Accurate Feature Point Research Articles

A novel 3D reconstruction method of blast furnace burden surface based on virtual camera array

Accurate three-dimensional (3D) blast furnace burden surface topography is crucial for optimizing material distribution and furnace operation. However, harsh conditions within the furnace pose challenges to this 3D reconstruction, such as difficulties in matching feature points and sparse 3D point clouds. To overcome these challenges, we propose a 3D reconstruction method for the blast furnace burden surface using virtual camera array. Firstly, an ORB feature extraction and matching method based on bidirectional optical flow tracking is proposed to solve the impact of illumination changes and noise. Then, the virtual camera array is constructed to generate a sparse 3D point cloud from an image sequence. Finally, dense surface reconstruction of the burden surface is achieved based on the improved PMVS and the Poisson surface reconstruction method. Experimental results demonstrate that the proposed method can extract accurate feature points and reconstruct the accurate 3D topography of the burden surface.

River Surface Velocity Measurement for Rapid Levee Breach Emergency Response Based on DFP-P-LK Algorithm.

In recent years, the increasing frequency of climate change and extreme weather events has significantly elevated the risk of levee breaches, potentially triggering large-scale floods that threaten surrounding environments and public safety. Rapid and accurate measurement of river surface velocities is crucial for developing effective emergency response plans. Video image velocimetry has emerged as a powerful new approach due to its non-invasive nature, ease of operation, and low cost. This paper introduces the Dynamic Feature Point Pyramid Lucas-Kanade (DFP-P-LK) optical flow algorithm, which employs a feature point dynamic update fusion strategy. The algorithm ensures accurate feature point extraction and reliable tracking through feature point fusion detection and dynamic update mechanisms, enhancing the robustness of optical flow estimation. Based on the DFP-P-LK, we propose a river surface velocity measurement model for rapid levee breach emergency response. This model converts acquired optical flow motion to actual flow velocities using an optical flow-velocity conversion model, providing critical data support for levee breach emergency response. Experimental results show that the method achieves an average measurement error below 15% within the velocity range of 0.43 m/s to 2.06 m/s, demonstrating high practical value and reliability.

ICG signal denoising based on ICEEMDAN and PSO-VMD methods.

Impedance cardiography (ICG) plays a crucial role in clinically evaluating cardiac systolic and diastolic functions, along with various other cardiac parameters. However, its accuracy heavily depends on precisely identifying feature points reflecting cardiac function. Moreover, traditional signal processing techniques used to mitigate random noise and breathing artifacts may inadvertently distort the amplitude and temporal characteristics of ICG signals. To address this issue, this study investigates a noise and artifact elimination method based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and Particle Swarm Optimization-based Variational Mode Decomposition Algorithm (PSO-VMD). The goal is to preserve the amplitude and temporal features of ICG signals to ensure accurate feature point extraction and computation of associated cardiac parameters. Comparative analysis with signal processing methods employing various wavelet families and Ensemble Empirical Mode Decomposition (EEMD) in ICG signal processing applications reveals that the proposed method achieves superior signal-to-noise ratio (SNR) and lower root-mean-square error (RMSE), while demonstrating enhanced correlation and waveform consistency with the original signal.

PDE-Constrained Scale Optimization Selection for Feature Detection in Remote Sensing Image Matching

Feature detection and matching is the key technique for remote sensing image processing and related applications. In this paper, a PDE-constrained optimization model is proposed to determine the scale levels advantageous for feature detection. A variance estimation technique is introduced to treat the observation optical images polluted by additive zero-mean Gaussian noise and determine the parameter of a nonlinear scale space governed by the partial differential equation. Additive Operator Splitting is applied to efficiently solve the PDE constraint, and an iterative algorithm is proposed to approximate the optimal subset of the original scale level set. The selected levels are distributed more uniformly in the total variation sense and helpful for generating more accurate and robust feature points. The experimental results show that the proposed method can achieve about a 30% improvement in the number of correct matches with only a small increase in time cost.

