Image Points Research Articles

Directional region-based feature point matching algorithm based on SURF.

Feature point matching is one of the fundamental tasks in binocular vision. It directly affects the accuracy and quality of 3D reconstruction. This study proposes a directional region-based feature point matching algorithm based on the SURF algorithm to improve the accuracy of feature point matching. First, same-name points are selected as the matching reference points in the left and right images. Then, the SURF algorithm is used to extract feature points and construct the SURF feature point descriptors. During the matching process, the location relationship between the query feature point and the reference point in the left image is directed to determine the corresponding matching region in the right image. Then, the matching is completed within this region based on Euclidean distance. Finally, the grid-based motion statistics algorithm is used to eliminate mismatches. Experimental results show that the proposed algorithm can substantially improve the matching accuracy and the number of valid matched points, particularly in the presence of a large amount of noise and interference. It also exhibits good robustness and stability.

A Preliminary Study of the Intellectual Image in Bulgakov's Works - Exemplified by Heart of a Dog

Mikhail Bulgakov is one of the renowned Soviet writers of the 20th century, whose works are noted for their imaginative and highly satirical nature. The intellectual image serves as one of the main character categories in the authors works. Bulgakov casts on these characters the ideology and social atmosphere of Soviet society in the early 20th century. Heart of a Dog is a milestone in Bulgakov's novel writing. The purpose of this essay is to take Professor Preobrazhensky as an example, to analyze the common points of the author's image of intellectuals who are extravagant, conservative, and obstinate, and to further analyze the tragic destiny of these intellectuals from the aspects of scientific ethics and personal worship.

Instance Segmentation Frustum–PointPillars: A Lightweight Fusion Algorithm for Camera–LiDAR Perception in Autonomous Driving

The fusion of camera and LiDAR perception has become a research focal point in the autonomous driving field. Existing image–point cloud fusion algorithms are overly complex, and processing large amounts of 3D LiDAR point cloud data requires high computational power, which poses challenges for practical applications. To overcome the above problems, herein, we propose an Instance Segmentation Frustum (ISF)–PointPillars method. Within the framework of our method, input data are derived from both a camera and LiDAR. RGB images are processed using an enhanced 2D object detection network based on YOLOv8, thereby yielding rectangular bounding boxes and edge contours of the objects present within the scenes. Subsequently, the rectangular boxes are extended into 3D space as frustums, and the 3D points located outside them are removed. Afterward, the 2D edge contours are also extended to frustums to filter the remaining points from the preceding stage. Finally, the retained points are sent to our improved 3D object detection network based on PointPillars, and this network infers crucial information, such as object category, scale, and spatial position. In pursuit of a lightweight model, we incorporate attention modules into the 2D detector, thereby refining the focus on essential features, minimizing redundant computations, and enhancing model accuracy and efficiency. Moreover, the point filtering algorithm substantially diminishes the volume of point cloud data while concurrently reducing their dimensionality, thereby ultimately achieving lightweight 3D data. Through comparative experiments on the KITTI dataset, our method outperforms traditional approaches, achieving an average precision (AP) of 88.94% and bird’s-eye view (BEV) accuracy of 90.89% in car detection.

Complete Region of Interest for Unconstrained Palmprint Recognition.

Unconstrained palmprint images have shown great potential for recognition applications due to their lower restrictions regarding hand poses and backgrounds during contactless image acquisition. However, they face two challenges: 1) unclear palm contours and finger-valley points of unconstrained palmprint images make it difficult to locate landmarks to crop the palmprint region of interest (ROI); and 2) large intra-class diversities of unconstrained palmprint images hinder the learning of intra-class-invariant palmprint features. In this paper, we propose to directly extract the complete palmprint region as the ROI (CROI) using the detection-style CenterNet without requiring the detection of any landmarks, and large intra-class diversities may occur. To address this, we further propose a palmprint feature alignment and learning hybrid network (PalmALNet) for unconstrained palmprint recognition. Specifically, we first exploit and align the multi-scale shallow representation of unconstrained palmprint images via deformable convolution and alignment-aware supervision, such that the pixel gaps of the intra-class palmprint CROIs can be minimized in shallow feature space. Then, we develop multiple triple-attention learning modules by integrating spatial, channel, and self-attention operations into convolution to adaptively learn and highlight the latent identity-invariant palmprint information, enhancing the overall discriminative power of the palmprint features. Extensive experimental results on four challenging palmprint databases demonstrate the promising effectiveness of both the proposed PalmALNet and CROI for unconstrained palmprint recognition.

