Hough Transform Research Articles

Technical Evaluation on Improved Hough Transform for Monitoring Traffic Sign Images under Depth Algorithm

Technical Evaluation on Improved Hough Transform for Monitoring Traffic Sign Images under Depth Algorithm

Smart Navigation in Assistive Devices: Depth Camera-Driven Stairs Recognition

With almost 8 million blind and visually impaired persons in India, there is an urgent need for autonomous navigation systems to help them. Since most homes have stairs, it is crucial that they be automatically detected in real time. The division of stairs into "up" and "down" categories is the main topic of this essay. 3D point cloud photos taken with an Intel RealSense camera are used in the study. The Hough Transform is applied to the corresponding RGB image in order to extract a 1D feature along the stairs' length from the depth image. The Intel RealSense camera was used to build a balanced dataset of 170 point cloud images that represented both "up" and "down" stairs. Experimental results demonstrate that the proposed method achieves classification performances of 60% with SVM and 85% with MLP, showcasing the potential of the approach for realworld applications.

Composite Localization for OD Segmentation from Retinal Images Through Circular Hough Transform

Composite Localization for OD Segmentation from Retinal Images Through Circular Hough Transform

Research on belt deviation diagnosis of belt conveyors based on deep learning

Abstract Due to the slow detection speed, low accuracy, and small detection range of existing methods for detecting belt deviation in belt conveyors, this paper introduces an enhanced ultra-fast lane detection (UFLD) algorithm that leverages deep learning for the detection of belt deviation. Based on the UFLD algorithm, a variable step-size row anchor division method is proposed, and the simple parameter-free attention module is added to the network to enhance the network model’s focus on edge information of conveyor belts. Furthermore, improvements are made to the convolution operations in the ResNet-18 Stem and the downsampling operations in the residual modules, thereby enhancing the network’s ability to recognize the edges of conveyor belts. Based on the established experimental platform, a high-definition camera equipped with a track-type inspection robot was used to inspect the entire belt conveyor, covering the whole of the transmission line. The conveyor belt operation datasets collected under various working conditions were used to train and comparatively study the Hough Transform, DHT, YOLOv5, YOLOv8, LaneNet, SAD, and UFLD algorithms. The experimental outcomes demonstrate that the algorithm introduced in this article outperforms the other algorithms, achieving an F1-measure of 90.31%, an accuracy rate of 94.19 %, and a detection speed of 71 frames per second, meeting the real-time diagnostic needs for belt misalignment in the coal mining industry.

Development of Robust Lane-Keeping Algorithm Using Snow Tire Track Recognition in Snowfall Situations.

This study proposed a robust lane-keeping algorithm designed for snowy road conditions, utilizing a snow tire track detection model based on machine learning. The proposed algorithm is structured into two primary modules: a snow tire track detector and a lane center estimator. The snow tire track detector utilizes YOLOv5, trained on custom datasets generated from public videos captured on snowy roads. Video frames are annotated with the Computer Vision Annotation Tool (CVAT) to identify pixels containing snow tire tracks. To mitigate overfitting, the detector is trained on a combined dataset that incorporates both snow tire track images and road scenes from the Udacity dataset. The lane center estimator uses the detected tire tracks to estimate a reference line for lane keeping. Detected tracks are binarized and transformed into a bird's-eye view image. Then, skeletonization and Hough transformation techniques are applied to extract tire track lines from the classified pixels. Finally, the Kalman filter estimates the lane center based on tire track lines. Evaluations conducted on unseen images demonstrate that the proposed algorithm provides a reliable lane reference, even under heavy snowfall conditions.

New Radio Observations of the Supernova Remnant CTA 1

We present new radio images of the supernova remnant (SNR) CTA 1 at 1420 and 408 MHz, and in the 21 cm line of H i observed with the Dominion Radio Astrophysical Observatory Synthesis Telescope and at 1420 MHz observed with the Effelsberg 100 m telescope. We confirm previously described continuum features and elaborate further on filamentary features identified using the high-resolution (1′) maps from these new observations. We investigate the abrupt change in sign of rotation measure (RM) across the SNR, using the linear polarization observations in the four bands around 1420 MHz. Following X. H. Sun et al.’s (2011) investigation, we both confirm that the distribution of signs of the RMs for extragalactic sources in the area appears to match that of the shell, as well as combine the data from the four bands to estimate the relative depolarization and the intrinsic rotation measure of the SNR. We do not conclusively reject X. H. Sun et al.’s (2011) claim of a Faraday screen in the foreground causing the distribution of RMs that we observe; however, we do suggest an alternative explanation of a swept-up stellar wind from the progenitor star with a toroidal magnetic field. Finally, we expand on the analysis of the H i observations by applying the Rolling Hough Transform to isolate filamentary structure and better identify H i emission with the SNR. Further constraining the H i velocity channels associated with CTA 1, we use more recent Galactic rotation curves to calculate an updated kinematic distance of 1.09 ± 0.2 kpc.

