Set Of Feature Points Research Articles

Optical Flow Approach Followed by SVM Classification Model to Recognize Abnormal Behavior of a Crowd

A many of researches have been carried out in the field of the crowd behavior recognition system. Recognizing crowd behavior in videos is most challenging and occlusions because of irregular human movement. This paper gives an overview of optical flow model along with the SVM (Support Vector Machine) classification model. This proposed approach evaluates sudden changes in motion of an event and classifies that event to a category: Normal and Abnormal. Geometric means of location, direction, and displacement of the feature points of each frame are estimated. Harris corner Detector is used in each frame for tracking a set of feature points. Proposed approach is very effective in real time scenario like public places where security is most important. After analyzing result ROC curve (receiver operating characteristics) is plotted which gives classification accuracy. We also presented frame level comparison with Ground truth and social force model (SFM) techniques. Our proposed approach is giving a promising result compare to all state of art methods.

Guided Locality Preserving Feature Matching for Remote Sensing Image Registration

Feature matching, which refers to establishing reliable correspondences between two sets of feature points, is a critical prerequisite in feature-based image registration. This paper proposes a simple yet surprisingly effective approach, termed as guided locality preserving matching, for robust feature matching of remote sensing images. The key idea of our approach is merely to preserve the neighborhood structures of potential true matches between two images. We formulate it into a mathematical model, and derive a simple closed-form solution with linearithmic time and linear space complexities. This enables our method to accomplish the mismatch removal from thousands of putative correspondences in only a few milliseconds. To handle extremely large proportions of outliers, we further design a guided matching strategy based on the proposed method, using the matching result on a small putative set with a high inlier ratio to guide the matching on a large putative set. This strategy can also significantly boost the true matches without sacrifice in accuracy. Experiments on various real remote sensing image pairs demonstrate the generality of our method for handling both rigid and nonrigid image deformations, and it is more than two orders of magnitude faster than the state-of-the-art methods with better accuracy, making it practical for real-time applications.

Gray level co-occurrence matrix feature based object tracking in thermal infrared imagery

Object tracking plays a vital role in many computer vision systems applications, such as video surveillance, robotics, 3-D image reconstruction, medical imaging, human computer interface, etc. In many proposed approaches, feature-based object tracking is widely used due to its accuracy. Feature extraction and feature correspondence are two main components of feature-based object tracking. In our proposed method, we have used gray level co-occurrence matrix (GLCM) features for object tracking in thermal imagery. As spatial resolution of the thermal sensor is fairly coarse, it also implies that temperature scales are close but may not exactly be the same, which indicates the presence of mutually related pixels or group of pixels. The GLCM texture analysis is based on assumption that the texture information of an image is an average spatial relationship between the gray tones in the image. Thus, this similarity in spatial resolution properties makes GLCM features suitable for object tracking in thermal infrared imagery. Initially, the target blobs to be tracked are provided by object detection stage. Then, for a given target blob in a frame, we first calculate GLCM feature points and then find corresponding features in the next successive frame. The sum of squared differences between two feature point sets is calculated to find feature correspondence between two frames for object tracking. Simultaneously, the codebook of the center of the blobs for prediction of the target candidate region in the next frame is maintained in order to have robust object tracking under occlusions. GLCM-based object tracking in thermal imagery outperforms the color or LBP-based mean-shift approach. This algorithm is also able to track objects in split and merge condition. The accuracy of this algorithm also depends on the object detection stage, such as Kalman tracking.

A vessel segmentation method for serialized cerebralvascular DSA images based on spatial feature point set of rotating coordinate system

Cerebrovascular pathology is one of the main fatal diseases which seriously affect the human's health. Extracting the accurate image of cerebral vascular tissue is the key of clinical diagnosis. However, the motion artifacts in DSA images seriously affected the quality of vascular subtraction image. In this paper, an automatic and accurate segmentation method is presented to extract the vascular region in the live image of brain. Firstly, a coarse registration for the live image and the mask image is implemented. And then, the SIFT algorithm is utilized to detect geometrical feature points in the serialized subtraction images. After that, a spatial model of rotating coordinate system and a calculative strategy of contextual information are designed to eliminate the error feature points. Finally, based on a dynamic threshold method, the blood vessel image can be obtained by region growing. The context information in the adjacent subtraction images is fully used. The experimental result shows that the segmented cerebral vascular image is satisfactory. This method can provide accurate vessel image data for the clinical operation based on DSA interventional therapy.

