Wyniki wyszukiwania - BazTech

1

Design of a terrain mapping system for low-cost exploration Robots based on Stereo Vision

Zuniga William Percy Cuno, Navarro Jordan Jonathan Quispe, Diaz Juan Daniel Pocohuanca, Suarez Jesus Talavera, Angulo Andres Montoya

Przegląd Elektrotechniczny

|

2023

|

R. 99, nr 5

270--275

EN

This paper proposes a low-cost system for terrestrial mapping and exploration of inaccessible or subterranean environments by using stereo vision with two cameras, image processing and a developed algorithm based on disparity maps that reconstructs a 3D map of the explored environment. The tests were performed on a robot with two stereo vision cameras mounted on a turret with 360° freedom of movement. The tests showed that this proposed system allows to visualize the depth of the objects around the robot and builds a 360° scenario of the explored place

PL

W artykule zaproponowano niedrogi system do mapowania naziemnego i eksploracji niedostępnych lub podziemnych środowisk przy użyciu stereowizyjnego widzenia z dwiema kamerami, przetwarzania obrazu i opracowanego algorytmu opartego na mapach rozbieżności, który rekonstruuje trójwymiarową mapę badanego środowiska. Testy przeprowadzono na robocie z dwiema kamerami stereowizyjnymi zamontowanymi na wieżyczce ze swobodą ruchu 360°. Testy wykazały, że proponowany system pozwala na wizualizację głębokości obiektów wokół robota i buduje scenariusz 360° badanego miejsca.

2

Estimating the distance to an object from grayscale stereo images using deep learning

Kulawik Joanna

Journal of Applied Mathematics and Computational Mechanics

|

2022

|

Vol. 21, nr 4

60--72

EN

This article presents an innovative proposal for estimating the distance between an autonomous vehicle and an object in front of it. Such information can be used, for example, to support the process of controlling an autonomous vehicle. The primary source of information in research is monochrome stereo images. The images were made in compliance with the laws of the canonical order. The developed convolutional neural network model was used for the estimation. A proprietary dataset was developed for the experiments. The analysis was based on the phenomenon of disparity in stereo images. As a result of the research, a correctly trained model of the CNN network was obtained in six variants. High accuracy of distance estimation was achieved. This publication describes an original proposal for a hybrid blend of digital image analysis, stereo-vision, and deep learning for engineering applications.

3

Evaluation of a low-cost approach to 2-D digital image correlation vs. a commercial stereo-DIC system in Brazilian testing of soil specimens

Arza-García M., Núňez-Temes C., Lorenzana J. A., Ortiz-Sanz J., Castro A., Portela-Barral M., Gil-Docampo M., Bastos G.

Archives of Civil and Mechanical Engineering

|

2022

|

Vol. 22, no. 1

art. no. e4, 2022

EN

Due to their cost, high-end commercial 3D-DIC (digital image correlation) systems are still inaccessible for many laboratories or small factories interested in lab testing materials. These professional systems can provide reliable and rapid full-field measurements that are essential in some laboratory tests with high-strain rate events or high dynamic loading. However, in many stress-controlled experiments, such as the Brazilian tensile strength (BTS) test of compacted soils, samples are usually large and fail within a timeframe of several minutes. In those cases, alternative low-cost methods could be successfully used instead of commercial systems. This paper proposes a methodology to apply 2D-DIC techniques using consumer-grade cameras and the open-source image processing software DICe (Sandia National Lab) for monitoring the standardized BTS test. Unlike most previous studies that theoretically estimate systematic errors or use local measures from strain gauges for accuracy assessment, we propose a contrast methodology with independent full-field measures. The displacement fields obtained with the low-cost system are benchmarked with the professional stereo-DIC system Aramis-3D (GOM GmbH) in four BTS experiments using compacted soil specimens. Both approaches proved to be valid tools for obtaining full-field measurements and showing the sequence of crack initiation, propagation and termination in the BTS, constituting reliable alternatives to traditional strain gauges. Mean deviations obtained between the low-cost 2D-DIC approach and Aramis-3D in measuring in-plane components were 0.08 mm in the perpendicular direction of loading (ΔX) and 0.06 mm in the loading direction (ΔY). The proposed low-cost approach implies considerable savings compared to commercial systems.