Improved Demons algorithm for non-rigid medical image alignment

Abstract Medical image alignment is an important research field in medical image processing, which is widely used in clinical diagnosis and treatment, such as surgical navigation, lesion tracking, and treatment evaluation. In this paper, an improved algorithm combining the Demons algorithm and SIFT algorithm is proposed, which uses the SIFT algorithm to represent the feature points in non-rigid medical images as a scale space sequence and normalize the descriptors in the scale space sequence. Then, the two-way alignment strategy and multi-resolution strategy are introduced to improve the accuracy of Demons algorithm in the alignment of non-rigid medical images with complex deformation. The study shows that the improved Demons algorithm can achieve better alignment results when the weights of the feature matching terms are taken as −1 and 1, which makes the improved Demons algorithm with the addition of SIFT feature terms perform optimally. Alignment simulation experiments found that the MSE value of this paper’s improved algorithm is only 0.077. The alignment effect of non-rigid medical images is much better than the comparison algorithm and can maintain a shorter running time. The algorithm in this paper can effectively realize the non-rigid alignment of medical images, which provides a reference method for medical diagnosis and the effective formulation of treatment plans.

АНАЛИЗ ОТРАСЛЕВОЙ АНИЗОТРОПИИ В МЕЖДУНАРОДНОМ МАШИНОСТРОЕНИИ

Industry anisotropy, including in international mechanical engineering, is a poorly studied property of the industry system. At the same time, it is anisotropy that determines the nature of intra-industry competition. The aim of the study is to propose an approach for the analysis of industry anisotropy in the coordinate space “ resilience – efficiency” where a two–petalled R-lens will be formed, which is then clustered, with the allocation of seven reference clusters. The inclusion of such enterprise image points in one of the six selected clusters allows companies from the industry to assess their location, nearest competitors, risks, and methods of repositioning (if applicable). The study is original, it uses methods of fuzzy set theory and soft computing. A new technology for analyzing industry anisotropy based on clustering of R-lenses is proposed.

Space Imaging Point Source Detection and Characterization

Space Imaging Point Source Detection and Characterization

Estimation of planar angles from non-orthogonal imaging.

Photogrammetry-based methods are traditionally used to estimate the geometrical parameters using optical images. These methods employ specific equipment, computationally sophisticated and expensive algorithms, and utilize projective geometry to reconstruct real-life scenes up to a scale. In this work, we used a computationally less-expensive method for sparse reconstruction to estimate the planar angles using two-view geometry and linear algorithms from non-orthogonal images acquired by a smartphone camera. First, intrinsic camera parameters were determined. Next, scale-invariant feature transform was used to identify the correspondence points from each pair of images. Epipolar constraint was applied on all these points to determine the essential matrix using the eight-point algorithm. Thereafter, extrinsic camera parameters were estimated from the essential matrix and combined with the intrinsic matrix to get the camera projection matrix. Finally, linear triangulation was used to get the sparse point cloud representing the scene. Planar angles were estimated by backprojecting the chosen image points and applying simple vector algebra on the obtained 3D points. The method was successful in estimating the planar angles in less than 10s on non-curved edges with an average error of 3% by using only ten images. Given the simplicity of methods used, this technique can be integrated into a smartphone for on-site measurements as well as large deformations.