An Automatic Evaluation Platform for Feature Matching Algorithms Based on an Orbital Optical Pushbroom Stereo Imaging System

Thanks to the high robustness of feature-based matching algorithms, they can be applied in remote sensing (RS) applications with complex image changes. However, evaluating feature matching algorithms on RS images is still challenging, because creating ground truth matching data sets of RS images costs a lot of both computing time and human operator time. Therefore, in this letter, we present an evaluation platform for simulating RS ground truth data sets of feature-points correspondences based on a customizable orbital optical pushbroom stereo imaging system. With the help of the proposed platform, evaluating feature matching algorithms could be fully automatic and customized. The performance of three state-of-the-art feature matching algorithms based on local transformation constraint is evaluated and discussed on the proposed platform with comprehensive experiments. The evaluation results of the platform are also compared with the manual evaluation results of 10 pairs of real RS stereo images. The evaluation results show that the proposed platform indeed offers an efficient way for evaluating RS feature matching algorithms.

A Novel Multi-resolution Representation for Streaming Time Series

Along with the coming of IoT (Internet of things) era, massive numbers of instruments and applications in various fields are continuously producing oceans of time series stream data, which could be characterized by its large amount, high dimensionality and continuity nature. In order to carry out different kinds of data mining tasks (similarity search, classification, clustering, prediction etc.) based on streaming time series efficiently and effectively, segmentation and representation which segment a streaming time series into several subsequences and provide more compact representation for the raw data, should be done as the first step. With the virtue of solid theoretical foundations, piecewise linear representation (PLR) has been gained success in yielding more compact representation and fewer segments, however, the current state of art PLR methods have their own flaws. In this paper, we propose a novel online time series segmentation algorithm called continuous segmentation and multi-resolution representation algorithm based on turning points (CSMR_TP), which partitions the streaming time series by a set of temporal feature points and represents the time series flexibly. Our method can not only generate more accurate approximation than the state-of-the-art of PLR algorithm, but also represent the streaming time series in a more flexible way to meet the diverse needs of users. Extensive experiments on different kinds of typical time series datasets have been conducted to demonstrate the superiorities of our method.

A New Framework for the Integrative Analytics of Intravascular Ultrasound and Optical Coherence Tomography Images

The integrative analysis of multimodal medical images plays an important role in the diagnosis of coronary artery disease by providing additional comprehensive information that cannot be found in an individual source image. Intravascular ultrasound (IVUS) and optical coherence tomography (IV-OCT) are two imaging modalities that have been widely used in the medical practice for the assessment of arterial health and the detection of vascular lumen lesions. IV-OCT has a high resolution and poor penetration, while IVUS has a low resolution and high detection depth. This paper proposes a new approach for the fusion of intravascular ultrasound and optical coherence tomography pullbacks to significantly improve the use of those two types of medical images. It also presents a new two-phase multimodal fusion framework using a coarse-to-fine registration and a wavelet fusion method. In the coarse-registration process, we define a set of new feature points to match the IVUS image and IV-OCT image. Then, the improved quality image is obtained based on the integration of the mutual information of two types of images. Finally, the matched registered images are fused with an approach based on the new proposed wavelet algorithm. The experimental results demonstrate the performance of the proposed new approach for significantly enhancing both the precision and computational stability. The proposed approach is shown to be promising for providing additional information to enhance the diagnosis and enable a deeper understanding of atherosclerosis.

Semantic Segmentation of Human Model Using Heat Kernel and Geodesic Distance

A novel approach of 3D human model segmentation is proposed, which is based on heat kernel signature and geodesic distance. Through calculating the heat kernel signature of the point clouds of human body model, the local maxima of thermal energy distribution of the model is found, and the set of feature points of the model is obtained. Heat kernel signature has affine invariability which can be used to extract the correct feature points of the human model in different postures. We adopt the method of geodesic distance to realize the hierarchical segmentation of human model after obtaining the semantic feature points of human model. The experimental results show that the method can overcome the defect of geodesic distance feature extraction. The human body models with different postures can be obtained with the model segmentation results of human semantic characteristics.

