Shape Detection Algorithm Research Articles

Automatic Switching of Electric Locomotive Power in Railway Neutral Sections Using Image Processing.

This article presents a computer vision-based approach to switching electric locomotive power supplies as the vehicle approaches a railway neutral section. Neutral sections are defined as a phase break in which the objective is to separate two single-phase traction supplies on an overhead railway supply line. This separation prevents flashovers due to high voltages caused by the locomotives shorting both electrical phases. The typical system of switching traction supplies automatically employs the use of electro-mechanical relays and induction magnets. In this paper, an image classification approach is proposed to replace the conventional electro-mechanical system with two unique visual markers that represent the 'Open' and 'Close' signals to initiate the transition. When the computer vision model detects either marker, the vacuum circuit breakers inside the electrical locomotive will be triggered to their respective positions depending on the identified image. A Histogram of Oriented Gradient technique was implemented for feature extraction during the training phase and a Linear Support Vector Machine algorithm was trained for the target image classification. For the task of image segmentation, the Circular Hough Transform shape detection algorithm was employed to locate the markers in the captured images and provided cartesian plane coordinates for segmenting the Object of Interest. A signal marker classification accuracy of 94% with 75 objects per second was achieved using a Linear Support Vector Machine during the experimental testing phase.

GEOMETRIC FEATURES INTERPRETATION OF PHOTOGRAMMETRIC POINT CLOUD FROM UNMANNED AERIAL VEHICLE

Abstract. Recent days point clouds have become one of the most common 3D sources of information which is provides accurate geometry features of the object. 3D point clouds can be derived from either photogrammetry, Lidar or SAR in some cases depending upon the application. These point clouds consisting of 3D geospatial location of an object in form of XYZ coordinates which can be used in various ways to deduct information related to that object either based on visualisation or geometrical interpretation. Quality assessment standards for these point clouds are still very much in nascent stage with optimum accuracy in relative terms only. In this paper, multiple scale of point cloud has been used to understand the level of information these clouds consist on these multiple scales. Based on the 3D spatial information of these point cloud in local neighbourhood, some of invariant geometric properties can be computed for each 3D point with respective covariance matrix. These can be used to describe the local 3D structure using eigenvalues for these matrices. Using these Geometric features an approach is developed to understand the point cloud quality assessment. The proposed methodology exploits these special geometric properties to evaluate the 3D scene structure. Further, the point cloud is classified using shape detection algorithm which evaluates the geometric features to detect the mathematical shapes in the point cloud. This paper also enlightens on different geometric features that can be extracted from a point cloud and the importance of it.

Design and implementation of shape-based feature extraction engine for vision systems using Zynq SoC

With the great impact of vision and Artificial Intelligence (AI) technology in the fields of quality control, robotic assembly and robot navigation, the hardware implementation of object detection and classification algorithms on embedded platforms has got ever-increasing attention these days. The real-time performance with optimum resource utilization of the implementation and its reliability as well as the robustness of the underlying algorithm is the overarching challenges in this field. In this work, an approach employing a fast and accurate vision-based shape-detection algorithm has been proposed and its implementation in heterogeneous System on Chip (SoC) is discussed. The proposed system determines centroid distance and its Fourier Transform for the object feature vector extraction and is realized in the Zybo Z7 development board. The ARM processor is responsible for communication with the external systems as well as for writing data to the Block RAM (BRAM), the control signals for efficient execution of the memory operations are designed and implemented using Finite State Machine (FSM) in the Programmable Logic (PL) fabric. Shape feature vector determination has been accelerated using custom modules developed in Verilog, taking full advantage of the possible parallelization and pipeline stages. Meanwhile, industry-standard Advanced Extendable Interface (AXI) buses are adopted for encapsulating standardized IP cores and building high-speed data exchange bridges between units within Zynq-7000. The developed system processes images of size 32 × 64 in real-time and can generate feature descriptors at a clock rate of 62MHz. Moreover, the method yields a shape feature vector that is computationally light, scalable and rotation invariant. The hardware design is validated using MATLAB for comparative studies

Sunfa Ata Zuyan machine learning models for moon phase detection: algorithm, prototype and performance comparison