YOLO-Weld: A Modified YOLOv5-Based Weld Feature Detection Network for Extreme Weld Noise

Weld feature point detection is a key technology for welding trajectory planning and tracking. Existing two-stage detection methods and conventional convolutional neural network (CNN)-based approaches encounter performance bottlenecks under extreme welding noise conditions. To better obtain accurate weld feature point locations in high-noise environments, we propose a feature point detection network, YOLO-Weld, based on an improved You Only Look Once version 5 (YOLOv5). By introducing the reparameterized convolutional neural network (RepVGG) module, the network structure is optimized, enhancing detection speed. The utilization of a normalization-based attention module (NAM) in the network enhances the network’s perception of feature points. A lightweight decoupled head, RD-Head, is designed to improve classification and regression accuracy. Furthermore, a welding noise generation method is proposed, increasing the model’s robustness in extreme noise environments. Finally, the model is tested on a custom dataset of five weld types, demonstrating better performance than two-stage detection methods and conventional CNN approaches. The proposed model can accurately detect feature points in high-noise environments while meeting real-time welding requirements. In terms of the model’s performance, the average error of detecting feature points in images is 2.100 pixels, while the average error in the world coordinate system is 0.114 mm, sufficiently meeting the accuracy needs of various practical welding tasks.

WiCRF: Weighted Bimodal Constrained LiDAR Odometry and Mapping With Robust Features

Accurate localization is a fundamental capability of autonomous driving systems, and LiDAR has been widely used for localization systems in recent years due to its high reliability and accuracy. In this paper, we propose a robust and accurate LiDAR SLAM, which innovates feature point extraction and motion constraint construction. For feature extraction, the proposed adaptive point roughness evaluation based on geometric scaling effectively improves the stability and accuracy of feature points (plane, line). Then, outliers are removed with a dynamic threshold filter, which improves the accuracy of outlier recognition. For motion constraint construction, the proposed weighted bimodal least squares is employed to optimize the relative pose between current frame and point map. The map stores both 3D coordinates and vectors (principal or normal vectors). Using vectors in current frame and point map, bimodal reprojection constraints are constructed. And all constraints are weighted according to the neighboring vector distribution in the map, which effectively reduces the negative impact of vector errors on registration. Our solution is tested in multiple datasets and achieve better performance in terms of accuracy and robustness.

Robust Keypoint Detection and Matching on Fisheye Images by Self-Supervised Learning.

Accurate image feature point detection and matching are essential to computer vision tasks such as panoramic image stitching and 3D reconstruction. However, ordinary feature point approaches cannot be directly applied to fisheye images due to their large distortion, which makes the ordinary camera model unable to adapt. To address such a problem, this paper proposes a self-supervised learning method for feature point detection and matching on fisheye images. This method utilizes a Siamese network to automatically learn the correspondence of feature points across transformed image pairs to avoid high annotation costs. Due to the scarcity of the fisheye image dataset, a two-stage viewpoint transform pipeline is also adopted for image augmentation to increase the data variety. Furthermore, this method adopts both deformable convolution and contrastive learning loss to improve the feature extraction and description of distorted image regions. Compared with traditional feature point detectors and matchers, this method has been demonstrated with superior performance on fisheye images.

Deep Learning-Based Signal Quality Assessment for Wearable ECGs

Nowadays, use of the dynamic electrocardiogram (ECG) has developed rapidly because of the wide application of wearable devices [1]–[3]. Most ECG-based diagnostic algorithms require that the ECG signal have a clear waveform and accurate feature points. However, the collected wearable ECG signal usually contains a certain amount of noise and causes many false alarms in the ECG analysis system [4], [5]. Thus, signal quality assessment (SQA) plays a prominent role in ruling out the ECG segments with poor signal quality [6]. Compared with traditional static ECG signals, dynamic wearable ECGs contain more noise, which brings greater challenges to disease detection algorithms [7]–[9]. These artifacts and noises in dynamic ECG signals can seriously affect the R-peaks detection, ECG beat extraction, ECG morphological feature extraction and the detection of noise peaks, resulting in frequent false alarms [10]. In 2008, Li et al. [11] proposed the bSQI signal quality indexes: comparison of two beat detectors on a single ECG lead. Liu et al. [12] generalized the two QRS wave complex (QRS) detectors-based bSQI to multiple QRS detectors-based bSQI (GbSQI) to improve the SQA performance. Liu et al. [8] proposed an efficient real-time SQA method for healthy subjects.

