Showing papers on "Line segment published in 2022"

Towards Light-Weight and Real-Time Line Segment Detection

Abstract: Previous deep learning-based line segment detection (LSD) suffers from the immense model size and high computational cost for line prediction. This constrains them from real-time inference on computationally restricted environments. In this paper, we propose a real-time and light-weight line segment detector for resource-constrained environments named Mobile LSD (M-LSD). We design an extremely efficient LSD architecture by minimizing the backbone network and removing the typical multi-module process for line prediction found in previous methods. To maintain competitive performance with a light-weight network, we present novel training schemes: Segments of Line segment (SoL) augmentation, matching and geometric loss. SoL augmentation splits a line segment into multiple subparts, which are used to provide auxiliary line data during the training process. Moreover, the matching and geometric loss allow a model to capture additional geometric cues. Compared with TP-LSD-Lite, previously the best real-time LSD method, our model (M-LSD-tiny) achieves competitive performance with 2.5% of model size and an increase of 130.5% in inference speed on GPU. Furthermore, our model runs at 56.8 FPS and 48.6 FPS on the latest Android and iPhone mobile devices, respectively. To the best of our knowledge, this is the first real-time deep LSD available on mobile devices.

Smoothly varying projective transformation for line segment matching

Abstract: Line segment matching is important in applications that require recovering the 3D structure of objects (e.g., manmade objects in street-level scenarios). However, differentiating between true and false line matches is generally difficult without strong geometric constraints for line segments. Hence, additional constraints are forced to be used, sacrificing many true line matches. This study proposes a robust line segment matching method based on global projective transformation modeling. We develop a non-parametric motion regression formulation with a specially designed direct linear transformation-based cost function that reformulates the piecewise smoothly varying projective transformations as a global continuous model from highly noisy point matches. The resultant model can effectively approximate the real underlying image transformation and derive high-quality point matches. We apply the computed model and high-quality point matches to a point-correspondence-based line matching pipeline, which provides sufficient strict geometric constraints for first generating the pair-to-pair matches and then distilling the line-to-line matches. Extensive experiments conducted on two challenging line matching datasets show that the proposed method can obtain considerable correct line segment matches, outperforming the comparison methods in mean F-score by at least 15.5% on the benchmark dataset and 16.9% on the local dataset. Code is available at https://github.com/geovsion/SLEM.

Smoothly varying projective transformation for line segment matching

Abstract: Line segment matching is important in applications that require recovering the 3D structure of objects (e.g., manmade objects in street-level scenarios). However, differentiating between true and false line matches is generally difficult without strong geometric constraints for line segments. Hence, additional constraints are forced to be used, sacrificing many true line matches. This study proposes a robust line segment matching method based on global projective transformation modeling. We develop a non-parametric motion regression formulation with a specially designed direct linear transformation-based cost function that reformulates the piecewise smoothly varying projective transformations as a global continuous model from highly noisy point matches. The resultant model can effectively approximate the real underlying image transformation and derive high-quality point matches. We apply the computed model and high-quality point matches to a point-correspondence-based line matching pipeline, which provides sufficient strict geometric constraints for first generating the pair-to-pair matches and then distilling the line-to-line matches. Extensive experiments conducted on two challenging line matching datasets show that the proposed method can obtain considerable correct line segment matches, outperforming the comparison methods in mean F-score by at least 15.5% on the benchmark dataset and 16.9% on the local dataset. Code is available at https://github.com/geovsion/SLEM .

Minimising line segments in linear diagrams is NP-hard

Abstract: Linear diagrams have been shown to be an effective method of representing set-based data. Moreover, a number of guidelines have been proven to improve the efficacy of linear diagrams. One of these guidelines is to minimise the number of line segments appearing in a diagram. We show this problem to be NP-hard.

Line-Based 3D Building Abstraction and Polygonal Surface Reconstruction From Images.