The history recorded moon as the most inspiring object in the sky, but it combined with visibility issues to study the phases. This research paper proposes a novel algorithm named Sunfa Ata Zuyan (SAZ), which is meant to extend the shape detection algorithms to aim for lunar phase deceleration and overcome the difficulties encountered by the previous methods to find the moon and determine its phase. The paper sets to investigate two aims. First, propose the add-on algorithm SAZ to determine the lunar phase's data faster. Secondly, evaluate the Raspberry Pi as the main CPU due to its compact size and power as the primary processor based on the idea of a portable designed system. Then to examine the ability of the SAZ algorithm, it's combined with famous algorithms like hue, saturation and value (HSV), Canny, erosion, shape detection, and binarization has been tested on both personal computers (PC) and Raspberry Pi with the same images being compared. The results show that SAZ will help the shape detection algorithm to find the object and disclose the moon phases. Furthermore, the Raspberry Pi, functioning as a CPU, can perform as a hand-to-hand system to determine the lunar phase as a compact portable remote sensing structure.

An efficient Bayesian neural network surrogate algorithm for shape detection

We present an efficient Bayesian algorithm for identifying the shape of an object from noisy far field data. The data is obtained by illuminating the object with one or more incident waves. Bayes' theorem provides a framework to find a posterior distribution of the parameters that determine the shape of the scatterer. We compute the distribution using the Markov Chain Monte Carlo (MCMC) method with a Gibbs sampler. The principal novelty of this work is to replace the forward far-field-ansatz wave model (in an unbounded region) in the MCMC sampling with a neural-network-based surrogate that is hundreds of times faster to evaluate. We demonstrate the accuracy and efficiency of our algorithm by constructing the distributions, medians and confidence intervals of non-convex shapes using a Gaussian random circle prior.

Use of geotechnologies in mining planning in Quarries carbonated rocks - Contribution to the digital transition (Industry 4.0)

As part of the strategy for Industry 4.0, this work was developed to outline a methodology that is an important contribution to improve the efficiency and productivity of processes in the ornamental stone extraction industry. Since this sector is important for the Portuguese economy, it is imperative to optimize processes to improve their efficiency in the use of resources, economic valuation, and economic viability. Knowing that one of the main factors to take into account in the feasibility of an exploration of ornamental rocks is the density, persistence and attitude of the discontinuities present in the rock mass, a methodology is proposed that aims to map and characterize the existing discontinuities in the using the latest digital technologies and whenever possible open access (CloudCompare, Stereonet, 3D Block Expert). To this end, work was initially carried out on an active exploration front, identifying and characterizing, through the traditional method (compass and clinometer) and photogrammetry, existing discontinuities and statistically analysing their occurrence. The data analysis shows a variation in the attitude of the discontinuities in a range of -17.72 ° to 14.7 °, this variation corresponding to the strike. As a percentage, there is also a variation in the range of values, from -5.30% to 4.91%, with the reference value being the value obtained by the photogrammetric method. This step was also used to compare the acquired data and verify the variations between them depending on the method used. Photogrammetry was used with another complementary purpose, but very important for the proposed methodology, which is related to the 3D modelling of the fronts and the subsequent projection or extraction of the existing discontinuity plans. The determination of the attitude of the discontinuities was obtained through the manipulation of the point clouds obtained by the photogrammetric modelling, based on the technique of Structure for Motion [SfM] and application of the RANSAC Shape Detection algorithm of the CloudCompare® program, which allows the determination of the attitude of the discontinuities. The characterization of the discontinuities by the photogrammetric method provided the data that was used in the present study to calculate the blocometry in that sector. This was calculated using the 3D BlockExpert software, based on the exploration sequences. The program calculated the predicted volumes in each one, based on a standard dimension for the block of 2.7 × 3.0 × 2.0 meters. As a result, it was possible to compare a number of blocks the value predicted by the 449 modellings and the number of blocks produced 490. This difference of approximately 10% for this order of magnitude is acceptable and confirms the reliability of the proposed methodology. This evaluation using Geotechnologies allows data modelling to be effectively an important process in the planning of the extractive process, and with the development of this approach, it may introduce in a second phase the decision automation of the extractive process, based on economic and commercial criteria and last and third stage, the automation of the extractive process.

