstruction for Multi-resolution Image Sequence

A blind super resolution (SR) image reconstruction algorithm based on scale invariant feature transform (SIFT) and image registration is proposed for multi-resolution image sequence taken in various focal lengths. First, SIFT keypoints in images are extracted. Then keypoint descriptors are matched initially under the criterion of vectorial angle cosine and outliers of matches are eliminated by random sample consensus (RANSAC) algorithm to improve registration accuracy. And registered low-resolution (LR) images are mapped onto a high-resolution (HR) grid according to their transform parameters. Finally, space pixels are filled in by a pixel reliability weighted algorithm to reconstruct the image with a higher resolution. Experimental results show that the proposed algorithm can estimate scaling factors accurately and it is effective in affine transformation and is robust to registration errors within a certain range. The algorithm can essentially improve the resolution of multi-resolution image sequence with relatively satisfactory reconstruction result especially under the condition when the number of low-resolution image frames is too small and available information for reconstruction is seriously insufficient.

Robust Object Tracking by Particle Filter with Scale Invariant Features

Few literatures employ SIFT (scale-invariant feature transform) for tracking because it is time-consuming. However, we found that SIFT can be adapted to real-time tracking by employing it on a subarea of the whole image. In this paper the particle filter based method exploits SIFT features to handle challenging scenarios such as partial occlusions, scale variations and moderate deformations. As proposed in our method, not a brute-force feature extraction in the whole image, we firstly extract SIFT keypoints in the object search region only for once, through matching SIFT features between object search region and object template, the number of matched keypoints is obtained, which is utilized to compute the particle weights. Finally, we can obtain an optimal estimate to object location by the particle filter framework. Comparative experiments with quantitative evaluations are provided, which indicate that the proposed method is both robust and faster.

Tracking video objects with feature points based particle filtering

For intelligent video surveillance, the adaptive tracking of multiple moving objects is still an open issue. In this paper, a new multi-object tracking method based on video frames is proposed. A type of particle filtering combined with the SIFT (Scale Invariant Feature Transform) is proposed for motion tracking, where SIFT key points are treated as parts of particles to improve the sample distribution. Then, a queue chain method is adopted to record data associations among different objects, which could improve the detection accuracy and reduce the computational complexity. By actual road tests and comparisons, the system tracks multi-objects with better performance, e.g., real time implementation and robust against mutual occlusions, indicating that it is effective for intelligent video surveillance systems.

Robust Spatiotemporal Matching of Electronic Slides to Presentation Videos

We describe a robust and efficient method for automatically matching and time-aligning electronic slides to videos of corresponding presentations. Matching electronic slides to videos provides new methods for indexing, searching, and browsing videos in distance-learning applications. However, robust automatic matching is challenging due to varied frame composition, slide distortion, camera movement, low-quality video capture, and arbitrary slides sequence. Our fully automatic approach combines image-based matching of slide to video frames with a temporal model for slide changes and camera events. To address these challenges, we begin by extracting scale-invariant feature-transformation (SIFT) keypoints from both slides and video frames, and matching them subject to a consistent projective transformation (homography) by using random sample consensus (RANSAC). We use the initial set of matches to construct a background model and a binary classifier for separating video frames showing slides from those without. We then introduce a new matching scheme for exploiting less distinctive SIFT keypoints that enables us to tackle more difficult images. Finally, we improve upon the matching based on visual information by using estimated matching probabilities as part of a hidden Markov model (HMM) that integrates temporal information and detected camera operations. Detailed quantitative experiments characterize each part of our approach and demonstrate an average accuracy of over 95% in 13 presentation videos.

Airport Detection From Large IKONOS Images Using Clustered SIFT Keypoints and Region Information

This letter presents a new method for airport detection from large high-spatial-resolution IKONOS images. To this end, we describe airport by a set of scale-invariant feature transform (SIFT) keypoints and detect it using an improved SIFT matching strategy. After obtaining SIFT matched keypoints, to both discard the redundant matched points and locate the possible regions of candidates that contain the target, a novel region-location algorithm is proposed, which exploits the clustering information from matched SIFT keypoints, as well as the region information extracted through the image segmentation. Finally, airport recognition is achieved by applying the prior knowledge to the candidate regions. Experimental results show that the proposed approach outperforms the existing algorithms in terms of detection accuracy.