Estimation of projection matrices from a sparse set of feature points for 3D tree reconstruction from multiple images

3D reconstruction of trees is an important task for tree analysis but the most affordable approach to capture real objects is with a camera. Although, there already exist methods for 3D reconstruction of trees from multiple photographs, they mostly handle only self-standing trees captured at narrow angles. In fact, dense feature detection and matching is in most cases only the first step of the reconstruction and requires a large set of features and high similarity between individual pictures. However, capturing trees in the orchard is in most cases possible only at wider angles between the individual pictures and with overlapping branches from other trees, which prevents reliable feature matching. We introduce a new approach for estimating projection matrices to produce 3D point clouds of trees from multiple photographs. By manually relating a smaller number of points on images to reference objects, we substitute the missing dense set of features. We assign to each image a projection matrix and minimize the projection error between the images and reference objects using simulated annealing. Thereby, we produce correct projection matrices for further steps in 3D reconstruction. Our approach is tested on a simple application for 3D reconstruction of trees to produce a 3D point cloud. We analyze convergence rates of the optimization and show that the proposed approach can produce feasible projection matrices from a sufficiently large set of feature points. In the future, this approach will be a part of a complete system for tree reconstruction and analysis.

Gaussian field consensus: A robust nonparametric matching method for outlier rejection

In this paper, we propose a robust method, called Gaussian Field Consensus (GFC), for outlier rejection from given putative point set matching correspondences. Finding correct correspondences (inliers) is a key component in many computer vision and pattern recognition tasks, and the goal of outlier (mismatch) rejection is to fit the transformation function that maps one feature point set to another. Our GFC starts by inputting a putative correspondence set which is contaminated by many outliers, and the main task of our GFC is to identify the underlying true correspondences from outliers. Then we formulate this challenging problem by Gaussian Field nonparametric matching model which bases on the exponential distance loss and kernel method in a reproducing kernel Hilbert space. Next, We introduce a local linear constraint based on the regularization theory to preserve the topological structure of the feature points. Moreover, the sparse approximation is used to reduce the search space, in this way, we can handle a large number of points easily. Finally, we test the GFC method on several real image datasets in the presence of outliers, where the experimental results show that our proposed method outperforms current state-of-the-art methods in most test scenarios.

Fuzzy correspondences guided Gaussian mixture model for point set registration

Recovering correspondences and estimating transformations are challenging to solve in the presence of outliers and other degradations for non-rigid point set registration. In this paper, we propose a new methodology based on fuzzy correspondences guided Gaussian Mixture Model (GMM) to solve the registration problem between two or more feature point sets. We first construct a mixture model to represent the moving point set, where inliers are formulated as a mixture of Gaussian, and outliers are formulated as an additional uniform distribution. Then we use the context-aware shape descriptor to assign the points and obtain the fuzzy correspondences. On the one hand, the soft-assignment is used to classify the weight of inliers and outliers. On the other hand, by using the fuzzy correspondences, the Gaussian elements in the mixture model can be estimated to increase the registration accuracy efficiently. In this way, the optimal transformation between two point sets can be expressed by representation theorem and solved by EM algorithm iteratively in a high-dimensional feature space (i.e., reproducing kernel Hilbert space, RKHS). Extensive experiments on synthesized and real datasets demonstrate the proposed method performs favorably against the state-of-the-art methods in most tested scenarios.

A ROBUST METHOD FOR STEREO VISUAL ODOMETRY BASED ON MULTIPLE EUCLIDEAN DISTANCE CONSTRAINT AND RANSAC ALGORITHM

Abstract. Visual Odometry (VO) is a critical component for planetary robot navigation and safety. It estimates the ego-motion using stereo images frame by frame. Feature points extraction and matching is one of the key steps for robotic motion estimation which largely influences the precision and robustness. In this work, we choose the Oriented FAST and Rotated BRIEF (ORB) features by considering both accuracy and speed issues. For more robustness in challenging environment e.g., rough terrain or planetary surface, this paper presents a robust outliers elimination method based on Euclidean Distance Constraint (EDC) and Random Sample Consensus (RANSAC) algorithm. In the matching process, a set of ORB feature points are extracted from the current left and right synchronous images and the Brute Force (BF) matcher is used to find the correspondences between the two images for the Space Intersection. Then the EDC and RANSAC algorithms are carried out to eliminate mismatches whose distances are beyond a predefined threshold. Similarly, when the left image of the next time matches the feature points with the current left images, the EDC and RANSAC are iteratively performed. After the above mentioned, there are exceptional remaining mismatched points in some cases, for which the third time RANSAC is applied to eliminate the effects of those outliers in the estimation of the ego-motion parameters (Interior Orientation and Exterior Orientation). The proposed approach has been tested on a real-world vehicle dataset and the result benefits from its high robustness.