Proximity Sensor for Thin Wire Recognition and Manipulation

In robotic grasping and manipulation, the knowledge of a precise object pose represents a key issue. The point acquires even more importance when the objects and, then, the grasping areas become smaller. This is the case of Deformable Linear Object manipulation application where the robot shall autonomously work with thin wires which pose and shape estimation could become difficult given the limited object size and possible occlusion conditions. In such applications, a vision-based system could not be enough to obtain accurate pose and shape estimation. In this work the authors propose a Time-of-Flight pre-touch sensor, integrated with a previously designed tactile sensor, for an accurate estimation of thin wire pose and shape. The paper presents the design and the characterization of the proposed sensor. Moreover, a specific object scanning and shape detection algorithm is presented. Experimental results support the proposed methodology, showing good performance. Hardware design and software applications are freely accessible to the reader.

A robust approach to identify roof bolts in 3D point cloud data captured from a mobile laser scanner

Roof bolts such as rock bolts and cable bolts provide structural support in underground mines. Frequent assessment of these support structures is critical to maintain roof stability and minimise safety risks in underground environments. This study proposes a robust workflow to classify roof bolts in 3D point cloud data and to generate maps of roof bolt density and spacing. The workflow was evaluated for identifying roof bolts in an underground coal mine with suboptimal lighting and global navigation satellite system (GNSS) signals not available. The approach is based on supervised classification using the multi-scale Canupo classifier coupled with a random sample consensus (RANSAC) shape detection algorithm to provide robust roof bolt identification. The issue of sparseness in point cloud data has been addressed through upsampling by using a moving least squares method. The accuracy of roof bolt identification was measured by correct identification of roof bolts (true positives), unidentified roof bolts (false negatives), and falsely identified roof bolts (false positives) using correctness, completeness, and quality metrics. The proposed workflow achieved correct identification of 89.27% of the roof bolts present in the test area. However, considering the false positives and false negatives, the overall quality metric was reduced to 78.54%.

Computer Vision Based Robotic Arm Controlled Using Interactive GUI

This paper presents the design and implementation of a robotic vision system operated using an interactive Graphical User Interface (GUI) application. As robotics continue to become a more integral part of the industrial complex, there is a need for automated systems that require minimal to no user training to operate. With this motivation in mind, the system is designed so that a beginner user can operate the device with very little instruction. The application allows users to determine their desired object, which will be picked up and placed by a robotic arm into the target location. The application allows users to filter objects based on color, shape, and size. The filtering along the three parameters is done by employing a Hue-Saturation-Value (HSV) mode color detection algorithm, shape detection algorithm, size determining algorithm. Once the target object is identified, a centroid detection algorithm is employed to find the object’s center coordinates. An inverse kinematic algorithm is used to ascertain the robotic arm’s joint positions for picking the object. The arm then goes through a set of preset positions to pick up the object, place the object, and then return the arm to the initial position. The joint coordinates are forwarded to a microcontroller that sets the arm’s joint angle at each position.

Algorithm for decoding visual gestures for an assistive virtual keyboard

Text production is one of the most frequent activities on a computer, a trivial task that can be limiting for individuals affected by severe neuromotor disorders such as Amyotrophic Lateral Sclerosis (ALS) that can lead to Locked-in syndrome (LIS). These individuals need augmentative and alternative communication tools, since they may have only the eye movements as a form of communication and interaction with the outside world. This work investigates methods of interaction based on eye movement tracking and presents a virtual keyboard that utilizes gaze detection as a text input. It describes the development of the shape detection algorithm for the assistive keyboard, typed word voting from a Brazilian Portuguese lexicon and preliminary results on the decoding algorithm.