SOFTWARE IMPLEMENTATION OF ALGORITHMS FOR SELECTING THE OUTLINES OF OBJECTS IMAGES IN INTELLECTUAL VIDEO SURVEILLANCE SYSTEMS

The rapid advancement in digital image acquisition and transmission technologies poses challenges in processing vast volumes of video information streams. Images serve as crucial sources of decision-making information across a wide range of tasks. Key objectives addressed by intelligent video surveillance systems include object identification, trajectory determination, object speed measurement, and real-time detection of critical events for securing premises. Among the primary operations in intelligent video surveillance systems is the extraction of object contours from images, as contours contain essential information for object recognition based on their shape. This approach excludes internal image points, significantly reducing the amount of processed information and enabling real-time image analysis. Contour analysis encompasses methods for selecting, describing, and processing image contours to describe, store, compare, and search for objects based on their external contours. This methodology effectively addresses fundamental challenges in pattern recognition, such as transferring, rotating, and scaling object images. The paper discusses prominent contour analysis methods and presents software implementations of algorithms for extracting object outlines in intelligent video surveillance systems. A promising future direction involves synthesizing algorithms that extract object contours using a two-scale statistical image model.

A comparative study of pose estimation algorithms for visual navigation in autonomous robots

Autonomous navigation is a research field that gives mobile robots the capacity to perform various tasks without human assistance. Autonomous navigation based on visual sensors can be used in GPS denied environments. Vision-based navigation performs feature detection, matching, and pose estimation using camera images. This paper presents a new approach to autonomous navigation for mobile robots using a Color-based Image Segmentation and Centroid Detection algorithm instead of traditional feature detection algorithms. The algorithm intentionally matches features across images using known feature points and uses conventional techniques such as Epipolar Geometry and Perspective-N-Points algorithms for camera pose estimation. The study includes camera calibration to estimate intrinsic parameters and their physical unit conversion ensuring accurate measurements. Experimental datasets are used to analyze the performance of the Epipolar geometry, Perspective-3-Point, and Efficient-Perspective-n-Point based pose estimation algorithms. To enhance accuracy, the P3P algorithm is modified to consider combinations of image points for pose estimation. The paper concludes with a comparative analysis between the original P3P algorithm and the modified version, providing valuable insights into their respective performances. Overall, the paper aims to provide a comparison of different pose estimation algorithms used for visual navigation. Keywords: pose estimation, visual navigation, camera calibration, perspective-n-point, efficient pnp, epipolar geometry Abbreviations PnP, perspective-n-point; P3P, perspective-3-point; EPnP, efficient perspective-n-point; SLAM, simultaneous localization and mapping; VO, visual odometry; GPS, global positioning system; SURF, speeded up robust features; SIFT, scale-invariant feature transform; EKF, extended kalman filter; RGB, red-green-blue; HSV, hue- saturation-value; CNN, convolutional neural network

A Robust Machine Learning Model for Diabetic Retinopathy Classification.

Ensemble learning is a process that belongs to the artificial intelligence (AI) field. It helps to choose a robust machine learning (ML) model, usually used for data classification. AI has a large connection with image processing and feature classification, and it can also be successfully applied to analyzing fundus eye images. Diabetic retinopathy (DR) is a disease that can cause vision loss and blindness, which, from an imaging point of view, can be shown when screening the eyes. Image processing tools can analyze and extract the features from fundus eye images, and these corroborate with ML classifiers that can perform their classification among different disease classes. The outcomes integrated into automated diagnostic systems can be a real success for physicians and patients. In this study, in the form image processing area, the manipulation of the contrast with the gamma correction parameter was applied because DR affects the blood vessels, and the structure of the eyes becomes disorderly. Therefore, the analysis of the texture with two types of entropies was necessary. Shannon and fuzzy entropies and contrast manipulation led to ten original features used in the classification process. The machine learning library PyCaret performs complex tasks, and the empirical process shows that of the fifteen classifiers, the gradient boosting classifier (GBC) provides the best results. Indeed, the proposed model can classify the DR degrees as normal or severe, achieving an accuracy of 0.929, an F1 score of 0.902, and an area under the curve (AUC) of 0.941. The validation of the selected model with a bootstrap statistical technique was performed. The novelty of the study consists of the extraction of features from preprocessed fundus eye images, their classification, and the manipulation of the contrast in a controlled way.