Infrared and Visible Image Registration Based on Automatic Robust Algorithm

Image registration is the base of subsequent image processing and has been widely utilized in computer vision. Aiming at the differences in the resolution, spectrum, and viewpoint of infrared and visible images, and in order to accurately register infrared and visible images, an automatic robust infrared and visible image registration algorithm, based on a deep convolutional network, was proposed. In order to precisely search and locate the feature points, a deep convolutional network is introduced, which solves the problem that a large number of feature points can still be extracted when the pixels of the infrared image are not clear. Then, in order to achieve accurate feature point matching, a rough-to-fine matching algorithm is designed. The rough matching is obtained by location orientation scale transform Euclidean distance, and then, the fine matching is performed based on the update global optimization, and finally, the image registration is realized. Experimental results show that the proposed algorithm has better robustness and accuracy than several advanced registration algorithms.

Remote sensing image registration based on the improved attention neighborhood consistency network

Image registration plays an important role in surface detection, aerial image classification, and satellite image fusion. However, the existing image registration frameworks pay less attention to local feature information. Additionally, such frameworks have insufficient extraction of important channel and spatial information and ambiguous matching. To address these issues, we propose an end-to-end remote sensing image registration framework based on the improved attention neighborhood consistency network. Our network improves the robustness of the rotation distortion region by employing an asymmetric convolution block in the feature extraction stage, which is augmented by two one-dimensional convolution kernels with square convolution kernels. Moreover, we use a 1 × 1 convolution to adjust the residual network channel to retain global information, realize feature reuse, and obtain multiscale image information. Next, the attention mechanism is improved by utilizing skip connections to resolve the problems of high resolution and image heterogeneity issues in remote sensing images. This allows the framework to quickly focus on important regional features and improve the network’s ability to distinguish and localize image features. In the feature matching stage, a bidirectional cross-correlation algorithm is used to establish the correspondence between the two pictures and match the corresponding points are matched. At the same time, the multilayer perceptron (MLP) structure is introduced into the neighborhood consensus network to eliminate the noise generated by mismatching. Further, it establishes a strong matching locality, prompts information aggregation at different positions and different channels, reduces registration deviation, and enhances matching robustness. The experimental results show that, overall, the algorithm outperforms comparable algorithms, extracting more accurate feature points and efficiently reducing the mismatch rate. The algorithm put forward effectively functions in a variety of situations, exhibiting high efficiency and high accuracy.

3D Static Point Cloud Registration by Estimating Temporal Human Pose at Multiview.

This paper proposes a new technique for performing 3D static-point cloud registration after calibrating a multi-view RGB-D camera using a 3D (dimensional) joint set. Consistent feature points are required to calibrate a multi-view camera, and accurate feature points are necessary to obtain high-accuracy calibration results. In general, a special tool, such as a chessboard, is used to calibrate a multi-view camera. However, this paper uses joints on a human skeleton as feature points for calibrating a multi-view camera to perform calibration efficiently without special tools. We propose an RGB-D-based calibration algorithm that uses the joint coordinates of the 3D joint set obtained through pose estimation as feature points. Since human body information captured by the multi-view camera may be incomplete, a joint set predicted based on image information obtained through this may be incomplete. After efficiently integrating a plurality of incomplete joint sets into one joint set, multi-view cameras can be calibrated by using the combined joint set to obtain extrinsic matrices. To increase the accuracy of calibration, multiple joint sets are used for optimization through temporal iteration. We prove through experiments that it is possible to calibrate a multi-view camera using a large number of incomplete joint sets.