New crescent moon detection using Circular Hough Transform (CHT)

Over 1.5 billion Muslims worldwide rely on a calendar based on the observation of the new crescent moon, particularly during the Hijri calendar months of Ramadhan, Shawal, and Zulhijjah. Accurately detecting the new crescent moon immediately after its conjunction is essential for ensuring the precision of the calendar, but it poses a technical challenge due to the low contrast between the new crescent moon and its background. This study aimed to solve the challenge of reliably identifying the new crescent moon at this critical phase, which is vital for accurately determining important dates that signify religious events. It intended to create and verify a computer vision model that would greatly improves the precision and efficiency of identifying a new crescent moon based on images. This will assist in precisely identifying important dates relevant to Muslim religious practices. The methodology employs image preprocessing techniques such as Gaussian Blur for image smoothing and Adaptive Thresholding for contrast enhancement to optimize the visibility of the crescent moon in a single image. The Circular Hough Transform (CHT) technique was used to accurately detect the new crescent moon, while the OpenCV software package helped to implement all of these methods, thus, providing a strong foundation for precisely identifying the new crescent moon. Findings of this study, which involved observations at Kolej Ugama Sultan Zainal Abidin (KUSZA) Observatory, Teluk Kemang Observatory, and Miri Observatory, indicate that the utilization of image processing techniques results in significant improvements in both the efficiency and precision of identifying and detecting the new crescent moon. These enhancements exceed the performance of conventional digital imaging methods employed during regular observations. The model’s processing rate surpasses the usual observation efficiency and showcases exceptional accuracy in distinguishing images that feature the new crescent moon from those that do not. In conclusion, the proposed model demonstrates an effective and efficient methodology for improving the precision of lunar calendar management and the quick planning of important Islamic religious events in accordance with the lunar cycle. This technological advancement offers a reliable method for accurately seeing the crescent moon, which has important implications for enhancing the precision of lunar-based calendars and coordinating important Islamic religious occasions.

Underwater Horizontal Attitude Determination Technology Based on Fusion Power Circle Theory and Improved 3D Cone Hough Transform

Due to the complexity of underwater conditions, achieving stable long-endurance autonomous underwater navigation has always been a challenging issue. Polarized light navigation, which utilizes the polarization field in the underwater downward radiation field to determine the heading angle, requires a known horizontal attitude beforehand. In response to the significant deviations caused by interference in the existing underwater polarization attitude determination algorithms, this paper proposes an edge recognition method that integrates the Power theorem of circles and Improved 3D Conical Hough Transformation (PTC–3D-CoHT). This method has the advantages of pre-screening effective pixel points, better handling of distorted circles, and improving the deviation in extracting Snell’s window. The theoretical basis, model, and detailed calculation process of this method are provided in this paper. Underwater experiments show that, compared to the Circular Hough Transformation (CiHT) and 3D Conical Hough Transformation (3D-CoHT) algorithms, PTC–3D-CoHT enhances the robustness of Snell’s window extraction, verifying the effectiveness of the proposed method.

Machine learning‐driven design of dual‐band antennas using PGGAN and enhanced feature mapping

AbstractThis paper presents a systematic antenna design methodology that integrates machine learning, leveraging the progressive growth technique of Progressive Growing of GANs (PGGAN) to generate images of various dual‐band PIFA‐like antenna structures. The process involves using data augmentation methods to generate 4180 antenna samples. In the latent space, the authors employ Latin Hypercube Sampling to maintain diversity and combine it with the Hough Transform to enhance the edge features of the antennas while providing labelling functionality. This labelling method strengthens the relationship between antenna frequency and wavelength characteristics. The paper clearly outlines the design process, starting from the simulation of two types of single‐frequency PIFA‐like antennas (2.45 and 5.2 GHz, respectively) to the completion of PGGAN's generation task, resulting in a novel dual‐band Wi‐Fi PIFA‐like antenna structure. The measurement results of the dual‐band antennas exhibit excellent consistency with the simulation results.

Novel analysis tool for the distance of gold dimers controlled by the DNA strand length on the DNA origami.