ANALYSIS OF CALIBRATION ERRORS IN AUTOMOBILE CONTROL TELEVISION SYSTEM

Camera calibration is a critical method for 3D measurement applications based on 2D images. During calibration, internal camera parameters such as principal point and focal length are determined. The principal point is the intersection of the camera's optical axis and the image plane, while the focal length is measured from the lens center to the principal point.This article theoretically investigates calibration errors in two reference planes considering various conditions, such as shifts in the reference plane and changes in focal lengths. Errors in determining the coordinates of reference points in images were used to evaluate these calibration errors.The error in estimating the focal length and principal point is formulated using analytical equations, and the results are compared with simulation outcomes to validate the effectiveness of the proposed formulas. The research reveals that calibration errors arise due to shifts in the reference plane and changes in focal lengths. The obtained results are crucial for enhancing camera calibration methods and improving the accuracy of 3D measurements based on 2D images.This article extends the understanding of camera calibration errors and provides new theoretical approaches for their assessment. The research findings may be beneficial for scientists and practitioners working in the fields of computer vision, image processing, and 3D measurements.Further research in this area may contribute to the development of new calibration methods and approaches that will improve the performance of automotive systems and ensure high accuracy and reliability in the future.

Preoperative Imaging Evaluation of Endometrial Cancer in FIGO 2023.

The staging of endometrial cancer is based on the International Federation of Gynecology and Obstetrics (FIGO) staging system according to the examination of surgical specimens, and has revised in 2023, 14 years after its last revision in 2009. Molecular and histological classification has incorporated to new FIGO system reflecting the biological behavior and prognosis of endometrial cancer. Nonetheless, the basic role of imaging modalities including ultrasound, computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography, as a preoperative assessment of the tumor extension and also the evaluation points in CT and MRI imaging are not changed, other than several point of local tumor extension. In the field of radiology, it has also undergone remarkable advancement through the rapid progress of computational technology. The application of deep learning reconstruction techniques contributes the benefits of shorter acquisition time or higher quality. Radiomics, which extract various quantitative features from the images, is also expected to have the potential for the quantitative prediction of risk factors such as histological types and lymphovascular space invasion, which is newly included in the new FIGO system. This article reviews the preoperative imaging diagnosis in new FIGO system and recent advances in imaging analysis and their clinical contributions in endometrial cancer. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 3.

Mobile Robot Vision Image Feature Recognition Method Based on Machine Vision

In order to improve the efficiency and accuracy of mobile robot visual image feature recognition, a mobile robot visual image feature recognition method based on machine vision is proposed in this paper. Firstly, the development of mobile robot vision is analyzed, and the specific functions of robot visual feature recognition method are designed; Then, the Fourier series method is used to collect the mobile robot visual image, and the matrix associated with the autocorrelation function is calculated according to the Harris algorithm to complete the edge feature extraction of the mobile robot visual image; SIFT feature points of mobile robot visual image are classified, and mobile robot visual image feature recognition is realized through machine vision. The experimental results show that when the number of images is 600, the accuracy of image feature recognition and the loss value of image edge feature extraction of this method are 96.98% and 6.38%, respectively, and the number of iterations is 500. The time of visual image feature recognition of this method is only 3 minutes; The method has the lowest error mean and error variance under different noise conditions. This method can effectively improve the efficiency and accuracy of image feature recognition.