Abstract: Textureless objects, repetitive patterns and limited computational resources pose significant challenges to man-made structure reconstruction from images, because feature-points-based reconstruction methods usually fail due to the lack of distinct texture or ambiguous point matches. Meanwhile multi-view stereo approaches also suffer from high computational complexity. In this paper, we present a new framework to reconstruct 3D surfaces for buildings from multi-view images by leveraging another fundamental geometric primitive: line segments. To this end, we first propose a new multi-resolution line segment detector to extract 2D line segments from each image. Then, we construct a 3D line cloud by introducing an improved Line3D++ algorithm to match 2D line segments from different images. Finally, we reconstruct a complete and manifold surface mesh from 3D line segments by formulating a Bayesian probabilistic modeling problem, which accurately generates a set of underlying planes. This output model is simple and has low performance requirements for hardware devices. Experimental results demonstrate the validity of the proposed approach and its ability to generate abstract and compact surface meshes from the 3D line cloud with low computational costs.

Clothoidal Mapping of Road Line Markings for Autonomous Driving High-Definition Maps

Abstract: Lane-level HD maps are crucial for trajectory planning and control in current autonomous vehicles. For this reason, appropriate line models should be adopted to define them. Whereas mapping algorithms often rely on inaccurate representations, clothoid curves possess peculiar smoothness properties that make them desirable representations of road lines in control algorithms. We propose a multi-stage pipeline for the generation of lane-level HD maps from monocular vision relying on clothoidal spline models. We obtain measurements of the line positions using a line detection algorithm, and we exploit a graph-based optimization framework to reach an optimal fitting. An iterative greedy procedure reduces the model complexity removing unnecessary clothoids. We validate our system on a real-world dataset, which we make publicly available for further research at https://airlab.deib.polimi.it/datasets-and-tools/.

A new hough transform operated in a bounded cartesian coordinate parameter space

Abstract: In this paper, a new Hough transform is proposed to detect lines with geometric meanings. In the standard Hough transform, lines are parameterized by the length and orientation of the normal vector from the origin to the line. The parameter space of the standard Hough transform is presented in a polar coordinate system. Geometric measurements such as distance and angle are not suitable in polar coordinate space due to the inconsistency of the axes. To deal with this problem, a Hough transform which is carried out in a bounded Cartesian coordinate parameter space is developed. The lines are represented by their perpendicular feet with respect to a fixed point. Since the parameter space is in Cartesian coordinate space, it is intuitive to the researchers. When detecting the peaks in the parameter space, distance and angle constraints can be applied. The effectiveness of the proposed method has been illustrated by two applications, that is, lane line detection and convex polygon extraction. The results show that the proposed Cartesian coordinate Hough transform is suitable for detecting meaningful lines.

Fast Line Segment Detection and Large Scene Airport Detection for PolSAR

Abstract: In this paper, we propose a fast Line Segment Detection algorithm for Polarimetric synthetic aperture radar (PolSAR) data (PLSD). We introduce the Constant False Alarm Rate (CFAR) edge detector to obtain the gradient map of the PolSAR image, which tests the equality of the covariance matrix using the test statistic in the complex Wishart distribution. A new filter configuration is applied here to save time. Then, the Statistical Region Merging (SRM) framework is utilized for the generation of line-support regions. As one of our main contributions, we propose a new Statistical Region Merging algorithm based on gradient Strength and Direction (SRMSD). It determines the merging predicate with consideration of both gradient strength and gradient direction. For the merging order, we set it by bucket sort based on the gradient strength. Furthermore, the pixels are restricted to belong to a unique region, making the algorithm linear in time cost. Finally, based on Markov chains and a contrario approach, the false alarm control of line segments is implemented. Moreover, a large scene airport detection method is designed based on the proposed line segment detection algorithm and scattering characteristics. The effectiveness and applicability of the two methods are demonstrated with PolSAR data provided by UAVSAR.

A Novel Feature Extraction Algorithm and System for Flexible Integrated Circuit Packaging Substrate

Abstract: Aiming at the line defect detection of a flexible integrated circuit substrate (FICS) without reference template, there are some problems such as line discontinuity or inaccurate line defect location in the detection results. In order to address these problems, a line feature detection algorithm for extracting an FICS image is proposed. Firstly, FICS image acquisition is carried out by using the appearance defect intelligent detection system independently developed in our lab. Secondly, in the algorithm design of the software system, the binary image of the line image to be segmented is obtained after the color FICS image is classified by K-means, median filtering, morphological filling and closed operation. Finally, for an FICS binary image, an image segmentation model with convexity-preserving indirect regular level set is proposed, which is applied to extract the line features of an FICS image. Experiment results show that, compared with the CV model, LBF model, LCV model, LGIF model, Order-LBF model and RSF model, the proposed model can extract line features with high accuracy, and the line boundary is smooth, which lays an important foundation for high-precision measurement of line width and line distance and high-precision location of defects.

