Line Feature Extraction Research Articles

Tightly coupled stereo vision-inertial odometry based on point and line feature

Abstract To improve the accuracy and robustness of visual simultaneous localization and mapping (SLAM) in low-texture environments, this paper proposes a robust and fast stereo vision inertial SLAM pose estimation method that combines point and line features with an inertial measurement unit (IMU). The method tightly couples visual point and line features with IMU constraints, forming a least-squares problem through the error of each constraint term for nonlinear optimization. To address the issues of over-segmentation and time consumption in traditional line segment detection (LSD) algorithms, an improved LSD algorithm is adopted to accelerate line feature extraction. This approach merges nearby line segments based on spatial geometric relationships and filters out invalid segments, improving the time efficiency of the algorithm. Finally, experiments conducted in low-texture environments demonstrate that our algorithm achieves high localization accuracy and robustness.

A Feature Line Extraction Method for Building Roof Point Clouds Considering the Grid Center of Gravity Distribution

A Feature Line Extraction Method for Building Roof Point Clouds Considering the Grid Center of Gravity Distribution

Step feature line extraction from large-scale point clouds of open-pit mine based on structural characteristics

High-precision step feature lines play a crucial role in open-pit mine design, production scheduling, mining volume calculations, road network planning, and slope maintenance. Compared with the feature lines of the geometric model, step feature lines are more irregular, complex, higher in density, and richer in detail. In this study, a novel technique for extracting step feature line from large-scale point clouds of open-pit mine by leveraging structural attributes, that is, SFLE_OPM (Step Feature Line Extraction for Open-Pit Mine), is proposed. First, we adopt the k-dimensional tree (KD-tree) resampling method to reduce the point-cloud density while retaining point-cloud features and utilize bilateral filtering for denoising. Second, we use Point Cloud Properties Network (PCPNET) to estimate the normal, calculate the slope and aspect, and then filter them. We then apply morphological operations to the step surface and obtain more continuous and smoother slope lines. In addition, we construct an Open-Pit Mine Step Feature Line (OPMSFL) dataset and benchmarked SFLE_OPM, achieving an accuracy score of 89.31% and true positive rate score of 80.18%. The results demonstrate that our method yields a higher extraction accuracy and precision than most of the existing methods. Our dataset is available at https://github.com/OPMDataSets/OPMSFL.

ULG-SLAM: A Novel Unsupervised Learning and Geometric Feature-Based Visual SLAM Algorithm for Robot Localizability Estimation

Indoor localization has long been a challenging task due to the complexity and dynamism of indoor environments. This paper proposes ULG-SLAM, a novel unsupervised learning and geometric-based visual SLAM algorithm for robot localizability estimation to improve the accuracy and robustness of visual SLAM. Firstly, a dynamic feature filtering based on unsupervised learning and moving consistency checks is developed to eliminate the features of dynamic objects. Secondly, an improved line feature extraction algorithm based on LSD is proposed to optimize the effect of geometric feature extraction. Thirdly, geometric features are used to optimize localizability estimation, and an adaptive weight model and attention mechanism are built using the method of region delimitation and region growth. Finally, to verify the effectiveness and robustness of localizability estimation, multiple indoor experiments using the EuRoC dataset and TUM RGB-D dataset are conducted. Compared with ORBSLAM2, the experimental results demonstrate that absolute trajectory accuracy can be improved by 95% for equivalent processing speed in walking sequences. In fr3/walking_xyz and fr3/walking_half, ULG-SLAM tracks more trajectories than DS-SLAM, and the ATE RMSE is improved by 36% and 6%, respectively. Furthermore, the improvement in robot localizability over DynaSLAM is noteworthy, coming in at about 11% and 3%, respectively.

The Extraction of Roof Feature Lines of Traditional Chinese Village Buildings Based on UAV Dense Matching Point Clouds

Traditional Chinese buildings serve as a carrier for the inheritance of traditional culture and national characteristics. In the context of rural revitalization, achieving the 3D reconstruction of traditional village buildings is a crucial technical approach to promoting rural planning, improving living environments, and establishing digital villages. However, traditional algorithms primarily target urban buildings, exhibiting limited adaptability and less ideal feature extraction performance for traditional residential buildings. As a result, guaranteeing the accuracy and reliability of 3D models for different types of traditional buildings remains challenging. In this paper, taking Jingping Village in Western Hunan as an example, we propose a method that combines multiple algorithms based on the slope segmentation of the roof to extract feature lines. Firstly, the VDVI and CSF algorithms are used to extract the building and roof point clouds based on the MVS point cloud. Secondly, according to roof features, village buildings are classified, and a 3D roof point cloud is projected into 2D regular grid data. Finally, the roof slope is segmented via slope direction, and internal and external feature lines are obtained after refinement through Canny edge detection and Hough straight line detection. The results indicate that the CSF algorithm can effectively extract the roofs of I-shaped, L-shaped, and U-shaped traditional buildings. The accuracy of roof surface segmentation based on slope exceeds 99.6%, which is significantly better than the RANSAC algorithm and the region segmentation algorithm. This method is capable of efficiently extracting the characteristic lines of roofs in low-rise buildings within traditional villages. It provides a reference method for achieving the high-precision modeling of traditional village architecture at a low cost and with high efficiency.