Metallic nanoparticle dimers have been used to enhance the excitation rate of single-quantum emitters. The interparticle distance (d) of the dimers has a crucial influence on the signal enhancement. Therefore, precise control of d is desired for optimal performance. However, statistical analysis of d has been often restricted to a small number of dimers due to the lack of reliable automatic software tools. For this reason, we developed a novel analysis tool for automatic dimer analysis. Our approach combines particle detection by circle Hough transformation (CHT) with custom classification routines optimised for distinct types of particles. We applied our tool to scanning electron microscopy (SEM) images and achieved great agreement in dimer detection, reaching an agreement of around 97% between automatic analysis and manual inspection for more than 3000 metallic nanoparticle dimers on DNA origami controlled by a combination of multiple DNA strands. Our study revealed the effects of the strand length (L) on the distribution of d. Based on geometric consideration, we expected a strong correlation between L and the standard deviation (σ) of d. We could verify this correlation by characterising four dimer designs with different L while analysing more than 1000 dimers per specimen.

Wall thinning quantification with a lift-off distance for ferromagnetic structures using pulsed ECT equipped with ICA-Gauss filter and Hough Transform

Determining the thickness of ferromagnetic materials with a lift-off distance poses a significant challenge for current non-destructive testing (NDT) techniques. Pulsed eddy current (PEC) testing is deemed as a powerful candidate to evaluate this type of defect. However, the signal-to-noise ratio (SNR) of the PEC response signal obtained with large lift-off distance is very poor, so that the signal feature can hardly be extracted. To improve the SNR of PEC response signals and capture the signal feature adaptively, this paper proposed a novel PEC signal processing algorithm based on ICA-Gauss filter and Hough Transform (HT). Firstly, the principle of the proposed method was introduced. Then, two case studies, a comparison experiment and an application experiment were conducted to verify the effectiveness and accuracy of this method. Results from these experiments show that (a) the ICA-Gauss filter can effectively suppress the power-line noises and random noises in PEC signals, (b) the ICA-Gauss filter outperforms traditional filters in feature robustness and computing efficiency, including double-logarithmic median filter and Savitzky-Golay filter, and (c) HT is an adaptive and accurate method to extract the PEC signal feature, thus achieving a small detection error.

Three-Dimensional Instance Segmentation Using the Generalized Hough Transform and the Adaptive n-Shifted Shuffle Attention.

The progress of 3D instance segmentation techniques has made it essential for several applications, such as augmented reality, autonomous driving, and robotics. Traditional methods usually have challenges with complex indoor scenes made of multiple objects with different occlusions and orientations. In this work, the authors present an innovative model that integrates a new adaptive n-shifted shuffle (ANSS) attention mechanism with the Generalized Hough Transform (GHT) for robust 3D instance segmentation of indoor scenes. The proposed technique leverages the n-shifted sigmoid activation function, which improves the adaptive shuffle attention mechanism, permitting the network to dynamically focus on relevant features across various regions. A learnable shuffling pattern is produced through the proposed ANSS attention mechanism to spatially rearrange the relevant features, thus augmenting the model's ability to capture the object boundaries and their fine-grained details. The integration of GHT furnishes a vigorous framework to localize and detect objects in the 3D space, even when heavy noise and partial occlusions are present. The authors evaluate the proposed method on the challenging Stanford 3D Indoor Spaces Dataset (S3DIS), where it establishes its superiority over existing methods. The proposed approach achieves state-of-the-art performance in both mean Intersection over Union (IoU) and overall accuracy, showcasing its potential for practical deployment in real-world scenarios. These results illustrate that the integration of the ANSS and the GHT yields a robust solution for 3D instance segmentation tasks.

An algorithm for lane detection based on RIME optimization and optimal threshold

In order to address the challenges of low lane line detection rates caused by complex road conditions,we propose a novel algorithm that integrates frost and ice optimisation with optimal thresholding. A pre-processing model based on Retinex theory is used to reduce noise and preserve grey scale detail. The optimal OTSU threshold is determined for segmentation, which is enhanced by tent mapping. To further enhance the precision of the detection process, the binarized image is transformed into a bird’s-eye view, and the lane line pixel features are identified through the use of an adaptive sliding window. Ultimately, the RANSAC algorithm is utilized in conjunction with a parabolic model for lane line fitting. The experimental results demonstrate that, in comparison to similar image segmentation algorithms, the proposed method exhibits a notable advantage in terms of threshold calculation error and computational efficiency. Moreover, in comparison to analogous line detection algorithms, the detection accuracy rate reaches 93.87%, effectively reducing the impact of interference factors and demonstrating remarkable robustness that surpasses the traditional Hough Transform, which has an accuracy of 43.2%, and sliding window and Hough transform, with an accuracy of 89.16%. The code of our research work is publicly available at: https://github.com/zx2000430/rime.

