Wyniki wyszukiwania - BazTech

1

Local Generating Map System Using Rviz ROS and Kinect Camera for Rescue Robot Application

Muharom Syahri, Firmansyah Riza Agung, Prabowo Yuliyanto Agung

International Journal of Electronics and Telecommunications

|

2023

|

Vol. 69, No. 3

621--626

EN

This paper presents a model to generate a 3D model of a room, where room mapping is very necessary to find out the existing real conditions, where this modeling will be applied to the rescue robot. To solve this problem, researchers made a breakthrough by creating a 3D room mapping system. The mapping system and 3D model making carried out in this study are to utilize the camera Kinect and Rviz on the ROS. The camera takes a picture of the area around it, the imagery results are processed in the ROS system, the processing carried out includes several nodes and topics in the ROS which later the signal results are sent and displayed on the Rviz ROS. From the results of the tests that have been carried out, the designed system can create a 3D model from the Kinect camera capture by utilizing the Rviz function on the ROS. From this model later every corner of the room can be mapped and modeled in 3D.

2

Ocena precyzji działania kontrolera Kinect

Mieszawski Piotr, Szymczyk Tomasz

Journal of Computer Sciences Institute

|

2021

|

Vol. 18

15--21

PL

Tematem tej pracy jest ocena precyzji działania kontrolera Kinect. Na potrzeby tego został opracowana metodyka badawcza oraz przygotowane stanowisko pomiarowe. Następnie została stworzona aplikacja, która wychwytuje gest rzutu użytkownika oraz symuluje lot wirtualnej piłki. Na podstawie tego wykonano pomiary, polegające na określeniu różnicy kątów pomiędzy tym jak poruszała się dłoń, a jak to zostało wykryte przez aplikacje oraz określeniu różnicy pomiędzy odległością rzutu wykonanego w rzeczywistości a w VR (ang. Virtual Reality). Analiza tych wyników pozwoliła określić precyzje kontrolera.

EN

The subject of this work is to evaluate the precision of the Kinect controller operation. Research study was performed and a measuring stand have been prepared. Then an application was created that captures the user's throw gesture and simulates the flight of a virtual ball. Based on this, measurements were made to determine the difference between hand movement and it’s detection by the application, and differences among throw made in real life and in VR. The analysis of these results allowed the accuracy of the controller to be assessed.

3

Economical methods for measuring road surface roughness

Grabowski D., Szczodrak M., Czyżewski A.

Metrology and Measurement Systems

|

2018

|

Vol. 25, nr 3

533--549

EN

Two low-cost methods of estimating the road surface condition are presented in the paper, the first one based on the use of accelerometers and the other on the analysis of images acquired from cameras installed in a vehicle. In the first method, miniature positioning and accelerometer sensors are used for evaluation of the road surface roughness. The device designed for installation in vehicles is composed of a GPS receiver and a multi-axis accelerometer. The measurement data were collected from recorded ride sessions taken place on diversified road surface roughness conditions and at varied vehicle speeds on each of examined road sections. The data were gathered for various vehicle body types and afterwards successful attempts were made in constructing the road surface classification employing the created algorithm. In turn, in the video method, a set of algorithms processing images from a depth camera and RGB cameras were created. A representative sample of the material to be analysed was obtained and a neural network model for classification of road defects was trained. The research has shown high effectiveness of applying the digital image processing to rejection of images of undamaged surface, exceeding 80%. Average effectiveness of identification of road defects amounted to 70%. The paper presents the methods of collecting and processing the data related to surface damage as well as the results of analyses and conclusions.

4

Badanie stanu nawierzchni drogowej z wykorzystaniem uczenia maszynowego

Grabowski D., Czyżewski A.

Magazyn Autostrady

|

2018

|

Nr 8-9

79--84

PL

W artykule opisano budowę systemu informowania o stanie nawierzchni drogowej z wykorzystaniem metod cyfrowego przetwarzania obrazów oraz uczenia maszynowego. Efektem wykonanych prac badawczych jest eksperymentalna platforma, pozwalająca na rejestrację uszkodzeń na drogach, system do analizy, przetwarzania i klasyfikacji danych oraz webowa aplikacja użytkownika do przeglądu stanu nawierzchni w wybranej lokalizacji.

EN

Damage to the road surface is caused by many factors: from atmospheric conditions to high traffic to erosion. Poor road conditions cause damage to vehicles, high fuel consumption and accidents. Investigations of this condition, due to their high costs, are often performed manually. The steps of designing and implementing a system for the automatic identification of road pavement and creating a web application for informing the user about the road condition are presented in the paper. A set of algorithms for processing RGB and depth images was created. A neural network model has been trained and used to classify road defects. The obtained research results show 83% efficiency of using digital image processing in discarding images without any damages. In the case of pavement defects classification, the achieved average efficiency approximated 70%.