From lines to Polygons: Polygonal building contour extraction from High-Resolution remote sensing imagery

Automated extraction of polygonal building contours from high-resolution remote sensing images is important for various applications. However, it remains a difficult task to achieve automated extraction of polygonal buildings at the level of human delineation due to diverse building structures and imperfect image conditions. In this paper, we propose Line2Poly, an end-to-end approach that uses feature lines as geometric primitives to achieve polygonal building extraction by recovering topological relationships among these lines within an individual building. To extract building feature lines with precision, we adopt a two-stage strategy that combines Convolutional Neural Network (CNN) and transformer architectures. A CNN-based module extracts preliminary feature lines, which serve as positional priors for initializing positional queries in the subsequent transformer-based module. For polygonal building contour reconstruction, we devise a learnable polygon topology reconstruction module that predicts adjacency relationships among discrete lines, and integrates lines into building polygons. The resultant building polygons, based on feature lines, exhibit inherent regularity that aligns with manual labeling standards. Extensive experiments on the Vectorizing World Buildings dataset, the WHU aerial building dataset and the WHU-Mix (vector) dataset validate Line2Poly’s impressive performance in building feature line extraction and instance-level building detection. Moreover, Line2Poly’s predictions exhibit the highest level of concurrence with manual delineations, with over 83% agreement on the WHU aerial building test set and 68.7/59.7% on the WHU-Mix (vector) test set I and II, respectively.

Extraction of Roof Feature Lines Based on Geometric Constraints from Airborne LiDAR Data

Airborne LiDAR (Light Detection and Ranging) is an active Earth observing system, which can directly acquire high-accuracy and dense building roof data. Thus, airborne LiDAR has become one of the mainstream source data for building detection and reconstruction. The emphasis for building reconstruction focuses on the accurate extraction of feature lines. Building roof feature lines generally include the internal and external feature lines. Efficient extraction of these feature lines can provide reliable and accurate information for constructing three-dimensional building models. Most related algorithms adopt intersecting the extracted planes fitted by the corresponding points. However, in these methods, the accuracy of feature lines mostly depends on the results of plane extraction. With the development of airborne LiDAR hardware, the point density is enough for accurate extraction of roof feature lines. Thus, after acquiring the results of building detection, this paper proposed a feature lines extraction strategy based on the geometric characteristics of the original airborne LiDAR data, tracking roof outlines, normal ridge lines, oblique ridge lines and valley lines successively. The final refined feature lines can be obtained by normalization. The experimental results showed that our methods can achieve several promising and reliable results with an accuracy of 0.291 m in the X direction, 0.295 m in the Y direction and 0.091 m in the H direction for outlines extraction. Further, the internal feature lines can be extracted with reliable visual effects using our method.

Structural asymmetric convolution for wireframe parsing

Simultaneously extracting junctions and their corresponding line segments from images presents a promising approach to structural environment cognition. However, conventional methods employ square convolution for line feature extraction, resulting in the exclusion of long-range dependencies and the generation of suboptimal wireframe predictions. In this paper, we introduce an efficient and concise parsing method named Structural Asymmetric Convolution-based Wireframe Parser (SACWP). Taking advantage of the inherent similarities between structural asymmetric convolution and the predominant distribution of line segments in man-made environments, we propose a Structural Asymmetric Convolution module (SAC) that captures long-range contextual features while efficiently filtering out irrelevant information from neighboring pixels. Additionally, we introduce a feature aggregation module based on dilated convolution (DCFA) to seamlessly integrate contextual information from multiple receptive fields. We thoroughly evaluate our approach on the Wireframe and YorkUrban datasets, achieving preferable results of 69.3% and 29.7% msAP respectively. On the other hand, the promising results adequately demonstrate the effectiveness of SACWP to Wireframe Parsing task.