CTRing: An R package to extract wood density profiles from computed tomography images of discs and logs

Accurately determining the position of pith and accessing tree-ring density profiles, including intra-ring variations, is important for both the forest industry and dendroclimatology. Although several available methods exist for acquiring this information, such as X-ray computed tomography (CT), micro-CT, and X-ray films, the availability of open-source programs for extracting data remains limited. The CTRing package in the R environment integrates a series of functions to detect precisely the pith and tree-ring boundaries and generate tree-ring density profiles using CT images of tree cross sections. Before processing, grey values are transformed into density using a calibration function. Pith position is then detected by combining an adapted Hough Transform method and a one-dimensional edge detector. Tree-ring profiles along the pith-to-bark path of interest are inspected visually, and tree-ring boundaries can be easily added or removed manually via a graphical user interface. After correcting for tree-ring boundaries, the inflection points of a 3rd-degree polynomial obtained from density profiles are used to delimit the earlywood–latewood transition. We tested this package using 60 CT-scanned images of white spruce (Picea glauca (Moench) Voss) discs collected at various tree heights (0 %, 25 %, 50 % and 75 % of the total tree height as well as at 1.3 m). The pith detection function had an average mean error of 0.72 mm with 95 % of the automatically detected pith locations that differed by less than 2 mm from their manually located positions. Error decreased toward the apex of the tree. The functions of the CTRing package are flexible and can be easily implemented or adapted. The package could also be used with simple images of discs to obtain ring-width time series; however, this use must be evaluated further. Future work with this package involves assessing the use of low-quality images and ring-porous species.

Research on the Identification of Rock Mass Structural Planes and Extraction of Dominant Orientations Based on 3D Point Cloud

The different spatial distribution forms of rock mass structural planes create weak zones in the rock mass, which is also a key factor in controlling rock mass stability. Accurately and efficiently identifying rock mass structural planes and obtaining their dominant orientations is critical for rock mass engineering design and construction. Traditional surveying methods for high and steep rock mass structural planes pose high safety risks, offer limited data, and make comprehensive statistical analysis difficult. This paper utilizes complex rock mass surface 3D point cloud data obtained through 3D laser scanning technology and uses the Hough space transform method to calculate the normal vectors of the 3D point cloud. Based on the difference in normal vectors and surface variation, region growing segmentation is applied to identify and extract rock mass structural planes. Additionally, the fast search and density peak clustering method (CFSFDP) is used for clustering analysis of the rock mass structural planes to obtain dominant orientations. This method was applied to a highway’s high and steep rock slope, successfully identifying 281 structural planes and two sets of dominant structural planes. The orientation of the dominant structural planes identified through RocScience Dips 7.0 analysis showed a deviation of no more than ±3°, complying with engineering standards. The research results offer a feasible solution for the identification of high and steep rock mass structural planes and the extraction of the orientation of dominant structural planes.

Improved Early-Stage Maize Row Detection Using Unmanned Aerial Vehicle Imagery

Monitoring row centerlines during early growth stages is essential for effective production management. However, detection becomes more challenging due to weed interference and crop row intersection in images. This study proposed an enhanced Region of Interest (ROI)-based approach for detecting early-stage maize rows. It integrated a modified green vegetation index with a dual-threshold algorithm for background segmentation. The median filtering algorithm was also selected to effectively remove most noise points. Next, an improved ROI-based feature point extraction method was used to eliminate residual noises and extract feature points. Finally, the least square method was employed to fit the row centerlines. The detection accuracy of the proposed method was evaluated using the unmanned aerial vehicle (UAV) image data set containing both regular and intersecting crop rows. The average detection accuracy of the proposed approach was between 0.456° and 0.789° (the angle between the fitted centerline and the expert line), depending on whether crop rows were regular/intersecting. Compared to the Hough Transform (HT) algorithm, the results demonstrated that the proposed method achieved higher accuracy and robustness in detecting regular and intersecting crop rows. The proposed method in this study is helpful for refined agricultural management such as fertilization and irrigation. Additionally, it can detect the missing-seedling regions and replenish seedings in time to increase crop yields.

Solving Ambiguity in EBSD Indexing of Long-Period Stacking Ordered (LPSO) Phase in Mg with Template Matching Approach

Magnesium (Mg) alloys with long-period stacking ordered (LPSO) phases are receiving increasing interest because of their excellent mechanical performance. The close similarity in atomic stacking sequences between different LPSO polytypes and Mg lattice often leads to ambiguous indexing in electron backscatter diffraction (EBSD), a commonly used material characterization technique. Instead of the Hough transformation approach used in commercial software, an alternative indexing approach, which can catch subtle differences by matching experimental patterns with simulated ones, is explored in this study. Our results, showing ~94% of mapping data being correctly indexed as the target phase, 14H LPSO, demonstrate the capability of not only resolving the LPSO phases but also distinguishing different LPSO polytypes. This approach offers a valuable, if not unique, solution for the microscale characterization of LPSO phases, enabling precise microstructure tuning to further promote the mechanical properties of Mg alloys.