5

A set of depth sensor processing ROS tools for wheeled mobile robot navigation

Drwięga M., Jakubiak J.

Journal of Automation Mobile Robotics and Intelligent Systems

|

2017

|

Vol. 11, No. 2

48--56

EN

The paper presents a set of soŌware tools dedicated to support mobile robot navigaƟon. The tools are used to process an image from a depth sensor. They are implemented in ROS framework and they are compaƟble with standard ROS navigaƟon packages. The soŌware is released with an open source licence. First of the tools converts a 3D depth image to a 2D scan in polar coordinates. It provides projecƟon of the obstacles, removes the ground plane from the image and compensates sensor Ɵlt angle. The node is faster than the standard node within ROS and it has addiƟonal funcƟons increasing range of possible applicaƟons. The second tool allows detecƟon of negaƟve obstacles i.e. located below the ground plane level. The third tool esƟmates height and orientaƟon of the sensor with RANSAC algorithm applied to the depth image. The paper presents also the results of usage of the tools with mobile plaƞorms equipped with MicrosoŌ Kinect sensors. The plaƞorms are elements of the ReMeDi project within which the soŌware was developed.

6

3D object detection and recognition for robotic grasping based on RGB-D images and global features

Czajewski W., Kołomyjec K.

Foundations of Computing and Decision Sciences

|

2017

|

Vol. 42, No. 3

220--237

EN

This paper describes the results of experiments on detection and recognition of 3D objects in RGB-D images provided by the Microsoft Kinect sensor. While the studies focus on single image use, sequences of frames are also considered and evaluated. Observed objects are categorized based on both geometrical and visual cues, but the emphasis is laid on the performance of the point cloud matching method. To this end, a rarely used approach consisting of independent VFH and CRH descriptors matching, followed by ICP and HV algorithms from the Point Cloud Library is applied. Successfully recognized objects are then subjected to a classical 2D analysis based on color histogram comparison exclusively with objects in the same geometrical category. The proposed two-stage approach allows to distinguish objects of similar geometry and different visual appearance, like soda cans of various brands. By separating geometry and color identification phases, the applied system is still able to categorize objects based on their geometry, even if there is no color match. The recognized objects are then localized in the three-dimensional space and autonomously grasped by a manipulator. To evaluate this approach, a special validation set was created, and additionally a selected scene from the Washington RGB-D Object Dataset was used.

7

Zastosowanie technologii Kinect w ocenie nachylenia krzywizn kręgosłupa w płaszczyźnie strzałkowej

Jurek M., Janus O.

Aktualne Problemy Biomechaniki

|

2017

|

z. 12

29--34

PL

W pracy przedstawiono propozycję rozwiązania sprzętowego, które umożliwia określenie prawidłowości postawy ciała człowieka poprzez wyznaczenie kąta kifozy piersiowej (P2) oraz kąta lordozy lędźwiowej (P3), wykorzystując urządzenie Kinect dla Xbox 360 oraz oprogramowanie Kinect for Windows SDK.

EN

The paper depicts the hardware solution proposal, which enables the assessment of the regularity of human posture. The measurement relies on the determination of chest kyphosis angle (P2) and lumbar lordosis angle (P3). With this end in view, Kinect device for Xbox 360 and Kinect for Windows SDK software were used.

8

Analiza zakresu ruchów w stawach kończyny górnej podczas swingu golfowego z wykorzystaniem urządzenia kinect oraz w warunkach rzeczywistych - badania pilotażowe

Guzik-Kopyto A., Reich M., Bieniek A.

Aktualne Problemy Biomechaniki

|

2017

|

z. 12

21--28

PL

Golf to dyscyplina sportu, wymagająca od gracza bardzo dużej precyzji. Celem niniejszej pracy była analiza kinematyki kończyny górnej podczas swingu golfowego w warunkach rzeczywistych oraz z wykorzystaniem urządzenia Kinect. Pilotażowe badania doświadczalne przeprowadzono na jednej osobie, która wykonywała swing golfowy 10 razy w każdym etapie badań. Po przeprowadzeniu analizy kinematycznej zaobserwowano porównywalne wyniki dla obydwu etapów przeprowadzonych badań. Największą ruchomość podczas wykonywania swingu golfowego zaobserwowano w stawie łokciowym.

EN

Golf is a sport discipline, which require of the player very high precision. The aim of this study was the kinematic analysis of the upper limb during golf swing using the Kinect device and in real conditions. Pilot experimental studies were carried out on the one person, who was obligated to perform swing golf 10 times in every stage of research. Kinematic analysis has shown that the results for both phases were comparable. The greatest mobility during golf swing was observed in the elbow’s joint.