Vision measurement for flat parts based on local line-angle contour segmentation

Abstract: In order to detect the size information of complex flat parts, this paper proposed a method for flat part measurement based on local line-angle contour segmentation. After processing the images taken by photos and edge detection, we obtained sub-pixel part contours. Then, the local line-angles of the part contours were calculated, processed and analyzed, and so on the features of the connection between the geometric primitives of different line segments on its contour were obtained. The segmentation of the part contour came true. Next, a line segmentation error model was built, and then we got the parameters of the contour segment and the key points of the components by iterative fitting the segmented line and pinpointing the location of the segmentation. Afterwards a binocular vision model provided the spatial point cloud of the key points. As a result, the size information of the parts were acquired after analyzation and calculation. The present method can successfully measure the multiple size of the complex flat parts, which is more efficient and precise.

LSPP: A Novel Path Planning Algorithm Based on Perceiving Line Segment Feature

Abstract: Path planning in the automatic driving system generally uses point features to evaluate the influence of obstacles on the robot, leading to missing information or increasing computational burden. This paper proposes a novel path planning with line segment (LSPP) algorithm from the viewpoint of line segment, which is easy to be obtained directly from sensors. In LSPP, an artificial potential field (APF) based on the azimuth and distance (ADAPF) from obstacles to the robot is first constructed for implementation of integral calculation. Unlike the traditional APF which only considers the nearest distance from obstacles to the robot, ADAPF can effectively assess the influence of boundary points on the robot by fully utilizing the information of obstacles. Based on ADAPF, boundary points are integrated into lines as edges of the drivable area in a specialized coordinate system. Then, a multi-loss function is designed to guarantee that the robot is far away from obstacles to the optimized path, and thus solved by a modified Dogleg (MDL) algorithm combined with symmetric rank-1 (SR1) method based on adaptive initial trust-region radii. Finally, a smooth and safe path is provided in LSPP with the requirements of speed and quality being satisfied simultaneously. Real-world experimental results validate the robustness and the effectiveness of LSPP.

A New Algorithm for Pyramidal Clipping of Line Segments in E3

Abstract: A new algorithm for clipping a line segment against a pyramid in E3 is presented. This algorithm avoids computation of intersection points which are not end-points of the output line segment. It also allows solving all cases more effectively. The performance of this algorithm is shown to be consistently better than existing algorithms, including the Cohen-Sutherland, Liang-Barsky and Cyrus-Beck algorithms.

An Adaptive Threshold Line Segment Feature Extraction Algorithm for Laser Radar Scanning Environments

Abstract: An accurate map is needed for the autonomous navigation of mobile robots in unknown environments. The application of laser radars has the advantages of high ranging accuracy and long ranging distances. Due to the small amount of data on laser radars and the influence of noise on the sensor itself, these amount to causing problems such as low accuracies of map construction and large positioning errors. Currently, the feature extraction of environmental line segments based on radar scanning data generally adopts the idea of recursion. However, the amount of calculations for applying recursion is large, and the threshold of extracted feature points needs to be set manually. Moreover, the fixed segmentation threshold will cause under-segmentation or over-segmentation. In this paper, an adaptive threshold-based feature extraction method for environmental line segments is proposed. The method denoises the original data first, and then an adaptive threshold of the nearest neighbor algorithm is provided to improve the accuracy of breakpoint judgment; next, the slope difference between adjacent line segments is evaluated according to the line segment fitting error in order to obtain the optimal corner feature. Finally, the point set is segmented to fit line-segment features. Based on actual environment tests, the environmental similarity of the line segment features extracted by the new algorithm in this paper increases by 8.3% compared with the IEPF (Iterative End Point Fit) algorithm. The algorithm avoids recursive operations, improves the efficiency by four times, and meets the real-time requirements of line segment fitting.