Simultaneous Vehicle Localization and Roadside Tree Inventory Using Integrated LiDAR-Inertial-GNSS System

Autonomous driving systems rely on a comprehensive understanding of the surrounding environment, and trees, as important roadside features, have a significant impact on vehicle positioning and safety analysis. Existing methods use mobile LiDAR systems (MLS) to collect environmental information and automatically generate tree inventories based on dense point clouds, providing accurate geometric parameters. However, the use of MLS systems requires expensive survey-grade laser scanners and high-precision GNSS/IMU systems, which limits their large-scale deployment and results in poor real-time performance. Although LiDAR-based simultaneous localization and mapping (SLAM) techniques have been widely applied in the navigation field, to the best of my knowledge, there has been no research conducted on simultaneous real-time localization and roadside tree inventory. This paper proposes an innovative approach that uses LiDAR technology to achieve vehicle positioning and a roadside tree inventory. Firstly, a front-end odometry based on an error-state Kalman filter (ESKF) and a back-end optimization framework based on factor graphs are employed. The updated poses from the back-end are used for establishing point-to-plane residual constraints for the front-end in the local map. Secondly, a two-stage approach is adopted to minimize global mapping errors, refining accumulated mapping errors through GNSS-assisted registration to enhance system robustness. Additionally, a method is proposed for creating a tree inventory that extracts line features from real-time LiDAR point cloud data and projects them onto a global map, providing an initial estimation of possible tree locations for further tree detection. This method uses shared feature extraction results and data pre-processing results from SLAM to reduce the computational load of simultaneous vehicle positioning and roadside tree inventory. Compared to methods that directly search for trees in the global map, this approach benefits from fast perception of the initial tree position, meeting real-time requirements. Finally, our system is extensively evaluated on real datasets covering various road scenarios, including urban and suburban areas. The evaluation metrics are divided into two parts: the positioning accuracy of the vehicle during operation and the detection accuracy of trees. The results demonstrate centimeter-level positioning accuracy and real-time automatic creation of a roadside tree inventory.

Nighttime Image Stitching Method Based on Image Decomposition Enhancement.

Image stitching technology realizes alignment and fusion of a series of images with common pixel areas taken from different viewpoints of the same scene to produce a wide field of view panoramic image with natural structure. The night environment is one of the important scenes of human life, and the night image stitching technology has more urgent practical significance in the fields of security monitoring and intelligent driving at night. Due to the influence of artificial light sources at night, the brightness of the image is unevenly distributed and there are a large number of dark light areas, but often these dark light areas have rich structural information. The structural features hidden in the darkness are difficult to extract, resulting in ghosting and misalignment when stitching, which makes it difficult to meet the practical application requirements. Therefore, a nighttime image stitching method based on image decomposition enhancement is proposed to address the problem of insufficient line feature extraction in the stitching process of nighttime images. The proposed algorithm performs luminance enhancement on the structural layer, smoothes the nighttime image noise using a denoising algorithm on the texture layer, and finally complements the texture of the fused image by an edge enhancement algorithm. The experimental results show that the proposed algorithm improves the image quality in terms of information entropy, contrast, and noise suppression compared with other algorithms. Moreover, the proposed algorithm extracts the most line features from the processed nighttime images, which is more helpful for the stitching of nighttime images.

Automatic Recognition of Vertical-Line Pulse Train from China Seismo-Electromagnetic Satellite Based on Unsupervised Clustering

Pulse signals refer to electromagnetic waveforms with short duration and high peak energy in the time domain. Spatial electromagnetic pulse interference signals can be caused by various factors such as lightning, arc discharge, solar disturbances, and electromagnetic disturbances in space. Pulse disturbance signals appear as instantaneous, high-energy vertical-line pulse trains (VLPTs) on the spectrogram. This paper uses computer vision techniques and unsupervised clustering algorithms to process and analyze VLPT on very-low-frequency (VLF) waveform spectrograms collected by the China Seismo-Electromagnetic Satellite (CSES) electric field detector. First, the waveform data are transformed into time–frequency spectrograms with a duration of 8 s using the short-time Fourier transform. Then, the spectrograms are subjected to grayscale transformation, vertical line feature extraction, and binarization preprocessing. In the third step, the preprocessed data are dimensionally reduced and fed into an unsupervised K-means++ clustering model to achieve automatic recognition and labeling of VLPTs. By recognizing and studying VLPT, not only can interference be recognized, but the temporal and spatial locations of these interferences can also be determined. This lays the foundation for identifying VLPT sources and gaining deeper insights into the generation, propagation, and characteristics of electromagnetic radiation.