Leaf Disease Detection using Labview Imaq Vision

The intension of our project is to design a system which can identify the good leaves from the diseased ones. Image processing is a powerful tool capable of many applications. Image processing combined with Machine Vision can simulate and execute real time projects. In this project we have used LabVIEW along with IMAQ Vision to acquire real time images and process them. LabVIEW IMAQ Vision is potentially useful for agricultural products since it combines the merits of both LabVIEW and IMAQ Vision, which have graphical programming environment and rich image processing functions. The project aims to provide a brief introduction into the IMAQ vision components like Image Acquisition, Calibration, Defect detection. Major leaf diseases’ symptoms include spots or discolouration of leaves. The presence or absence of macro and micro nutrients, bug infestation and other diseases can be identified through leaves. In this project we have obtained the images through LabVIEW IMAQ vision pallet. Further on two procedures were followed – one based on colour of the leaves and other is based on spots and patterns present on the leaves. For the discolouration we first split the image into its constituent planes- RGB and CMYK, here we used Green, Cyan and Yellow planes. Then on we decided a threshold based on sample data using Linear Regression based prediction model of Machine Learning to classify the data into three states – safe, risk and high risk.The second method was detecting spots. First, we split the images into its constituent planes to convert the RGB image to Greyscale and increase the contrast using the Colour Plane Extraction tool then use the Look up table tool to further enhance the contrast. Then on locate the bright objects and then using dilation from the Morphology tool box we increase the size of the spots to increase detection rate. Using Advanced Morphology tool box we removed the boundary objects to isolate the spots. Then using the shape detection or circle detection algorithm we can detect the spots. Several samples were obtained and are successfully classified. Finally, current limitations and likely future development trends are discussed. Combining LabVIEW along with different programming algorithms can help in raising the accuracy of the system.

Comparing shape descriptor methods for different color space and lighting conditions

AbstractDetecting and recognizing objects is one of the most important uses of vision systems in nature and is consequently highly evolved. This paper aims to accurately detect an object using its shape and color information from a complex background. In particular, we evaluated our algorithm to detect 19 different integrated circuits (IC) from 10 different printed circuit boards (PCB) of different colors. We have compared three different shape descriptors for four different color space models. We have evaluated shape detection algorithms in different lighting conditions (indoor, outdoor, and controlled light source) to find suitable illumination for image acquisition. We undertook statistical hypothesis testing to find the effect of color space models and shape descriptors on the accuracy, false positive and false negative rates. While measuring accuracy, we have noted that L*a*b* color space is significantly worse, and the best result is obtained in YCbCr color space using bounding box shape descriptors for 2500 Lux using LED.

Multistep rocky slope stability analysis based on unmanned aerial vehicle photogrammetry

High-steep slope information collection and multistep rocky slope stability analysis play an important role in slope engineering. However, traditional on-site investigations suffer from terrain restrictions and data omissions. This paper presents a block identification method based on UAV (unnamed aerial vehicle) photogrammetry and its computer implementation. An SfM (structure from motion) method is introduced and a 3D reconstruction software-PhotoScan was used to build the DEM (digital elevation model) of the rock mass for real-time monitoring. Then, an RANSAC (random sample consensus) shape detection algorithm was used to search the structural planes in the point cloud model. A computer program GeoSMA-3D (geotechnical structure and model analysis-3D) has been developed to implement engineering applications and a case study was carried out which confirmed the efficiency of the method in dealing with complex surface modeling and multistep rocky slope stability analysis.

Real-Time Robotic Manipulation of Cylindrical Objects in Dynamic Scenarios Through Elliptic Shape Primitives

Robotic manipulation employs the object detection in images to create a scene awareness and locate an object's pose. In dynamic scenarios, fast multiobject detection and tracking are crucial. Many objects commonly found in household and industrial environments are represented by cylindrical shapes. Thus, it is available for robots to manipulate them through the real-time detection of elliptic shape primitives formed by the circular tops of these objects. We devise an efficient algorithm of the detection of elliptic shape primitives, which in turn enables robust and real-time robotic manipulations of such objects. The proposed algorithm incorporates the information of elliptic edge curvature, splits complex curves into arcs, classifies the arcs into different quadrants of a candidate elliptic shape, determines the quality of arc selection for ellipse fitting, and then retrieves the corresponding elliptic shape primitive. Our algorithm provides either faster or more accurate ellipse detection results than the current state-of-the-art methods, irrespective of challenging scenarios such as occluded or overlapping ellipses. This is verified by performance comparison with six state-of-the-art elliptic shape detection algorithms on four public image datasets. The algorithm has been integrated on robots to demonstrate the ability to carry out accurate robotic manipulations (tracking, grasping, and stacking) of cylindrical objects in real time. We show that the robotic manipulator, empowered by the elliptic shape primitive algorithm, performs well in complex manipulation experiments as well as dynamic scenarios.

