Keypoint Extraction Methods Research Articles

Remote Sensing Image Ship Matching Utilising Line Features for Resource-Limited Satellites

The existing image matching methods for remote sensing scenes are usually based on local features. The most common local features like SIFT can be used to extract point features. However, this kind of methods may extract too many keypoints on the background, resulting in low attention to the main object in a single image, increasing resource consumption and limiting their performance. To address this issue, we propose a method that could be implemented well on resource-limited satellites for remote sensing images ship matching by leveraging line features. A keypoint extraction strategy called line feature based keypoint detection (LFKD) is designed using line features to choose and filter keypoints. It can strengthen the features at corners and edges of objects and also can significantly reduce the number of keypoints that cause false matches. We also present an end-to-end matching process dependent on a new crop patching function, which helps to reduce complexity. The matching accuracy achieved by the proposed method reaches 0.972 with only 313 M memory and 138 ms testing time. Compared to the state-of-the-art methods in remote sensing scenes in extensive experiments, our keypoint extraction method can be combined with all existing CNN models that can obtain descriptors, and also improve the matching accuracy. The results show that our method can achieve ∼50% test speed boost and ∼30% memory saving in our created dataset and public datasets.

Research on Fatigued-Driving Detection Method by Integrating Lightweight YOLOv5s and Facial 3D Keypoints.

In response to the problem of high computational and parameter requirements of fatigued-driving detection models, as well as weak facial-feature keypoint extraction capability, this paper proposes a lightweight and real-time fatigued-driving detection model based on an improved YOLOv5s and Attention Mesh 3D keypoint extraction method. The main strategies are as follows: (1) Using Shufflenetv2_BD to reconstruct the Backbone network to reduce parameter complexity and computational load. (2) Introducing and improving the fusion method of the Cross-scale Aggregation Module (CAM) between the Backbone and Neck networks to reduce information loss in shallow features of closed-eyes and closed-mouth categories. (3) Building a lightweight Context Information Fusion Module by combining the Efficient Multi-Scale Module (EAM) and Depthwise Over-Parameterized Convolution (DoConv) to enhance the Neck network's ability to extract facial features. (4) Redefining the loss function using Wise-IoU (WIoU) to accelerate model convergence. Finally, the fatigued-driving detection model is constructed by combining the classification detection results with the thresholds of continuous closed-eye frames, continuous yawning frames, and PERCLOS (Percentage of Eyelid Closure over the Pupil over Time) of eyes and mouth. Under the premise that the number of parameters and the size of the baseline model are reduced by 58% and 56.3%, respectively, and the floating point computation is only 5.9 GFLOPs, the average accuracy of the baseline model is increased by 1%, and the Fatigued-recognition rate is 96.3%, which proves that the proposed algorithm can achieve accurate and stable real-time detection while lightweight. It provides strong support for the lightweight deployment of vehicle terminals.

Optical and SAR Image Registration Based on the Phase Congruency Framework

The improved phase congruency (PC) algorithms have been successfully applied to optical and synthetic aperture radar (SAR) image registration since they are insensitive to nonlinear radiometric and geometric differences. However, most of the algorithms are sensitive to large-scale differences and rotation differences between optical and SAR images. To tackle this, we propose a PC framework to register optical and SAR images. It is compatible with large-scale and rotation invariance. Firstly, a multi-scale Harris keypoint extraction method based on the maximum moment of PC (named PC-Harris) is proposed. The scale space is constructed by combining PC with the log-Gabor filter. Secondly, we propose a PC model to construct the feature descriptors. The orientation and amplitude responses are obtained based on the PC model. Meanwhile, the novel descriptor is constructed based on the polar coordinate system and thus can handle the scale and rotation differences between optical and SAR images. Finally, outliers are removed by the fast sample consensus (FSC). The experiments conducted on several optical and SAR images verify the effectiveness of the proposed framework.

A Novel Copy–Move Forgery Detection Algorithm via Gradient-Hash Matching and Simplified Cluster-Based Filtering

Copy–move forgery is one of the most frequently used methods for producing fake digital images. Current algorithms for copy–move forgery detection (CMFD) cannot combine high accuracy and fast speed. Motivated by the observation, we propose a novel CMFD algorithm whose workflow is as follows. First, we use a keypoint-extraction method with the lowest contrast threshold to extract more keypoints from the input image. Second, a new technique, gradient-hash matching, finds pairs of similar keypoints quickly and effectively using a hash table, where the hash value is computed using gradients of keypoints. Subsequently, a new method called simplified cluster-based filtering exploits the density pattern of keypoints in the copy–move regions to remove false matching keypoint pairs. Finally, image matting is applied to indicate the forgery regions vividly. Extensive experiments show that not only the new algorithm is better than the state-of-the-art algorithms in terms of computation correctness, but also its computation time is drastically less. Commonly only about half time is needed. The relative time saving is even higher when images are larger. Different algorithms modules are compared through experiments to choose the best combination.