9

Human motion capture using Kinect and third party sensors

Żorski W., Pałys T.

Przegląd Teleinformatyczny

|

2016

|

T. 4, Nr 1-2 (41)

17--38

EN

The paper describes an applicable solution combining advantages of the Kinect device and properties of appropriable third party sensors. The elaborated solution allows tracking of a human arm along with recognition of basic hand gestures. This way it may be possible to remotely control a manipulator or a robotic arm performing some actions determined by a user's hand. The Kinect is mainly used to preliminary calibrate the system and for verification purposes. The system was designed using kinematics-based approach with rigid transformation combining rotations and translations. Matrix transformation operators were exchanged by dual quaternions as quaternions are native for the used devices. Additionally, as this is not a trivial mathematical tool, the machinery of dual quaternions has been introduced and its implementation is given.

PL

Artykuł przedstawia rozwiązanie problemu śledzenia ręki poruszającego się człowieka, wraz z rozpoznawaniem prostych gestów, przy wykorzystaniu właściwości urządzenia Kinect oraz dodatkowych sensorów. Rozwiązanie może być stosowane do zdalnego sterowania manipulatorem za pomocą ręki i gestów dłoni. Urządzenie Kinect służy głównie na etapie kalibracji systemu oraz w celu weryfikacji jego działania. System został pierwotnie zaprojektowany przy użyciu standardowej kinematyki manipulatora, opartej na macierzowych operatorach przekształcenia, które następnie zostały zastąpione przez kwaterniony dualne, gdyż są one wykorzystywane natywnie przez zastosowane urządzenia. Artykuł zawiera krótkie wprowadzenie do kwaternionów dualnych oraz ich przykładową implementację w środowisku Scilab.

10

A low cost depth sensor-based computer control system for the disabled people

Połok B., Bilski P.

Measurement Automation Monitoring

|

2016

|

Vol. 62, No. 9

292--296

EN

The paper presents the system for support interaction of disabled people using a low-cost computer module. The system is based on the Microsoft Kinect device. Its usability strongly depends on the designed software. The architecture of both software and hardware part of the system is discussed. The tests performed on human volunteers are presented as well. The conducted research confirms the usability of the system, showing its disadvantages and limitations.

11

Recognition of Hand Posture Based on a Point Cloud Descriptor and a Feature of Extended Fingers

Warchoł D., Wysocki M.

Journal of Automation Mobile Robotics and Intelligent Systems

|

2016

|

Vol. 10, No. 1

48--57

EN

Our work involves hand posture recognition based on 3D data acquired by the KinectTM sensor in the form of point clouds. We combine a descriptor built on the basis of the Viewpoint Feature Histogram (VFH) with additional feature describing the number of extended fingers. First, we extract a region corresponding to the hand and then a histogram of the edge distances from the palm center is built. Based on quantized version of the histogram we calculate the number of extended fingers. This information is used as a first feature describing the hand which, together with VFH-based features, form the feature vector. Before calculating VFH we rotate the hand making our method invariant to hand rotations around the axis perpendicular to the camera lens. Finally, we apply nearest neighbor technique for the posture classification. We present results of crossvalidation tests performed on a representative dataset consisting of 10 different postures, each shown 10 times by 10 subjects. The comparison of recognition rate and mean computation time with other works performed on this dataset confirms the usefulness of our approach.

12

Using gesture and voice commands for the Tribot robot control

Czekalski P., Golenia M., Lipka Ł., Tokarz K.

Studia Informatica

|

2015

|

Vol. 36, nr 3

11--25

EN

Presented project integrates seamlessly modern device control methods into one, solid solution. The Project is in touch-less control algorithm to the robotics, considered as a technology sampler for feature industrial usage. It implements gesture and voice recognition based solution to control the mobile Tribot robot driving over flat, two dimensional surface. It integrates Microsoft Kinect sensor, Lego Mindstorms NXT robot and a PC computer all together. It also provides voice con-trolled calibration of the human to machine interface.

PL

W dokumencie opisano projekt, w którym zintegrowano nowoczesne metody sterowania bezdotykowego robotem mobilnym przy użyciu gestów oraz rozpoznawania głosu. Przedmiotem sterowania jest robot zbudowany na platformie Lego Mindstorms NXT, poruszający się po dwuwymiarowej przestrzeni. Rozwiązanie integruje sensor Microsoft Kinect do sterowania robotem oraz metodę kalibracji położenia użytkownika za pomocą rozpoznawania komend głosowych.

13

Motion capture using multiple Kinect controllers

Kopniak P.