4

Porównywanie zdjęć roślin na podstawie miar podobieństwa różniących się wykładnikiem potęgi

Kaczmarek Adam L.

Zeszyty Naukowe Wydziału Elektrotechniki i Automatyki Politechniki Gdańskiej

|

2019

|

Nr 68

13--16

PL

Artykuł przedstawia studium przypadku poświęcone zastosowaniu różnych miar podobieństwa do porównywania zdjęć roślin. Miary te mają zastosowanie w przypadku użycia układu kamer składającej się z pięciu kamer umieszczonych w bliskiej odległości. Badany układ kamer, nazwany EBCA (Equal Baseline Camera Array), składa się z jednej kamery centralnej oraz kamer bocznych. Opisane miary podobieństwa stosuje się w algorytmach widzenia stereoskopowego pozwalających na oszacowanie odległości między kamerami a obiektami widocznymi na zdjęciach. W artykule zaproponowane zostało uogólnienie stosowanych dotychczas miar tj. SAD (Sum of Absolute Differences) i SSD (Sum of Squared Differences). Przeprowadzone eksperymenty świadczą to tym, że zaproponowane miary pozwalają na redukcję błędów oszacowania polegających na otrzymaniu wyników odbiegających od prawidłowych wartości o przyjętą wartość progową.

EN

The paper presents a case study concerned with applying different similarity measures for comparing images of plants. These measures are used for a camera array which consists of five adjacent cameras. The researched array called Equal Baseline Camera Array (EBCA) contains one central camera and four side cameras. The described measures can be used with stereo vision algorithms designed for estimating distances between cameras and objects visible in images taken with the use of these cameras. The paper introduces generalizations of currently used measures such as Sum of Absolute Differences (SAD) and Sum of Squared Differences (SSD). The experiments show that the proposed measures make it possible to reduce estimation errors which occur in results differing from right values more than a selected threshold.

5

Wpływ nadmiarowych danych wejściowych na jakość map rozbieżności pozyskanych za pomocą układu pięciu kamer w konfiguracji EBMCS

Kaczmarek A. L.

Zeszyty Naukowe Wydziału Elektrotechniki i Automatyki Politechniki Gdańskiej

|

2018

|

Nr 60

41--44

PL

Artykuł dotyczy zastosowania układu kamer typu EBMCS (Equal Baseline Multiple Camera Set) składającego się z kamery centralnej oraz kamer bocznych. Na podstawie zdjęć wykonanych za pomocą tego układu można otrzymać mapy rozbieżności (ang. disparity map), które pozwalają na określenie odległości od kamer do obiektów znajdujących się w ich polu widzenia. Mapy te są wyższej jakości niż mapy otrzymane za pomocą kamery stereoskopowej. Artykuł przedstawia zastosowanie EBMCS do otrzymywania map głębi dla wybranych fragmentów uzyskanych zdjęć. Artykuł podejmuje temat wpływu rozmiaru otoczenia badanego fragmentu na jakość wyników. Opisane w artykule eksperymenty zostały przeprowadzone na podstawie dwóch zestawów testowych zawierających zdjęcia roślin.

EN

The paper describes the usage of a camera array called Equal Baseline Multiple Camera Set (EBMCS) consisting of a central camera and side cameras. The set is designed for taking images for the purpose of acquiring disparity maps which makes it possible to determine distances between a camera set and obtains located within its field of view. These maps have a higher quality than maps acquired using a stereo camera. The paper presents how EBMCS can be used for making disparity maps for only fragments of available images. The paper shows the influence of including in data processing vicinities of the fragment for which disparity maps is generated. Experiments presented in the paper were based on two test data sent containing images of plants.