The Estimation of Image Jacobian Matrix with Time-Delay Compensation

Time delay exists in image-based visual servo system, which will have a certain impact on the system control. To solve the impact of time delay, the time delay compensation of the object feature point image and the image Jacobian matrix is discussed in this paper. Some work is done in this paper: The estimation of the object feature point image under time delay is based on a proposed robust decorrelation Kalman filtering model, for the measurement vectors which cannot be obtained during time delay in the robust Kalman filtering model, a polynomial fitting method is proposed in which the selection of the polynomial includes the position, velocity and acceleration of the object feature point which impact the feature point trajectory, then the more accurate object feature point image can be obtained. From the estimated object feature point image under time delay, the more accurate image Jacobian matrix under time delay can be obtained. Simulation and experimental results verify the feasibility and superiority of this paper method.

3D Mesh Pre-Processing Method Based on Feature Point Classification and Anisotropic Vertex Denoising Considering Scene Structure Characteristics

3D mesh denoising plays an important role in 3D model pre-processing and repair. A fundamental challenge in the mesh denoising process is to accurately extract features from the noise and to preserve and restore the scene structure features of the model. In this paper, we propose a novel feature-preserving mesh denoising method, which was based on robust guidance normal estimation, accurate feature point extraction and an anisotropic vertex denoising strategy. The methodology of the proposed approach is as follows: (1) The dual weight function that takes into account the angle characteristics is used to estimate the guidance normals of the surface, which improved the reliability of the joint bilateral filtering algorithm and avoids losing the corner structures; (2) The filtered facet normal is used to classify the feature points based on the normal voting tensor (NVT) method, which raised the accuracy and integrity of feature classification for the noisy model; (3) The anisotropic vertex update strategy is used in triangular mesh denoising: updating the non-feature points with isotropic neighborhood normals, which effectively suppressed the sharp edges from being smoothed; updating the feature points based on local geometric constraints, which preserved and restored the features while avoided sharp pseudo features. The detailed quantitative and qualitative analyses conducted on synthetic and real data show that our method can remove the noise of various mesh models and retain or restore the edge and corner features of the model without generating pseudo features.

Feature Matching Based on Minimum Relative Motion Entropy for Image Registration

Accurate point matching is widely used, and it is a critical and challenging process in feature-based image registration. To improve feature matching accuracy on putative matches with heavy outliers and similar local structures, an accurate and robust feature point matching algorithm based on minimum relative motion entropy (MRME) is proposed, in which the relative motion between the putative matches and their K-nearest neighbors is formulated. Based on the relative motion clustering result, the relative motion entropy is defined to find the coincident relative motions. According to relative motions with MRME, the outliers are removed in a two-stage feature match strategy. With quasi-linear time complexity, outliers with random or irregular relative motion are removed efficiently and accurately, while inliers with coincident relative motion are retained. Three data sets with repetitive patterns, viewpoint changes, low overlapping areas, and local deformations are used to demonstrate the performance of the proposed algorithm. MRME is shown to be more robust and accurate than ten state-of-the-art feature matching algorithms.

Accurate feature point detection method exploiting the line structure of the projection pattern for 3D reconstruction.

The 3D imaging methods using a grid pattern can satisfy real-time applications since they are fast and accurate in decoding and capable of producing a dense 3D map. However, like the other spatial coding methods, it is difficult to achieve high accuracy as is the case for time multiplexing due to the effects of the inhomogeneity of the scene. To overcome those challenges, this paper proposes a convolutional-neural-network-based method of feature point detection by exploiting the line structure of the grid pattern projected. First, two specific data sets are designed to train the model to individually extract the vertical and horizontal stripes in the image of a deformed pattern. Then the predicted results of trained models with images from the test set are fused in a unique skeleton image for the purpose of detecting feature points. Our experimental results show that the proposed method can achieve higher location accuracy in feature point detection compared with previous ones.