Facial expression synthesis with direction field preservation based mesh deformation and lighting fitting based wrinkle mapping

Nowadays, facial expression synthesis is widely used in expression simulation, recognition and animation. While a variety of works available in literature are 3D based, these algorithms usually require face matching and trimming, are thus time consuming. In this work, an automatic algorithm for expression synthesis in 2D space is proposed, which mainly consists of three stages.The optimum matching of three sets of feature points on the faces of source neutral (Fsn), source expression (Fse) and target neutral (Ftn) are obtained in the first stage. Different components on the target face are deformed by learning from not only the displacements but also the geometry shape of face Fse in the second stage. In the last stage, the details of the source expression are mapped onto the corresponding positions on the target face by fitting of the lighting differences. Experimental results on expression synthesis with large geometry deformation and lighting difference show that the proposed algorithm is able to accurately preserve the geometry deformation, and the synthesized expressions are visually realistic.

Feature point matching based on ABC-NCC algorithm

Feature point matching is the process of finding an optimal spatial transformation that aligns two arbitrary sets of feature points. It is one of the most fundamental problems in the computer vision domain and is frequently used in object recognition, image registration, camera self-calibration, and so on. Critical to most feature point matching techniques is the determination of correspondence between spatially localized feature points within each image. Moreover, there can be many feature points in either set that have no counterparts in the other. A robust and effective method for feature point matching is thus required and is still a challenge. In this work, an artificial bee colony (ABC) with a normalized cross-correlation (NCC) algorithm called “ABC-NCC” for feature point matching is presented. In this proposed method, both the size and the orientation of the correlation window used for calculating the NCC are determined according to the scale and the rotation direction of the interest points, which are optimized by the ABC algorithm. Experimental results obtained by our method show that the proposed approach works well for feature point matching and outperforms existing algorithms.

Sufficient Image Appearance Transfer Combining Color and Texture

Traditional color transfer methods can achieve satisfactory results for transferring the color style from a reference image to a source image, provided that the source image shares the similar color mood with the reference image. However, color transfer solutions are always sensitive to color category, which cannot generate natural results when the contents of the reference image and the source image are different, e.g., a lush tree in the reference image and a bare tree in the source image. In this situation, it is insufficient only through color transfer to transfer the appearance from the reference image to the source image only through color transfer, since other information such as texture should also be considered. To obtain sufficient appearance transfer results, we propose a new image appearance transfer method combining both color and texture features. Given a source image and a reference image, our method starts with feature detection and matching between the source image and the reference image. Then, we design a new method for expanding feature point sets to get texture transfer mark (TTM) and color transfer mark (CTM). TTM and CTM will guide texture transfer and color transfer, respectively. We demonstrate our appearance transfer algorithm between quantities of images and compare with results of existing methods. Experiment results show that given only a single reference image, our approach can produce more sufficient appearance transfer results than the state-of-the-art algorithms.

Slow Ground Moving Object Detection in Rotating Complex Background

Based on background modeling that employs a nonlinear model, a new approach for slow moving object detection in rotating complex background is proposed. First, the rotational motion pattern is determined and the complexity of the background is evaluated. Then background modeling of rotational motion is conducted through the following three steps: (1) retrieving a set of matching feature points and obtaining feature point motion vector field; (2) filtering the vector field and obtaining precise matching feature point set; (3) estimating nonlinear model parameters and reconstructing background motion vector field. Next, background compensated image is obtained by applying pixel interpolation. Last, moving objects are detected by applying threshold segmentation and morphological processing to difference images and searching for complete object contour according to region growing rule. The main test video sequence consists of 1200 frames with a resolution of 720 × 560 pixels. We successfully detected objects with an inter-frame velocity as low as 1 pixel per frame. The false alarm rate, misdetection rate, and the accuracy rate of detection are 2%, 2.6% and 95.4%, respectively. The detection of each frame takes 38 ms, meeting the real-time requirement of object detection in videos with a frame rate of 25 frames per second.