6

Improve a 3D distance measurement accuracy in stereo vision systems using optimization methods’ approach

Rodríguez-Quiñonez J. C., Sergiyenko O., Flores-Fuentes W., Rivas-lopez M., Hernandez-Balbuena D., Rascón R., Mercorelli P.

Opto-Electronics Review

|

2017

|

Vol. 25, No. 1

24--32

EN

This paper presents a 3D distance measurement accuracy improvement for stereo vision systems using optimization methods A Stereo Vision system is developed and tested to identify common uncertainty sources. As the optimization methods are used to train a neural network, the resulting equation can be implemented in real time stereo vision systems. Computational experiments and a comparative analysis are conducted to identify a training function with a minimal error performance for such method. The offered method provides a general purpose modelling technique, attending diverse problems that affect stereo vision systems. Finally, the proposed method is applied in the developed stereo vision system and a statistical analysis is performed to validate the obtained improvements.

7

Calibration of vision systems operating in separate coordinate systems

Kacperski D., Sankowski W., Włodarczyk M., Grabowski K.

International Journal of Microelectronics and Computer Science

|

2016

|

Vol. 7, nr 1

10--15

EN

Over the last years, the use of multiple cameras is becoming more and more popular in today’s computer vision systems. Such approach is widely used in many applications, such as navigation of autonomous mobile robots, video surveillance, the movie industry, augmented reality or people tracking and identification systems. Surprisingly, little attention is paid in the literature to the practical calibration procedures that can be employed to map space between various vision systems. Therefore, in this paper a novel approach that allows to map space between cameras with different coordinate systems: Cartesian and polar is presented. The practical problems that occurs in such scenarios are analysed and thoroughly discussed. The authors present stepby-step description of the proposed calibration procedure. A series of experiments were conducted to confirm the correctness of the presented approach and to demonstrate how to apply the developed solution in practical applications. The proposed method does not require any additional equipment beyond the standard calibration chessboard. The achieved results indicate, that for evaluated cameras configuration, the maximum mapping error for the horizontal and vertical axes does not exceed 0.6°. Obtained results are encouraging and useful for development of similar solutions.

8

A Survey of Passive 3D Reconstruction Methods on the Basis of More than One Image

Siudak M., Rokita P.

Machine Graphics and Vision

|

2014

|

Vol. 23, No. 3/4

57--117

EN

The research on the 3D scene reconstruction on the basis of its images and video recordings has been in progress for many years. As a result there is a number of methods concerning how to manage the reconstruction problem. This article's goal is to present the most important methods of reconstruction including stereo vision, shape from motion, shape from defocus, shape form silhouettes. shape from photo-consistency. All the algorithms explained in this article can be used on images taken with casual cameras in an ordinary illuminated scene (passive methods).

9

Ocena dokładności stereowizyjnej metody inspekcji dróg

Staniek M.

Budownictwo i Architektura

|

2014

|

Vol. 13, nr 4

259--266

PL

Ocena dokładności stereowizyjnej metody inspekcji dróg została zrealizowana na podstawie analizy rozkładu różnic pomiędzy pomiarami metody stereowizyjnej i metody pomiaru bezpośredniego z wykorzystaniem dalmierza laserowego. Przeprowadzona analiza ma zweryfikować uzyskany charakter błędów odwzorowania nawierzchni drogi. Została przeprowadzona na zbiorze danych pozyskanych podczas realizacji pomiarów w 160 przekrojach badawczych dla różnych nawierzchni drogowych o różnym stopniu degradacji. Oceniana metoda inspekcji stanu nawierzchni drogowych bazuje na metodzie stereowizyjnej odwzorowania nawierzchni drogi. Opis przestrzenny jest wyznaczany na podstawie stereo-obrazów pozyskany podczas wykonywania sekwencji zdjęć z pojazdu pomiarowego poruszającego się po badanym odcinku drogi. Właściwa analiza danych obrazowych i zastosowanie przekształceń matematycznych umożliwia określenie parametrów technicznych i eksploatacyjnych drogi. Opis przestrzenny pozwala na precyzyjną ocenę stanu nawierzchni drogi, która w tradycyjnych metodach obrazowania bez informacji dotyczącej głębi jest trudna do realizacji i często obarczona błędami kwalifikacji poszczególnych uszkodzeń nawierzchni.