Feature Scalar Field Grid-Guided Optical-Flow Image Matching for Multi-View Images of Asteroid

Images captured by deep space probes exhibit large-scale variations, irregular overlap, and remarkable differences in field of view. These issues present considerable challenges for the registration of multi-view asteroid sensor images. To obtain accurate, dense, and reliable matching results of homonymous points in asteroid images, this paper proposes a new scale-invariant feature matching and displacement scalar field-guided optical-flow-tracking method. The method initially uses scale-invariant feature matching to obtain the geometric correspondence between two images. Subsequently, scalar fields of coordinate differences in the x and y directions are constructed based on this correspondence. Next, interim images are generated using the scalar field grid. Finally, optical-flow tracking is performed based on these interim images. Additionally, to ensure the reliability of the matching results, this paper introduces three methods for eliminating mismatched points: bidirectional optical-flow tracking, vector field consensus, and epipolar geometry constraints. Experimental results demonstrate that the proposed method achieves a 98% matching correctness rate and a root mean square error of 0.25 pixels. By combining the advantages of feature matching and optical-flow field methods, this approach achieves image homonymous point matching results with precision and density. The matching method exhibits robustness and strong applicability for asteroid images with cross-scale, large displacement, and large rotation angles.

Adaptive learning point cloud and image diversity feature fusion network for 3D object detection

3D object detection is a critical task in the fields of virtual reality and autonomous driving. Given that each sensor has its own strengths and limitations, multi-sensor-based 3D object detection has gained popularity. However, most existing methods extract high-level image semantic features and fuse them with point cloud features, focusing solely on consistent information from both sensors while ignoring their complementary information. In this paper, we present a novel two-stage multi-sensor deep neural network, called the adaptive learning point cloud and image diversity feature fusion network (APIDFF-Net), for 3D object detection. Our approach employs the fine-grained image information to complement the point cloud information by combining low-level image features with high-level point cloud features. Specifically, we design a shallow image feature extraction module to learn fine-grained information from images, instead of relying on deep layer features with coarse-grained information. Furthermore, we design a diversity feature fusion (DFF) module that transforms low-level image features into point-wise image features and explores their complementary features through an attention mechanism, ensuring an effective combination of fine-grained image features and point cloud features. Experiments on the KITTI benchmark show that the proposed method outperforms state-of-the-art methods.

Detecting delamination defects in CFRP plates using nonlinear defect index of air-coupled Lamb waves and adaptively weighted imaging algorithm

The air-coupled ultrasonic technique is capable of detecting defects in in-service CFRP plates and ensuring their application safety. Traditional air-coupled ultrasonic methods often rely on the linear defect index, which is not effective in characterizing small-size defects. Additionally, the scanning step length completely limits their imaging spatial resolution, resulting in the contradiction between imaging spatial resolution and detection efficiency. To address the above problems, the nonlinear defect index and the adaptively weighted imaging algorithm are proposed. The nonlinear defect index uses the relatively nonlinear coefficient of the Lamb wave to enhance the ability to detect small-size defects. Considering the beam width, the adaptively weighted imaging algorithm constructs the relationship between any imaging point and all scanning paths. At this time, the imaging spatial resolution can be set arbitrarily, eliminating the dependence on the scanning step length. The experimental results demonstrate that the proposed nonlinear defect index can characterize the small-size defect more accurately than the linear defect index. When the scanning step length is increased to improve detection efficiency, the adaptively weighted imaging algorithm can achieve better imaging spatial resolution compared to the traditional defect probability imaging algorithm. For the small-size defect with a diameter of 10 mm, the proposed method has an area detection error of only 7.8 %, whereas the traditional method has an error of 22.4 %. The proposed method is promising to detect small-size defects of in-service CFRP plates in the aircraft skin.