A Method for Tracking an Underwater Pipeline from Stereo Images Using an Autonomous Underwater Vehicle

The problem of tracking an underwater pipeline (UP) is considered in the context of an inspection mission. It is assumed that the diameter of the cylindrical pipe is known. To solve this problem, a tracking method is proposed, based on searching and calculating the center line of the UP, and determining the relative position of the autonomous underwater robot (AUV) and UP in the coordinate system of the AUV camera. Unlike well-known analogues, in which the solution is based on recognizing and constructing the boundaries of the UP in images, the proposed method searches for the true position of the center line of the UP on a set of possible options by checking their veracity. Possible options for the spatial position of the search centerline of the current UP section are generated by varying the direction of the beam in the horizontal and vertical plane. The starting point of the ray is the end point of the centerline of the previous section. The veracity criterion is to check that the 3D point features constructed in the scene belong to the cylindrical surface of the UP. The generation and matching of pointfeatures in images of a stereo pair is carried out using the SURF detector. The choice of the correct direction of the center line of the current UP section is ultimately made by voting. The end point of the center line of the current section is determined taking into account the calculated common visibility area with the previous section of the UP. To evaluate the effectiveness of the method, computational experiments were carried out on virtual scenes. The effectiveness was assessed by the accuracy of UP localization (in the AUV coordinate system) and by the speed of calculations in comparison with: a) the first version of this method, based on the use of a vectorized form of images; b) analogues using the Canny and Hough Transform detectors. The stability of the method to the accumulation of navigation accuracy errors during long-term tracking of UPs was also assessed.

Algorithms and software for processing images of the structure of metallic materials for the purpose of determining creep characteristics

The paper contains a description of the approach, algorithms, and software tool for image analysis of deformed material structures. The developed approach is based on the analysis of the microstructure of the material to identify important factors that affect high-temperature deformation during creep in a heat-resistant nickel-based alloy, namely, the dimensions of the channels and their orientation. The developed software tool uses algorithms for converting images into binary black and white using the Otsu method. The intensity of the gradient at each point of the image is visualized using the Sobel operator. Fragment boundaries are determined using the Canny edge detector. Straight line segments are found using the Hough transformation. The software tool is implemented in the Python programming language using the OpenCV library. The main components are described and a flow chart of the program is provided. With the use of the developed software, the transformation of the known experimentally obtained images of the structures of the specimens from heat-resistant nickel-based alloy CMSX-4 deformed at a temperature of 1273K and in a wide range of stresses at different time moments was performed. The results of the analysis of the dimensions of the g-phase channels in the alloy using quantitative evaluation of transformed binary images are discussed. The found characteristics were matched to the value of the creep strain rate, which was determined by calculation based on known experimental data. The possibility of determining the transition from the secondary creep to the stage of avalanche-like growth of strains and hidden damage is shown. For the considered example, the location of the channels in the representative image was determined. A technique for correcting creep curves with the involvement of material structure image processing data is proposed.

Hardware Implementation of Hough Transform for the Application in Lane Detection in Smart Vehicles

Lane detection is one of the important features of smart vehicles. It is used to assist drivers in achieving the best driving experience. Lane detection utilizes the line detection algorithm where there are many algorithms that are available, but the most effective algorithm is the Hough Transform because it is simple and can be applied in both software and hardware implementations. However, studies shown that Hough Transform implementation of video in the software environment could result in sub-par performance because it requires extremely high computation resources and memory. Therefore, we propose hardware implementation of the Hough Transform for lane detection in this work. The targeted hardware is the Field Programmable Logic Array (FPGA) as its reconfigurable nature allows for rapid design. Hardware implementation of video processing enables parallel data processing, which reduces overall system latency. Furthermore, the hardware design can be optimized to reduce the number of logics that will lead to lower power consumption. The hardware logics were designed based on the Hough Transform equation by using the Verilog Hardware Description Language (HDL) in Intel Quartus Prime software. After the design is successfully completed and verified through simulation, the execution speed of the hardware implementation is then compared with the same design in the software environment (MATLAB). The results show that Hough Transform implemented on the hardware is more than 100 times faster than the software implementation. The total number of logic elements is less than 1% of logic resources, resulting in low power consumption at 146 mW.