EN

The estimation of stereovision precision in road inspection was determined by the analysis of the distribution of differences between measurements: the stereo vision method and the method of direct measurement with the use of laser distance meter. The carried out analysis is aimed at verifying the type of mapping error of a road surface. The input data was obtained from 160 measurement sections which feature both a different type and a different condition of road pavement. The estimated method of road inspection is based on the stereo vision method of surface representation. Spatial representation of the road is obtained from the images recorded through taking stereo sequences of images by the measurement vehicle moving along the studied section of the road. The proper analysis of the image-based data and the application of mathematical transformations allow for determination of technical and functional parameters of the road. Spatial description allows for a precise evaluation of the state of a road pavement, which in traditional methods of image processing, without information about the depth, is difficult to be achieved and often burdened with errors of qualification of road distresses.

10

Wide-angle vision for road views

Huang F., Fehrs K. K., Hartmann G., Klette R.

Opto-Electronics Review

|

2013

|

Vol. 21, No. 1

1-22

EN

The field-of-view of a wide-angle image is greater than (say) 90 degrees, and so contains more information than available in a standard image. A wide field-of-view is more advantageous than standard input for understanding the geometry of 3D scenes, and for estimating the poses of panoramic sensors within such scenes. Thus, wide-angle imaging sensors and methodologies are commonly used in various road-safety, street surveillance, street virtual touring, or street 3D modelling applications. The paper reviews related wide-angle vision technologies by focusing on mathematical issues rather than on hardware.

11

Research on camera calibration using new optimization strategy

Li L.

Opto-Electronics Review

|

2011

|

Vol. 19, No. 4

454-461

EN

An important task for stereo vision is camera calibration, whose goal is to obtain the intrinsic and extrinsic parameters of each camera. This paper proposes a new accurate calibration method with multilevel process of camera parameters. In or- der to improve the calibration accuracy, a sub-pixel corner detection method is presented. We start with several views of a planar calibration to obtain some intrinsic camera parameters and to build an accurate model with lens distortion on a planar calibration target. Flexibly making use of geometry imaging theory, our algorithm obtains all the parameters through logical organization of solving order, accordingly avoids obtaining possible local optimized problem when solving the non-linear equation, gets over the relativity influence of every unknown parameters of traditional calibration way, and makes the error distributed among the constraint relation of parameters. Experiments with real images are carried out to verify the image correction effect and numerical robustness of our results. Compared with classical calibration techniques, that use expensive equipment and complicated mathematical computation, the proposed technique, which was verified by experiment, achieves high accuracy and reliable parameters.

12

Concept of binocular stereo vision system for inspection of surfaces

Garbacz P., Giesko T.

Problemy Eksploatacji

|

2010

|

nr 4

193-205

EN

The article presents the idea of a binocular stereo vision system for surface inspection and discusses the basic characteristics of epipolar geometry and the advantages and limitations of the methods of representation that use it. The structure of the vision system, basic optical parameters and the configuration of the equipment are presented. The assumed practical implementation possibilities are determined.

PL

W artykule przedstawiona została koncepcja dwutorowego systemu stereowizyjnej inspekcji powierzchni. Omówione zostały podstawowe cechy geometrii epipolarnej oraz zalety i ograniczenia metod obrazowania z jej wykorzystaniem. Zaprezentowana została struktura układu wizyjnego, podstawowe parametry optyczne oraz konfiguracja sprzętowa. Określone zostały przewidywane możliwości zastosowań praktycznych.

13

An Iterative Parameter Estimation Method for Observation Models with Nonlinear Constraints

Dang T.