A Novel Fusion Model of Hand-Crafted Features With Deep Convolutional Neural Networks for Classification of Several Chest Diseases Using X-Ray Images

With the continuing global pandemic of coronavirus (COVID-19) sickness, it is critical to seek diagnostic approaches that are both effective and rapid to limit the number of people infected with the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The results of recent research suggest that radiological images include important information related to COVID-19 and other chest diseases. As a result, the use of deep learning (DL) to assist in the automated diagnosis of chest diseases may prove useful as a diagnostic tool in the future. In this study, we propose a novel fusion model of hand-crafted features with deep convolutional neural networks (DCNNs) for classifying ten different chest diseases such as COVID-19, lung cancer (LC), atelectasis (ATE), consolidation lung (COL), tuberculosis (TB), pneumothorax (PNET), edema (EDE), pneumonia (PNEU), pleural thickening (PLT), and normal using chest X-rays (CXR). The method that has been suggested is split down into three distinct parts. The first step involves utilizing the Info-MGAN network to perform segmentation on the raw CXR data to construct lung images of ten different chest diseases. In the second step, the segmented lung images are fed into a novel pipeline that extracts discriminatory features by using hand-crafted techniques such as SURF and ORB, and then these extracted features are fused to the trained DCNNs. At last, various machine learning (ML) models have been used as the last layer of the DCNN models for the classification of chest diseases. Comparison is made between the performance of various proposed architectures for classification, all of which integrate DCNNs, key point extraction methods, and ML models. We were able to attain a classification accuracy of 98.20% for testing by utilizing the VGG-19 model with a softmax layer in conjunction with the ORB technique. Screening for COVID-19 and other lung ailments can be accomplished using the method that has been proposed. The robustness of the model was further confirmed by statistical analyses of the datasets using McNemar’s and ANOVA tests respectively.

Key point extraction method for spatial objects in high-resolution remote sensing images based on multi-hot cross-entropy loss

Abstract Extracting spatial objects and their key points from remote sensing images has attracted great attention of worldwide researchers in intelligent machine perception of the Earth’s surface. However, the key points of spatial objects (KPSOs) extracted by the conventional mask region-convolution neural network model are difficult to be sorted reasonably, which is a key obstacle to enhance the ability of machine intelligent perception of spatial objects. The widely distributed artificial structures with stable morphological and spectral characteristics, such as sports fields, cross-river bridges, and urban intersections, are selected to study how to extract their key points with a multihot cross-entropy loss function. First, the location point in KPSOs is selected as one category individually to distinguish morphological feature points. Then, the two categories of key points are arranged in order while maintaining internal disorder, and the mapping relationship between KPSOs and the prediction heat map is improved to one category rather than a single key point. Therefore, the predicted heat map of each category can predict all the corresponding key points at one time. The experimental results demonstrate that the prediction accuracy of KPSOs extracted by the new method is 80.6%, taking part area of Huai’an City for example. It is reasonable to believe that this method will greatly promote the development of intelligent machine perception of the Earth’s surface.

Research on a Point Cloud Registration Method of Mobile Laser Scanning and Terrestrial Laser Scanning

Mobile laser scanning can quickly and dynamically obtain a wide range of urban scene point clouds. However, due to factors such as occlusion and field of view limitation, it needs to be supplemented by terrestrial laser scanning. The acquisition methods and data quality of mobile point clouds and terrestrial point clouds are quite different, the target of urban scene point clouds is complex and diverse, and the corresponding feature is difficult to extract, so the point cloud fusion is difficult. To this end, a point cloud registration method of mobile and terrestrial scanning based on the target features of artificial ground objects is proposed. Firstly, the data features of mobile laser scanning point clouds and terrestrial laser scanning point clouds are analyzed, and the point clouds are diluted with equal density. Then, the artificial ground objects are extracted as the registration primitives to reduce the scene complexity, and the features of urban scenes and the features of point cloud eigenvalues and principal curvature attributes are analyzed. Combined with the octree voxel index, the multi-scale key point extraction method is constructed to extract the multi-scale key points of registration primitives. Finally, the key point constraint is used to improve the deficiencies of 4PCS (4-Points Congruent Sets) algorithm and ICP (Iterative Closest Point) algorithm to complete the registration of mobile and terrestrial point clouds in different road scenes. Experiments show that the point cloud registration accuracy can reach 2.6 cm, which provides a feasible method for high precision fusion of multi-platform laser point clouds.