Robust Extraction of 3D Line Segment Features from Unorganized Building Point Clouds

Abstract: As one of the most common features, 3D line segments provide visual information in scene surfaces and play an important role in many applications. However, due to the huge, unstructured, and non-uniform characteristics of building point clouds, 3D line segment extraction is a complicated task. This paper presents a novel method for extraction of 3D line segment features from an unorganized building point cloud. Given the input point cloud, three steps were performed to extract 3D line segment features. Firstly, we performed data pre-processing, including subsampling, filtering and projection. Secondly, a projection-based method was proposed to divide the input point cloud into vertical and horizontal planes. Finally, for each 3D plane, all points belonging to it were projected onto the fitting plane, and the α-shape algorithm was exploited to extract the boundary points of each plane. The 3D line segment structures were extracted from the boundary points, followed by a 3D line segment merging procedure. Corresponding experiments demonstrate that the proposed method works well in both high-quality TLS and low-quality RGB-D point clouds. Moreover, the robustness in the presence of a high degree of noise is also demonstrated. A comparison with state-of-the-art techniques demonstrates that our method is considerably faster and scales significantly better than previous ones. To further verify the effectiveness of the line segments extracted by the proposed method, we also present a line-based registration framework, which employs the extracted 2D-projected line segments for coarse registration of building point clouds.

Optimal patrolling of high priority segments while visiting the unit interval with a set of mobile robots

Abstract: Consider a region that requires to be protected from unauthorized penetrations. The border of the region, modeled as a unit line segment, consists of high priority segments that require the highest level of protection separated by low priority segments that require to be visited infinitely often. We study the problem of patrolling the border with a set of k robots. The goal is to obtain strategies that minimize the maximum idle time (the time that a point is left unattended) of each point of the high priority segments while visiting each point of the low priority segments infinitely often. We use the concept of single lid cover (segments of fixed length) where each high priority point is covered with at least one lid, and then we extend it to strong double-lid cover where each high priority point is covered with at least two lids, and the unit line segment is fully covered. Let λk−1 be the minimum lid length that accepts a single λk−1-lid cover with k−1 lids and Λ2k be the minimum lid length that accepts a strong double Λ2k-lid cover with 2k lids. We show that 2min⁡(Λ2k,λk−1) is the lower bound of the idle time when the max speed of the robots is one. To compute Λ2k and λk−1, we present an algorithm with time complexity O(max⁡(k,n)log⁡n) where n is the number of high priority segments. Our algorithm improves by a factor of min⁡(n,k) the previous O(knlog⁡n) running time algorithm. For the upper bound, first we present a strategy with idle time λk−1 where robot k patrols the unit line segment, and robot i patrols the i-lid of a single λk−1-lid cover with k−1 lids. Then, we present a simple strategy with idle time 3Λ2k that splits the unit line into not-disjoint k segments of equal length that robots synchronously cover, i.e., reaching the leftmost and rightmost point simultaneously. Then, we present a complex strategy that splits the unit line into k non-disjoint segments that robots asynchronously cover. We show that the combination of strategies one and two attains an approximation of 1.5 the optimal idle time and combining strategies one and third attains an optimal idle time.

Domain Knowledge-based Automatic Parameter Selection for 2D/3D Line Segment Detection in Semi-unstructured Environment

Abstract: One of the fundamental problems in mobile robot navigation in challenging environment is to improve autonomy in the sensor information processes. This paper presents an automatic parameter selection method for path recognition of outdoor semi-unstructured environment, based on human knowledge on the paths. As a preliminary process for path recognition, line segment detection integrating 2D image and 3D point cloud is adopted. Human knowledge on the path, line segments are mostly horizontal and around the ground level, is reflected to parameter selection through Pareto optimality in the multiple objective optimization. The proposed selection was evaluated by depth images taken in outdoor environments where boundaries of paths are obscure. It was shown in the experiment that resolution and edge parameters are influential to boundary detection performance. It was verified that the proposed method could select appropriate set of processing parameters based on the knowledge. The proposed idea is expected to contribute automatic selection of sensor modalities for more various environmental recognition scenarios.