Metrology and Measurement Systems

|

2008

|

Vol. 15, nr 4

421-432

EN

This article presents a parameter estimation algorithm for observation models with nonlinear constraints. A prominent example that belongs to this category is the continuous auto-calibration of stereo cameras. Here, our knowledge of the relation between the available measurements and the desired parameters is given by a nonlinear implicit constraint equation. An estimation method derived from an Iterated Extended Kalman Filter is designed for this application. Experiments are conducted with synthetic and real data. The proposed algorithm provides very good results and is readily applicable to a wider range of applications.

14

The calibration method for stereoscopic vision system

Titov V. S., Degtyarev S. V., Truphanov M. I.

Machine Graphics and Vision

|

2008

|

Vol. 17, No. 4

373-387

EN

Stereoscopic vision systems are used not only in visual design computing but also in many other applications. In stereoscopic vision, an important property is the accuracy of three-dimensional reconstruction. This property depends considerably on the quality of the vision system calibration. The known solutions to the calibration problem are based on determining calibration parameters from an image of a special pattern. Our method allows calibration of the stereoscopic vision without such a special pattern. The calibration includes the following basic stages: selection of an object used in the calibration (one a priori unknown object instead of a special model object) which is chosen from a set of objects existing in a working scene, calibration of the angles between two cameras which are part of the stereoscopic vision system, and calibration of the distances between two cameras. The calibration parameters are calculated with the aid of images of calibration objects. This approach allows us to perform an adaptive calibration of the vision system (automatic calibration is performed from time to time when necessary) because this process does not require placing of the special calibration object in the working scene, it does not interrupt execution of main function of the vision system and increases the calibration accuracy since possible errors which may be introduced during the placement of the calibration object do not affect the result of the calibration.

15

A New 3D Sensor System by Using Virtual Camera Model and Stereo Vision for Mobile Robots

Lee H., Kim M. N., Cho H.

Journal of Automation Mobile Robotics and Intelligent Systems

|

2008

|

Vol. 2, No. 4

38-44

EN

So many researches have been conducted to develop 3D sensing method for mobile robots. Among them, the optical triangulation, a well-known method for 3D shape measurement, is also based on active vision sensing principle for mobile robot sensor system, so that the measurement result is robust to illumination noises from environments. Due to this advantage it has been popularly used. However, to obtain the 3D information of environment needs a special scanning process and scanning actuators need. To omit this scanning process multi-line projection methods have been widely researched. However, they suffer from an inherent limitation: The results of multi-line projection method commonly have measurement errors because of 2 -ambiguity caused by regularly repeated multiline laser pattern. In this paper, to overcome 2 -ambiguity effectively, we introduce a novel sensing method for a 3D sensing system using multi-line projection and stereo cameras, based on the virtual camera model and stereovision algorithm. To verify the efficiency and accuracy of the proposed method, a series of experimental tests is performed.

16

An improved neural networks for stereo-camera calibration

Xing Y. J., Xing J., Sun J., Hu L.

Journal of Achievements in Materials and Manufacturing Engineering

|

2007

|

Vol. 20, nr 1-2

315-318

EN

Purpose: Improve the generalization capability and speed of back-propagation neural network (BPNN). Design/methodology/approach: In this paper, CCD cameras are calibrated implicitly using BP neural network by means of its ability to fit the complicated nonlinear mapping relation. Conventional BP algorithms easily fall into part-infinitesimal, slowing speed of convergence and exorbitance training that will influence the training result, delay convergence time and debase generalization capability. During our experiments, dense sample data are acquired by using high precisely numerical control platform, and the variances error (PVE) is adopted during training the neural network. Findings: Experiments indicate that the neural network used PVE has great generalization. The error percentages obtained from our set-up are limitedly better than those obtained through Mean Square Error (MSE). The system is generalization enough for most machine-vision applications and the calibrated system can reach acceptable precision of 3D measurement standard. Research limitations/implications: The value needs to be decided by experiments, and the reconstruction images will be distorted if the value is more than 6. Originality/value: The variances error is be adopted in BPNN first.