Robust and Accurate Feature Detection on Point Clouds

Geometric feature detection on surfaces is a crucial task for the characterization and understanding of geometry shapes. In this paper, we present a robust and reliable approach for accurately capturing local surface variations at different feature sizes within point clouds. To this end, we define a bilateral weighted centroid projection-based metric to quantify surface deviations. Based on the metric, we propose a structure-to-detail feature perception algorithm to accurately locate geometric features of varying sizes. Additionally, we use tensor analysis to extract boundary features. We evaluate our method on various object- and scene-level point clouds, demonstrating its superiority and versatility over existing techniques. Computational results show that our method is capable of identifying a wide range of geometric characteristics within point clouds, including complicated structures, rich textures, fine details, shallow curves, and geometric boundaries. We also validate the effectiveness of our approach on several downstream applications, including segmentation, surface reconstruction, and feature line extraction.

Improved monocular visual-inertial odometry with point and line features using adaptive line feature extraction

Improved monocular visual-inertial odometry with point and line features using adaptive line feature extraction

Lightweight Semantic Architecture Modeling by 3D Feature Line Detection

Existing architecture semantic modeling methods in 3D complex urban scenes continue facing difficulties, such as limited training data, lack of semantic information, and inflexible model processing. Focusing on extracting and adopting accurate semantic information into a modeling process, this work presents a framework for lightweight modeling of buildings that joints point clouds semantic segmentation and 3D feature line detection constrained by geometric and photometric consistency. The main steps are: (1) Extraction of single buildings from point clouds using 2D-3D semi-supervised semantic segmentation under photometric and geometric constraints. (2) Generation of lightweight building models by using 3D plane-constrained multi-view feature line extraction and optimization. (3) Introduction of detailed semantics of building elements into independent 3D building models by using fine-grained segmentation of multi-view images to achieve high-accuracy architecture lightweight modeling with fine-grained semantic information. Experimental results demonstrate that it can perform independent lightweight modeling of each building on point cloud at various scales and scenes, with accurate geometric appearance details and realistic textures. It also enables independent processing and analysis of each building in the scenario, making them more useful in practical applications.

UPLP-SLAM: Unified point-line-plane feature fusion for RGB-D visual SLAM

Most of the existing RGB-D simultaneous localization and mapping (SLAM) systems are based on point features or point-line features or point-plane features. However, the existing multi- feature fusion SLAM methods based on the filter framework are not accurate and robust. And the fusion methods based on the optimization framework process different kinds of features separately and integrate them loosely. In the optimization-based framework, how to tightly fuse various kinds of features for achieving more accurate and robust pose estimation has been rarely considered. In this paper, we propose a unified point-line-plane fusion RGB-D visual SLAM method for navigation of mobile robots in structured environments, making full use of the information of three kinds of geometric features. Specifically, it extracts point, line, and plane features using images captured by the RGB-D camera and expresses them in a uniform way. Then, a mutual association scheme is designed for data association of point, line and plane features, which not only considers the correspondence of homogeneous features, i.e., point-point, line-line and plane-plane pairs, but also includes the association of heterogeneous features, i.e., point- line, point-plane and line-plane pairs. Afterwards, the matching errors between homogeneous features and the association errors between heterogeneous features are uniformly represented and jointly optimized to estimate the camera pose and feature parameters for accurate and consistent localization and map building. It is worth pointing out that the proposed unified framework contains two levels. From the system framework perspective, all the main components of the SLAM system, i.e., feature representation, feature association and error function are handled in a unified manner, which increases the accuracy and compactness of the multi-feature SLAM system. From the feature processing perspective, both homogeneous features and heterogeneous features are uniformly used, which provides more spatial constraints on pose estimation. Finally, the accuracy and robustness of the proposed method are verified by experiment comparisons with state-of-the-art visual SLAM systems on public datasets and in real-world environments

A Contour Line Group Simplification Method Based on Classified Terrain Features

Contour line group simplification methods can effectively preserve terrain features during map making and producing. This process involves two main steps, namely terrain feature line extraction and contour bend selection. The terrain feature line extraction includes two steps, that is, terrain feature point extraction and classification, and terrain feature line connection. However, to date, many similar studies have not considered the hierarchy of terrain features. Therefore, we proposed a group simplification method for contour lines based on classified terrain features and tested it on a study area with mainly positive landforms. In accordance with geomorphological theory, we divided valleys into either gradually descending or ordinary. Valley points were extracted based on the constrained Delaunay triangulation method and then classified into the two categories. Gradually descending and ordinary valley lines were then connected. The contour bends were grouped based on the valley lines extracted and then selected according to the geometric indicators of the bend group. The results have demonstrated that the valley lines extracted closely matched human perception in integrity and structure. Contour lines simplified by our method achieved effective reduction of map information and adequate retention of the main terrain structures, which are similar to those from manual simplification.