Compact World Anchors: Registration Using Parametric Primitives as Scene Description

Abstract: We present a registration method relying on geometric constraints extracted from parametric primitives contained in 3D parametric models. Our method solves the registration in closed-form from three line-to-line, line-to-plane or plane-to-plane correspondences. The approach either works with semantically segmented RGB-D scans of the scene or with the output of plane detection in common frameworks like ARKit and ARCore. Based on the primitives detected in the scene, we build a list of descriptors using the normals and centroids of all the found primitives, and match them against the pre-computed list of descriptors from the model in order to find the scene-to-model primitive correspondences. Finally, we use our closed-form solver to estimate the 6DOF transformation from three lines and one point, which we obtain from the parametric representations of the model and scene parametric primitives. Quantitative and qualitative experiments on synthetic and real-world data sets demonstrate the performance and robustness of our method. We show that it can be used to create compact world anchors for indoor localization in AR applications on mobile devices leveraging commercial SLAM capabilities.

PLI-VINS: Visual-Inertial SLAM Based on Point-Line Feature Fusion in Indoor Environment

Abstract: In indoor low-texture environments, the point feature-based visual SLAM system has poor robustness and low trajectory accuracy. Therefore, we propose a visual inertial SLAM algorithm based on point-line feature fusion. Firstly, in order to improve the quality of the extracted line segment, a line segment extraction algorithm with adaptive threshold value is proposed. By constructing the adjacent matrix of the line segment and judging the direction of the line segment, it can decide whether to merge or eliminate other line segments. At the same time, geometric constraint line feature matching is considered to improve the efficiency of processing line features. Compared with the traditional algorithm, the processing efficiency of our proposed method is greatly improved. Then, point, line, and inertial data are effectively fused in a sliding window to achieve high-accuracy pose estimation. Finally, experiments on the EuRoC dataset show that the proposed PLI-VINS performs better than the traditional visual inertial SLAM system using point features and point line features.

On Computing Optimal Linear Diagrams

Abstract: Linear diagrams are an effective way to visualize set-based data by representing elements as columns and sets as rows with one or more horizontal line segments, whose vertical overlaps with other rows indicate set intersections and their contained elements. The efficacy of linear diagrams heavily depends on having few line segments. The underlying minimization problem has already been explored heuristically, but its computational complexity has yet to be classified. In this paper, we show that minimizing line segments in linear diagrams is equivalent to a well-studied $$\mathsf {NP}$$ -hard problem, and extend the $$\mathsf {NP}$$ -hardness to a restricted setting. We develop new algorithms for computing linear diagrams with minimum number of line segments that build on a traveling salesperson (TSP) formulation and allow constraints on the element orders, namely, forcing two sets to be drawn as single line segments, giving weights to sets, and allowing hierarchical constraints via PQ-trees. We conduct an experimental evaluation and compare previous algorithms for minimizing line segments with our TSP formulation, showing that a state-of-the art TSP-solver can solve all considered instances optimally, most of them within few milliseconds.

Median location problem with two probabilistic line barriers: Extending the Hook and Jeeves algorithm

Abstract: <p style='text-indent:20px;'>We consider a median location problem in the presence of two probabilistic line barriers on the plane under rectilinear distance. It is assumed that the two line barriers move on their corresponding horizontal routes uniformly. We first investigate different scenarios for the position of the line barriers on the plane and their corresponding routes, and then define the visibility and invisibility conditions along with their corresponding expected barrier distance functions. The proposed problem is formulated as a mixed-integer nonlinear programming model. Our aim is to locate a new facility on the plane so that the total weighted expected rectilinear barrier distance is minimized. We present efficient lower and upper bounds using the forbidden location problem for the proposed problem. To solve the proposed model, the Hooke and Jeeves algorithm (HJA) is extended. We investigate various sample problems to test the performance of the proposed algorithm and appropriateness of the bounds. Also, an empirical study in Kingston-upon-Thames, England, is conducted to illustrate the behavior and applicability of the proposed model.</p>

Lane Line Detection Technology Based on OpenCV for Specific Scenarios

Abstract: Lane line detection is one of the important tasks of the environment perception system of autonomous vehicles, which must be very time sensitive and robust. To this end, this paper proposes a lane line detection implementation method based on the OpenCV platform, which can be applied to smart cars in specific places, mainly including image preprocessing and lane line detection and fitting. Applying morphological operations to the image preprocessing stage can effectively fill in the wear information of lane lines, and the least squares method is used to adjust lane lines after Hough transformation. The results show that the proposed method can improve the operation speed without affecting the accuracy of the algorithm, and has certain practicality.