17

Self-matching of stereoscopic images without camera calibration

Larabi S.

Machine Graphics and Vision

|

2001

|

Vol. 10, No. 3

333-351

EN

In computer vision applications where the calibration object is not avaible , it is useful to use an uncalibrated stereoscopic head. Even in this case, to calculate the three-dimensional structure of the viwed scene, the stereo matching is considered as the key step in stereo vision analysis. This paper presents a contribution to resolve this problem when an uncalibrated stereo rig is involved in a visual task. We propose an algorithm for self-matching of stereoscopic images of indoor scenes. Based on projective geometry, the principal idea of the method is to estimate the epipole position assuming a set of matched 2D surfaces. A voting approach is used to select the correct matching which produce the same solution. In practice, as the stereo images are noisy, we propose a mathematical analysis of the uncerainty measure. We assume that the vertices are noisy, and we propagate the effect of this noise in the different stages of the proposed algorithm. The new version of the algorithm allows to calculate the region where the epipole point appertains, called the "epipolar region". The stereo matching algorithm has been tested on both synthetic and real images, and the number of lines matched demostrates the robustness of the geometric method.

18

Novel feature-based stereo matching method that employs tensor representation on local pixels neighborhoods in images

Cyganek B.

Machine Graphics and Vision

|

2001

|

Vol. 10, No. 3

289-316

EN

Stereo matching techniques have evolved substantially throughout recent years. However, the problem of unambigous stereo points matching, especially in presence of object occlusions, as well as images noise and distortions, remains still open. In this paper, a novel feature-based stereo matching method, based on tensor representation of local structures in digital images, has been described. Application of a structural tensor enables more reliable matching of locally coherent structures, representing averaged dominant gradients in local neighborhoods rather than sparse points. The presented work has been completed with many experiments that confirmed its usefulness, especially in a case of real stereo images.

19

Capturing mosaic-based panoramic depth images with a single standard camera

Peer P., Solina F.

Machine Graphics and Vision

|

2001

|

Vol. 10, No. 3

369-397

EN

In this paper we present a panoramic depth imaging system. The system is mosaic-based which means that we use a single rotating camera and assemble the captured images in a mosaic. Due to a setoff of the camera's optical center from the rotational center of the system we are able to capure the motion parallax effect, which enables the stereo reconstruction. The camera rotating on a circular path with the step defined by an angle equivalent to a single column of the captured image. The equation for depth estimation can be easily extracted from the system geometry. To find the corresponding points on a stereo pair of panoramic images, the epipolar geometry needs to be determined. It can be shown that the epipolar geometry is very simple if we are doing the reconstruction based on a symmetric pair of stereo panoramic images. We get a symmetric pair of stereo pamoramic images when we take symmetric columns on the left and on the rihgt side from the captured image center column. Epipolar lines of the symmetrical pair of panoramic images are image rows. We focuse mainly on the system analysis. The system performs well in the reconstruction of small indoor spaces.

20

A neurocomputing approach to the correspondence problem in stereo vision based upon an unsupervised neural network

El-Henawy I., Fouda Y. M., Enab Y. M.

Machine Graphics and Vision

|

2001

|

Vol. 10, No. 1

29-46

EN

The stereo matching problem is one of the most widely stidied problems in stereo vision. In this paper we introduce a neurocomputing approach to the local stereo matching problem using edge segments as features with several attributes. Most classical local stereo matching techniques use features representing objects in both images and compute the minimum values of attribute differences. pajares et al ([21]) had verified that the differences in attributes, for the true matches, cluster in a cloud around a center. We used the self-organizing neural network to get the best cluster center. Based on the similarity constraint, we compute the minimum Mahalaobis distances between the differences of the attributes for a new pair of features and the cluster center to classify this new pair as true or false match. Experimental results with two real pairs of images are shown.