Research on Point Cloud Registration Algorithm Based on Boundary Harris-3D Points and 4PCS

Abstract Point cloud registration based on the 4PCS+ICP algorithm will lead to many problems such as large registration error, low efficiency, and unstable running time, especially when it encounters large point cloud data, these problems will be more prominent, which greatly limits the application of the algorithm. Based on these shortcomings, we propose an optimized registration algorithm, called BH4PCS, to improve the applicability of the 4PCS algorithm. In our method, we first extract the boundary Harris-3D points through the edge detection algorithm and Harris-3D key point extraction method, then we use the 4PCS algorithm for point cloud coarse registration, and finally use KD-ICP to speed up the fine registration. After experimental verification and comparison with the existing artworks, our proposed algorithm registers the larger point cloud model by only using a small number of data points, optimizing the registration efficiency, accuracy, and operation stability of the 4PCS + ICP registration method, and has good robustness to outliers.

A deep learning based approach for automatic detection of COVID-19 cases using chest X-ray images

In this global pandemic situation of coronavirus disease (COVID-19), it is of foremost priority to look up efficient and faster diagnosis methods for reducing the transmission rate of the virus severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Recent research has indicated that radio-logical images carry essential information about the COVID-19 virus. Therefore, artificial intelligence (AI) assisted automated detection of lung infections may serve as a potential diagnostic tool. It can be augmented with conventional medical tests for tackling COVID-19. In this paper, we propose a new method for detecting COVID-19 and pneumonia using chest X-ray images. The proposed method can be described as a three-step process. The first step includes the segmentation of the raw X-ray images using the conditional generative adversarial network (C-GAN) for obtaining the lung images. In the second step, we feed the segmented lung images into a novel pipeline combining key points extraction methods and trained deep neural networks (DNN) for extraction of discriminatory features. Several machine learning (ML) models are employed to classify COVID-19, pneumonia, and normal lung images in the final step. A comparative analysis of the classification performance is carried out among the different proposed architectures combining DNNs, key point extraction methods, and ML models. We have achieved the highest testing classification accuracy of 96.6% using the VGG-19 model associated with the binary robust invariant scalable key-points (BRISK) algorithm. The proposed method can be efficiently used for screening of COVID-19 infected patients.

Feature extraction of overlapping hevea leaves: A comparative study

Automation of rubber tree clone classification has inspired research into new methods of leaf feature extraction. In current practice, rubber clone inspectors has been using several leaf features to identify clone types. One of the unique features of rubber tree leaf is palmate leaflets. This characteristic generates different leaflet positions, where the leaves are overlapping or separated. In this research, we propose keypoint extraction and line detection methods to extract shape and axil (angle between petioles) features of leaflet positions. The results of keypoint extraction methods, namely, SIFT, Harris, and FAST, were compared and discussed for shape feature extraction. Next, Hough transformation and boundary-tracing methods were compared to identify the suitable axil detection method. The evaluation result demonstrates the proper keypoint extraction method for shape context and the clear advantages of Hough Transformation in accuracy of angle detection.

3D SLAM in texture-less environments using rank order statistics

SUMMARYWe present a real time 3D SLAM system for texture-less scenes using only depth information provided by a low cost RGB-D sensor. The proposed method is based on a novel informative sampling scheme that extracts points carrying the most useful 3D information for registration. The aim of the proposed sampling technique is to informatively sample a point cloud into a subset of points based on their 3D information. The flatness of a point is measured by applying a rank order statistics based robust segmentation method to surface normals in its local vicinity. The extracted keypoints from sequential frames are then matched and a rank order statistics based robust estimator is employed to refine the matches and estimate a rigid-body transformation between the frames. Experimental evaluations show that the proposed keypoint extraction method is highly repeatable and outperforms the state of the art methods in terms of accuracy and repeatability. We show that the performance of the registration algorithm is also comparable to other well-known methods in texture-less environments.

Multiple Feature Extraction Techniques in Image Stitching

Image stitching is the process of combining two or more images with overlapping area to produce a panorama of input images. In order to improve performance of creation of panorama, approach that combine different keypoint extraction methods can be used. This paper proposes a methodology for image stitching process that combines various feature detection and extraction algorithms. First, image stitching will be done based on feature keypoint matches. Final image with seam will be blended with image blending technique. The paper summarizes 3 robust feature detection and extraction algorithms namely SURF, SIFT and MSER. Combined set of keypoints will be used for image transformation. According to proposed system, multiple feature extraction techniques can be used for image stitching which can build seamless panorama image. General Terms Image Processing, Image, Image stitching Algorithm, Feature extraction algorithm, Image blending