On Computing Optimal Linear Diagrams

Abstract: Linear diagrams are an effective way to visualize set-based data by representing elements as columns and sets as rows with one or more horizontal line segments, whose vertical overlaps with other rows indicate set intersections and their contained elements. The efficacy of linear diagrams heavily depends on having few line segments. The underlying minimization problem has already been explored heuristically, but its computational complexity has yet to be classified. In this paper, we show that minimizing line segments in linear diagrams is equivalent to a well-studied NP-hard problem, and extend the NP-hardness to a restricted setting. We develop new algorithms for computing linear diagrams with minimum number of line segments that build on a traveling salesperson (TSP) formulation and allow constraints on the element orders, namely, forcing two sets to be drawn as single line segments, giving weights to sets, and allowing hierarchical constraints via PQ-trees. We conduct an experimental evaluation and compare previous algorithms for minimizing line segments with our TSP formulation, showing that a state-of-the art TSP-solver can solve all considered instances optimally, most of them within few milliseconds.

Competitive Location Strategies in the (r$$\mid $$p)-Centroid Problem on a Plane with Line Barriers

Abstract: In 1982, Drezner considered the competitive facility location problem when the leader and follower each place a facility on a plane. He proposed polynomial-time algorithms for the follower and leader optimal facility location. In 2013, Davydov et al. considered a generalization of this problem when the leader has a set of $$(p - 1)$$ facilities and wants to open another facility in the best position with the optimal response of the follower. We examine the influence of line barriers on the optimal leader and follower strategies. The paper considers the formulations in which the number of already open facilities is fixed, and the barriers divide the plane into polygons in such a way that two different paths from one polygon to another cannot exist. We propose a polynomial-time algorithm for the Drezner problem with barriers, as well as for the problem studied by Davydov et al.

Line segment visibility with sidedness constraints

Abstract: We study a family of line segment visibility problems, related to classical art gallery problems, which are motivated by monitoring requirements in commercial data centers. Given a collection of non-overlapping line segments in the interior of a rectangle, and a requirement to monitor the segments from one side or the other, we examine the problem of finding a minimal set of point guards. Guards may be placed anywhere in the interior of the rectangle but not on a line segment. We consider combinatorial bounds of problem variants where the problem solver gets to decide which side of the segments to guard or the problem poser gets to decide which side to guard, and many others. We show that virtually all variants are NP-Hard to solve exactly, and then provide heuristics and experimental results to give insight into the associated practical problems. Finally we describe a program for using experiments to guide the search for optimal combinatorial bounds.

Stabbing balls with line segments and polygonal paths

Abstract: We study the problem of ordered stabbing of $n$ balls (of arbitrary and possibly different radii, no ball contained in another) in $\mathbb{R}^d$, $d \geq 3$, with either a directed line segment or a (directed) polygonal curve. Here, the line segment, respectively polygonal curve, shall visit (intersect) the given sequence of balls in the order of the sequence. We present a deterministic algorithm that decides whether there exists a line segment stabbing the given sequence of balls in order, in time $O(n^{4d-2} \log n)$. Due to the descriptional complexity of the region containing these line segments, we can not extend this algorithm to actually compute one. We circumvent this hurdle by devising a randomized algorithm for a relaxed variant of the ordered line segment stabbing problem, which is built upon the central insights from the aforementioned decision algorithm. We further show that this algorithm can be plugged into an algorithmic scheme by Guibas et al., yielding an algorithm for a relaxed variant of the minimum-link ordered stabbing path problem that achieves approximation factor 2 with respect to the number of links. We conclude with experimental evaluations of the latter two algorithms, showing practical applicability.