Automatic Wheat Leaf Rust Detection and Grading Diagnosis via Embedded Image Processing System

Wheat leaf rust is one of the major fungal diseases that makes severe drop in the wheat production. With the desire for rapid and accurate identification of disease, real-time access to the degree of that and timely measures, a wheat leaf diseases detection system based on embedded image recognition technology is designed. The system adopted the ARM9 processor with the embedded Linux platform as the main body, and the program is developed in the Qt integrated environment. At first, the captured clear disease picture of wheat leaf rust was transformed into G single channel gray image of RGB model. Second, based on exploration Sobel operator method, vertical edges detection were implemented on the gray image, eliminate the background of image and extracts binary feature point set of disease spot. Third, the noisy points in the point set is further filtered out by flood filling algorithm. Finally, the area ratio of disease spots and leaf is calculated to get the precise diagnosis of disease level. It has been verified that the recognition rate reaches 96.2% and accuracy rated reaches 92.3% with the method of image processing, which is approximately equal to the result of human vision. This system can be used as agricultural robot to inspect in the field, realizing the intelligentization in detection, identification, diagnosis and classification of crop disease.

Higher-Order Graph Principles towards Non-Rigid Surface Registration.

This paper casts surface registration as the problem of finding a set of discrete correspondences through the minimization of an energy function, which is composed of geometric and appearance matching costs, as well as higher-order deformation priors. Two higher-order graph-based formulations are proposed under different deformation assumptions. The first formulation encodes isometric deformations using conformal geometry in a higher-order graph matching problem, which is solved through dual-decomposition and is able to handle partial matching. Despite the isometry assumption, this approach is able to robustly match sparse feature point sets on surfaces undergoing highly anisometric deformations. Nevertheless, its performance degrades significantly when addressing anisometric registration for a set of densely sampled points. This issue is rigorously addressed subsequently through a novel deformation model that is able to handle arbitrary diffeomorphisms between two surfaces. Such a deformation model is introduced into a higher-order Markov Random Field for dense surface registration, and is inferred using a new parallel and memory efficient algorithm. To deal with the prohibitive search space, we also design an efficient way to select a number of matching candidates for each point of the source surface based on the matching results of a sparse set of points. A series of experiments demonstrate the accuracy and the efficiency of the proposed framework, notably in challenging cases of large and/or anisometric deformations, or surfaces that are partially occluded.

A Robust Method for Ego-Motion Estimation in Urban Environment Using Stereo Camera.

Visual odometry estimates the ego-motion of an agent (e.g., vehicle and robot) using image information and is a key component for autonomous vehicles and robotics. This paper proposes a robust and precise method for estimating the 6-DoF ego-motion, using a stereo rig with optical flow analysis. An objective function fitted with a set of feature points is created by establishing the mathematical relationship between optical flow, depth and camera ego-motion parameters through the camera’s 3-dimensional motion and planar imaging model. Accordingly, the six motion parameters are computed by minimizing the objective function, using the iterative Levenberg–Marquard method. One of key points for visual odometry is that the feature points selected for the computation should contain inliers as much as possible. In this work, the feature points and their optical flows are initially detected by using the Kanade–Lucas–Tomasi (KLT) algorithm. A circle matching is followed to remove the outliers caused by the mismatching of the KLT algorithm. A space position constraint is imposed to filter out the moving points from the point set detected by the KLT algorithm. The Random Sample Consensus (RANSAC) algorithm is employed to further refine the feature point set, i.e., to eliminate the effects of outliers. The remaining points are tracked to estimate the ego-motion parameters in the subsequent frames. The approach presented here is tested on real traffic videos and the results prove the robustness and precision of the method.

Spatial Matching of Animated Meshes

AbstractThis paper presents a new technique which makes use of deformation and motion properties between animated meshes for finding their spatial correspondences. Given a pair of animated meshes exhibiting a semantically similar motion, we compute a sparse set of feature points on each mesh and compute spatial correspondences among them so that points with similar motion behavior are put in correspondence. At the core of our technique is our new, dynamic feature descriptor named AnimHOG, which encodes local deformation characteristics. AnimHOG is ob‐tained by computing the gradient of a scalar field inside the spatiotemporal neighborhood of a point of interest, where the scalar values are obtained from the deformation characteristic associated with each vertex and at each frame. The final matching has been formulated as a discreet optimization problem that finds the matching of each feature point on the source mesh so that the descriptor similarity between the corresponding feature pairs as well as compatibility and consistency as measured across the pairs of correspondences are maximized. Consequently, reliable correspondences can be found even among the meshes of very different shape, as long as their motions are similar. We demonstrate the performance of our technique by showing the good quality of matching results we obtained on a number of animated mesh pairs.