Feature Point Matching Based on Local Relative Velocity Consensus

Feature matching is still a crucial and challenging problem in image processing. In this paper, a novel feature matching algorithm based on local relative velocity consensus (LRVC) is proposed to find two accurate matched feature points. To remove the outliers accurately and robustly, the relative velocity between the putative matches and their corresponding neighbors are exploited. Based on the consensus of relative velocity and the consensus of neighborhood elements, the similarity of each putative matches is evaluated. With a two iteration outlier removal strategy, the feature points are matched accurately and robustly. In the experiment, VGG dataset are used to verify the accuracy and robustness of the proposed method LRVC. The matching results indicate that our method is superior to three other classic feature matching methods.

Semantic segmentation guided feature point classification and seam fusion for image stitching

Image stitching can be employed to stitch images taken from different times, perspectives, or devices into a panorama with a wider view. However, the imaging specification of images to be stitched is strict. If the imaging specification is not satisfied, artefacts caused by inaccurate alignment and unnatural distortion will occur. Semantic segmentation can solve the classification problem at the pixel level; however, image stitching significantly depends on the accuracy of feature points. Therefore, this paper proposes an image stitching algorithm based on semantic segmentation to guide feature point classification and seam fusion. First, the images are recognized by a cascade semantic segmentation network, and the image feature points are classified. Thereafter, the corresponding homography transformations are calculated using different class feature points, and the best homography mapping for the entire target image is selected. Finally, a seam-cutting algorithm based on semantic segmentation is used to compute the seam, and a feathering Poisson fusion with distance transformation is used to eliminate artefacts and light differences. Experiments show that the algorithm can generate transitional natural and perceptual stitching results even under the influence of perspective and light differences.

Accuracy improvement of time-of-flight depth measurement by combination of a high-resolution color camera.

Time-of-flight (ToF) cameras can acquire the distance between the sensor and objects with high frame rates, offering bright prospects for ToF cameras in many applications. Low-resolution and depth errors limit the accuracy of ToF cameras, however. In this paper, we present a flexible accuracy improvement method for depth compensation and feature points position correction of ToF cameras. First, a distance-error model of each pixel in the depth image is established to model sinusoidal waves of ToF cameras and compensate for the measured depth data. Second, a more accurate feature point position is estimated with the aid of a high-resolution camera. Experiments evaluate the proposed method, and the result shows the root mean square error is reduced from 4.38 mm to 3.57 mm.

Research on Bidirectional Matching Algorithm of Variable Threshold SIFT Based on DBSCAN

The safe distance measurement of stacking in hazardous chemicals warehouses is an important factor to ensure the safety of hazardous chemicals storage. Binocular vision distance measurement is a very promising technology. Aiming at the key problems in that feature points matching in distance measurement is easily affected by illumination and feature similarity, and based on the degree of density, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering algorithm is proposed to realize Scale-invariant feature transform (SIFT) matching algorithm of variable thresholds in different regions of the image, and then adaptive neighborhood and bidirectional matching algorithms are used to further eliminate the mismatch points. The experimental results show that the matching rate of binocular distance measurement in hazardous chemicals warehouse is 68% and the accuracy of feature points is 98%.

Seam Feature Point Acquisition Based on Efficient Convolution Operator and Particle Filter in GMAW

Seam feature point acquisition is the premise of the intelligent welding process such as initial point guiding and seam tracking. However, conventional seam feature point acquisition methods based on geometric feature have shortcomings of poor flexibility and robustness. In this article, a seam feature point acquisition method based on efficient convolution operator (ECO) and particle filter (PF) is proposed, which could be applied to different weld types and could achieve fast and accurate seam feature point acquisition even under the interference of welding arc light and spatter noises. First, a structured light vision sensor is developed to acquire welding image. Second, the ECO algorithm is adopted to track the seam region and acquire seam feature point during gas metal arc welding process. Third, the state and measurement equations of the weld seam position are established, and PF is applied to improve seam feature point acquisition accuracy. Finally, a welding experiment system is built and a series of seam feature point acquisition experiments of butt joint, lap joint, and fillet joint are carried out to validate the performance of the proposed method. The experiment results demonstrate that the processing speed of the proposed method could reach up 35 Hz, and the seam feature point acquisition errors are smaller than 0.15 mm, which could meet the real-time and accuracy requirement for subsequent initial point guiding and seam tracking.