SEMANTIC ENRICHMENT OF 3D POINT CLOUDS USING 2D IMAGE SEGMENTATION

Abstract. 3D point cloud segmentation is computationally intensive due to the lack of inherent structural information and the unstructured nature of the point cloud data, which hinders the identification and connection of neighboring points. Understanding the structure of the point cloud data plays a crucial role in obtaining a meaningful and accurate representation of the underlying 3D environment. In this paper, we propose an algorithm that builds on existing state-of-the-art techniques of 2D image segmentation and point cloud registration to enrich point clouds with semantic information. DeepLab2 with ResNet50 as backbone architecture trained on the COCO dataset is used for indoor scene semantic segmentation into several classes like wall, floor, ceiling, doors, and windows. Semantic information from 2D images is propagated along with other input data, i.e., RGB images, depth images, and sensor information to generate 3D point clouds with semantic information. Iterative Closest Point (ICP) algorithm is used for the pair-wise registration of consecutive point clouds and finally, optimization is applied using the pose graph optimization on the whole set of point clouds to generate the combined point cloud of the whole scene. 3D point cloud of the whole scene contains pseudo-color information which denotes the semantic class to which each point belongs. The proposed methodology use an off-the-shelf 2D semantic segmentation deep learning model to semantically segment 3D point clouds collected using handheld mobile LiDAR sensor. We demonstrate a comparison of the accuracy achieved compared to a manually segmented point cloud on an in-house dataset as well as a 2D3DS benchmark dataset.

Improving prestack time migration by introducing a new velocity-related parameter: Parameter picking and 3D real data application

Prestack time migration (PSTM), a commonly used tool for seismic imaging, has been widely applied in 3D seismic data processing. However, the conventional PSTM algorithms use only one effective velocity parameter (i.e., root-mean-square [rms] velocity) for each imaging point, which may not be accurate when stronger lateral variations occur in seismic velocities. In this paper, we introduce a new parameter called the velocity variation factor that considers velocity variations in inhomogeneous media to improve PSTM. This new parameter, together with the rms velocity, describes the propagation Green’s function at an imaging point with two effective parameters rather than one effective parameter as in conventional PSTMs. This provides a more accurate traveltime calculation for the wave propagating through media with moderate lateral velocity variation. Unlike the conventional bending-ray PSTM, the additional effective parameter is fully independent of the rms velocities. We estimate the two effective parameters at each imaging point by flattening the neighboring image gathers with a global optimization algorithm. The objective function is built at each imaging point using a selective crosscorrelation-based time shift, which can quantitatively describe the slight bending of events in the local migrated gathers regardless of the quality of the gathers. We estimate the two effective parameters using the very fast simulated annealing algorithm and multiscale approach, thus avoiding the local minimum caused by the noises in the migrated gathers. We apply our two-parameter PSTM to a real 3D land data set to demonstrate its industrial applicability. A comparison of the new imaging result with the conventional prestack depth migration also is presented.

MMCPP: A MULTI-MODAL CONTRASTIVE PRE-TRAINING MODEL FOR PLACE REPRESENTATION BASED ON THE SPATIO-TEMPORAL FRAMEWORK

Abstract. The concept of "place" is crucial for understanding geographical environments from a human perspective. Place representation learning involves converting places into numerical low-dimensional dense vectors and is a fundamental procedure for artificial intelligence in geography (GeoAI). However, most studies ignore multi-level distance constraints and spatial proximity interactions that enable behavioral interactions between places. Furthermore, representing the temporal characteristics of these interactions in trajectory sequences poses a challenge for natural language processing and other field techniques. In addition, most existing methods rely on all modalities from inputs as they use joint training to integrate multiple modalities. To address these issues, we propose a Multi-Modal Contrastive Pre-training model for Place representation (MMCPP). Our model consists of three encoders that capture corresponding place attributes across different modalities, including point of interests (POIs), images, and trajectories. The trajectory encoder, named RodtFormer, takes fine-grained spatio-temporal trajectories as input and leverages self-attention with rotary temporal interval position embedding to simulate dynamic spatial and behavioral proximity interactions between places. By using a coordinated pre-training framework, MMCPP independently encodes place representations across different modalities and improves model reusability. We verify the effectiveness of our model on a taxi trajectory dataset using the location prediction task at next n seconds, including 30 seconds(s), 180(s), 300(s). Our results demonstrate that compared to existing embedding methods, our model is capable of learning higher-quality position representations during pre-training, leading to improved performance on downstream tasks.