Improving the Classification Accuracy of Accurate Traffic Sign Detection and Recognition System Using HOG and LBP Features and PCA-Based Dimension Reduction

The automatic traffic sign detection and recognition (TSDR) is one of the most useful, important and consequential method towards designing automated and driverless vehicles. It is one of the real challenges to overcome. Even in current vehicles with drivers, it is an important matter which need to be tackled for enhancing driver’s safety. In this research, we propose to use histogram-oriented gradient (HOG) and local binary patterns (LBP) approaches for feature extraction followed by PCA-based dimension reduction for accurate TSDR system. The full approach and performance are measured on Chinese traffic sign (TS) database. The development approach of the system is divided into three steps: Image processing, detection, and recognition. For the detection of traffic signs, we used an RGB color segmentation (thresholding) technique with circular Hough Transform for circular TSDR and Hough transform Algorithm for shape detection. For recognition, features are extracted using techniques HOG and LBP. Further principal component analysis (PCA) is applied for strong component extraction and classification is performed using support vector machines (SVM) classifier. The result section validates the effectiveness of using the proposed features, as the classification accuracy has been improved with respect to previously reported works on TSDR.

Approaches For A Destructive Measurement Method Of Subsurface Damages

In optical manufacturing, the depth of subsurface damages (SSD) depicts an important quality aspect of optical elements. Nowadays, the investigation methods of the damage zone are mostly destructive and allow a sampling of the substrates only. This leads to a lack of statistical reliability. In this paper, one aim is to develop an easy and cheap procedure to evaluate the probes. Therefore, a spherical polishing and chemical etching is introduced. By means of imaging processing software the acquired data is analysed, which eliminates the operator influence und increases the reproducibility. Applying binarizing and shape detection algorithms the SSD structures is detected and the number of pixels per structure is calculated. The percentage of SSD over the depth fit with an exponential curve displays a maximum depth as a single value. The development of a method to choose the best threshold value represents an approach to quantify the uncertainty of the resulting SSD-depth.

Shape Sensing Monitoring System Based on Fiber-Optic Strain Measurements: Laboratory Tests

In the context of the characterization of the shape of flying sails whilst racing, a novel method for real-time form-finding of flexural beams based on strain measurements has been developed and implemented. The very large displacements and deformations occurred on the beam pose specific demands both to the algorithm for shape detection and to the materials and sensors to use in the practical implementation, which are described and addressed in this paper. The developed method is implemented by installation of fiber Bragg grating (FBG) sensors on a beam, which are used to evaluate the curvature at specific cross-sections. The deformation curve is reconstructed by integration of local curvatures and interpolation. The effectiveness of the developed method is verified by tests on a physical model. An image-based monitoring system is further employed to validate the concept and the tests conducted with the FBG sensors. This allows the performance of an additional series of sensitivity tests in order to define the most relevant measurement parameters and characterize the accuracy of the developed method.

A New Algorithm for Shape Detection

A New Algorithm for Shape Detection

Shape Detection Algorithm for Soft Manipulator Based on Fiber Bragg Gratings

The shape of soft a manipulator cannot be sensed by the operator directly, when applied to rescue of mine disaster, science exploration, or minimally invasive surgery due to the narrow and closed environment. Shape information is sometimes important for the soft manipulator to be controlled. In order to deal with the problem of shape sensing, a shape sensing algorithm and sensor network based on Fiber Bragg Gratings (FBGs) are introduced in this paper. The shape sensing algorithm is based on piecewise constant curvature and torsion assumption, and can translate the curvature and torsion measured by sensor network into global positions and orientations of nodes. Three-dimensional experiments show that the algorithm introduced in this paper can achieve high accuracy for 3-D shapes.

Object Segmentation based on Shape Feature using Active Contour Model

Active contour models has already under study from the past many years, several methods have been proposed for forming contours. Active contour are the curves that are generated by the computer that move within an images to find boundaries of the object in an image. They are also used in image analysis and computer vision to recognize and find objects, and to describe their shape. In the proposed system Active Contour Model that segments one or many regions of the image that are visually alike to an object of interest said as prior. The probability density function is used for extracting the color feature by applying heuristic rule, and then the new proposed shape detection algorithm is used to detect the photometric feature shape of the object in an image. For accurately segmenting object in an image. The proposed system provides the accurate results on real world and synthetic datasets. General Terms Algorithms, Experiments, Results.