Extraction of terrain ridge lines and valley lines based on agglomeration analysis of terrain points: a cluster analysis method

Terrain feature extraction is one of the critical issues in geographic information science. As important terrain feature lines, ridge lines and valley lines play an important role in hydrological analysis, terrain reconstruction and automatic integration of contour lines. But the extraction of terrain feature lines is complicated and time-consuming task. In this paper, a terrain feature line extraction method is proposed based on clustering technique. The terrain feature points are automatically extracted according to the agglomeration of terrain points, and the similar points are automatically identified according to the DBSCAN clustering algorithm. The points with high similarity are clustered along the direction of ridge or valley, and the whole terrain will be clustered into multiple sub-regions. The nearest sub-regions are found by calculating the minimum distance between these sub-regions, the adjacent sub-regions are connected orderly by their center line to obtain terrain feature lines. Compared with other methods, the cluster analysis method in this paper has simple process and high efficiency.

The IMU Augment SLAM on Unmanned Vehicle for Detection of Protective Measures in COVID-19

Detecting protective measures (e.g., masks, goggles and protective clothing) is a momentous step in the fight against COVID-19. The detection mode of unmanned devices based on Simultaneous localization and mapping (SLAM) and fusion technology is more efficient, economical and safe than the traditional manual detection. In this paper, a tightly-coupled nonlinear optimization approach is used to augment the visual feature extraction of SLAM by the gyroscope of the IMU to obtain a high-precision visual inertial system for joint position and pose estimation. Based on the VINS-Mono frame, first, an LSD algorithm based on a conditional selection strategy is proposed to extract line features efficiently. Then, we propose recovering missing point features from line features. Moreover, we propose a strategy to recover vanishing point features from line features, and add residuals to the SLAM cost function based on optimization, which optimizes point-line features in real time to promote the tracking and matching accuracy. Second, the wavelet threshold denoising method based on the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$3\sigma $ </tex-math></inline-formula> criterion is used to carry out real-time online denoising for gyroscope to improve the output precision. Our WD-PL-VINS was measured on publicly available EuRoC datasets, TUM VI datasets and evaluated and validated in lab testing with a unmanned vehicle (UV) based on the NVIDIA Jetson-TX2 development board. The results show that our method’s APE and RPE on MH_03_easy sequences are improved by 69.28% and 97.66%, respectively, compared with VINS-Mono.

Feature Line Extraction from Building Façade Point Clouds by Exploring Spatial Topological Relationship

After using a terrestrial laser scanner to acquire building facade point clouds, the extraction of feature lines can simplify the expression of building objects, thereby contributing to the accurate construction of building facade geometric models. To address the problems of missing extraction and low accuracy in existing methods, this study proposes a feature line extraction method for building facade point clouds by exploring the different spatial topological relationship between feature and non‐feature points. The method comprises three steps: feature point extraction, feature line generation, and feature line merging and optimization. First, feature points are extracted using the convex hull distance value and relative angle, as defined in this study. Thereafter, feature points are clustered by combining the random sample consensus and region growing algorithms, and the feature lines are obtained by utilizing the iterative weighted least squares method based on the IGGIII weight function. Finally, the feature lines are merged and optimized using an endpoint search method to improve the discontinuity and missing common endpoints of the original feature lines. The experimental results obtained using simulated and measured point cloud data show that this method can accurately extract feature points, and the extracted feature lines obtained from building facade point clouds have better accuracy and completeness, which is more practical than the existing methods and can be used in many applications such as building facade measurement and urban three‐dimensional modeling.

A Feature Extraction Algorithm Based on Optimal Neighborhood Size

The feature extraction of a point cloud fragment model is the basis of fragment splicing, which provides the technical support for research on the segmentation, splicing, and restoration of fragment surfaces. High-quality feature extraction, however, is a complicated process due to the diversity of the surface information of a fragment model. For this subject, a high-efficient point cloud feature extraction method was proposed to address a new method for extracting feature lines. First, the projection distance feature of the point cloud model was calculated to identify the potential feature points. Furthermore, the local information of the possible feature points was used to construct the adaptive neighborhoods for identifying the feature points based on neighborhoods of the model. The clustering fusion of the feature points was proposed according to the discrimination threshold values of the feature points. Finally, the Laplace operator was utilized to refine and connect the feature points to form smooth feature lines. The experimental results showed that the proposed method was automatic, highly efficient, and with good adaptability that could effectively extract the detailed features and construct the complete feature lines. Moreover, results showed that the provided framework could extract the features of simple structure models and be feasible to a certain extent for fragment models with abundant features.