Iterative filtering of SIFT keypoint matches for multi-view registration in Distributed Video Coding

Multi-view registration is an essential step in order to generate the side information for multi-view Distributed Video Coding. As stated in our previous work (Ciobanu and Corte-Real, Multimed Tools Appl 48(3):411---436, 2010) it can be achieved by SIFT (scale-invariant feature transform) generated keypoint matches. The registration accuracy is vital for the adequate generation of side information and it directly depends on the reliable match of possibly all the available point to point correlations between two complete-overlapped views. We propose a solution to this problem based on iterative filtering of SIFT-generated keypoint matches, using the Hough transform and block matching. It aims the generic, real-life and constraint-free scenarios having an arbitrarily close angle between the two views. Practical results show an overall significant reduction of the outliers while maintaining a high rate of correct matches.

2P1-D23 抵抗回路網を用いた実時間SIFT特徴量抽出視覚システム

A vision system that extracts SIFT (scale-invariant feature transform) features in real time was developed. In order to realize real-time processing, the system employed a resistive network and FPGA (field-programmable gate array) circuits. The gaussian filtering required for extracting the SIFT key points was processed by the resistive network instantaneously. The gradient of the image required for describing the SIFT features calculated in the FPGA circuits efficiently. The system developed here was successful in detecting corresponding points of objects with different sizes in real-time.

Scene matching algorithm for SAR images based on SIFT features

According to the characteristic of Synthetic Aperture Radar(SAR) images,a new scene matching algorithm for SAR images based on Scale Invariant Feature Transform(SIFT) features was proposed.Firstly,SIFT keypoints of realtime images and reference images were extracted efficiently using improved SIFT feature descriptor.Then ratio of distance and Random Sample Consensus(RANSAC) were performed to guarantee the stability of matching points.Finally,transformation parameters between realtime and reference images were computed by reliable matching points.The experimental results demonstrate that our approach is fast,reliable,efficient and robust.

Urban-Area and Building Detection Using SIFT Keypoints and Graph Theory

Very high resolution satellite images provide valuable information to researchers. Among these, urban-area boundaries and building locations play crucial roles. For a human expert, manually extracting this valuable information is tedious. One possible solution to extract this information is using automated techniques. Unfortunately, the solution is not straightforward if standard image processing and pattern recognition techniques are used. Therefore, to detect the urban area and buildings in satellite images, we propose the use of scale invariant feature transform (SIFT) and graph theoretical tools. SIFT keypoints are powerful in detecting objects under various imaging conditions. However, SIFT is not sufficient for detecting urban areas and buildings alone. Therefore, we formalize the problem in terms of graph theory. In forming the graph, we represent each keypoint as a vertex of the graph. The unary and binary relationships between these vertices (such as spatial distance and intensity values) lead to the edges of the graph. Based on this formalism, we extract the urban area using a novel multiple subgraph matching method. Then, we extract separate buildings in the urban area using a novel graph cut method. We form a diverse and representative test set using panchromatic 1-m-resolution Ikonos imagery. By extensive testings, we report very promising results on automatically detecting urban areas and buildings.

Intelligent Sensing Systems for Rescue Robots: Landmark Identification and Three-Dimensional Mapping of Unknown Cluttered Urban Search and Rescue Environments

In this paper a unique landmark identification method is proposed for identifying large distinguishable landmarks for three-dimensional (3-D) visual simultaneous localization and mapping (SLAM) in unknown cluttered urban search and rescue (USAR) environments. The novelty of the method is the utilization of both 3-D (i.e., depth images) and 2-D images. By utilizing a scale-invariant feature transform (SIFT)-based approach and incorporating 3-D depth imagery, we can achieve more reliable and robust recognition and matching of landmarks from multiple images for 3-D mapping of the environment. Preliminary experiments utilizing the proposed methodology verify (i) its ability to identify clusters of SIFT keypoints in both 3-D and 2-D images for representation of potential landmarks in the scene, and (ii) the use of the identified landmarks in constructing a 3-D map of unknown cluttered USAR environments via 3-D visual SLAM.