Przegląd Elektrotechniczny

|

2015

|

R. 91, nr 8

26--29

PL

Artykuł opisuje proces budowy systemu akwizycji ruchu (ang. motion capture) z wykorzystaniem kontrolerów Microsoft Kinect 360 i Kinect One. Przedstawiono w nim sposób użycia kilku kontrolerów równolegle i sposób wykorzystania darmowych szkieletów programistycznych do stworzenia oprogramowania do rejestracji ruchu. Artykuł zawiera wyniki porównania systemów akwizycji ruchu wykorzystujących jeden oraz dwa kontrolery jednocześnie oraz wskazuje ścieżki przyszłego rozwoju systemu.

EN

The following paper describes the process of developing a motion capture system with the use of Microsoft Kinect 360 and Kinect One controllers. The article presents how to use multiple Kinect controllers parallely and how to employ the existing freeware programming frameworks to produce an appropriate motion capture software. The article shows the results of comparison of single and multiple Kinect motion capture systems. The summary of this study will collect the research results and include some suggestions for the future development of this motion capture system.

14

Significance of features in object recognition using depth sensors

Harasymowicz-Boggio B., Chechlinski L, Siemiatkowska B.

Optica Applicata

|

2015

|

Vol. 45, nr 4

559--571

EN

This article concerns a key topic in the field of visual object recognition – the use of features. Object recognition algorithms typically rely on a fixed vector of pre-selected features extracted from 2D or 3D scenes, which are then analyzed with various classification techniques. On the other hand, the activation of particular features in biological vision systems is hierarchical and data-driven. To achieve a deeper understanding of the subject, we have introduced several mathematical tools to estimate multiple RGB-D features’ relevance for different object recognition tasks and conducted statistical experiments involving our database of high quality 3D point clouds. From the thorough analysis of the obtained results we draw conclusions that may be useful to design better, more adaptive object recognition algorithms.

15

Sterowanie robotem za pomocą gestów z wykorzystaniem czujnika ruchu

Wieszok Z., Lipka Ł.

Medical Robotics Reports

|

2014

|

vol. 3

46--51

PL

W niniejszym artykule opisano projekt, w którym przedstawiona została metoda bezdotykowego sterowania robota z zastosowaniem czujnika ruchu Kinect. Obiektem sterowanym jest jeżdżący robot składający się z: podwozia, silnika oraz modułu do komunikacji. Sterowanie odbywa się za pomocą sensora Microsoft Kinect wraz z odpowiednią analizą gestów sterujących. Przedstawiono algorytm sterowania oraz propozycje rozwiązania problemów wynikających z charakterystyki metody sterowania. Poruszono kwestię dopasowania algorytmu do budowy fizycznej osoby sterującej, zwiększenie dokładności sterowania w kluczowych zakresach oraz problemu śledzenia wielu osób znajdujących się przed czujnikiem.

EN

This paper describes the project that demonstrates the use of the Kinect motion sensor to control the robot using hand gestures. The controlled object is robot comprising of: the chassis, electronic components, engine and communication module. The control is done using the Microsoft Kinect sensor and proper analysis of controls gesture.

16

Top-view people counting in public transportation using Kinect

Malawski F.

Challenges of Modern Technology

|

2014

|

Vol. 5, no. 4

17--20

EN

This article describes a method for people counting in public transportation. In this particular scenario, various body poses corresponding to holding handrails must be accounted for. Kinect sensor mounted vertically has been employed to acquire a database of images of 1-5 persons, with and without body poses of holding a handrail. An algorithm has been devised for robust people counting, consisting of multiple steps. The handrails are removed by substituting an average image of the handrails from the image with persons holding a handrail. The image is then processed in blocks in order to find potential local maxima, which are subsequently verified to find head candidates. Finally, non-head objects are filtered out, based on the ratio of pixels with similar and near-zero value, in the neighbourhood of the maxima. The method has an average accuracy of 91% and has proved to handle well the handrails in the depth maps.

17

The use of Kinect sensor to control manipulator with electrohydraulic servodrives

Gośliński J., Owczarek P., Rybarczyk D.

Pomiary Automatyka Robotyka

|

2013

|

R. 17, nr 2

481-486

EN

The article describes the control of the 2-axis electrohydraulic manipulator by the human-hand motion. To recognition of skeleton points the Kinect sensor was used. In this application the information about coordinates of shoulder, elbow and hand was used to compute of inverse kinematic in manipulator. In investigation the accuracy of control by human’s hand motion was tested. The aim of study was to find a new of control method without commonly used joysticks to create human-machine interface.

PL

Artykuł opisuje sterowanie 2-osiowym manipulatorem z napędami elektro-hydraulicznymi za pomocą ruchów ręki człowieka. Do rozpoznawania punktów szkieletowych człowieka wykorzystany jest Kinect. W tej aplikacji informacje o współrzędnych barku, łokcia i ręki wykorzystywane były do wyliczenia kinematyki odwrotnej manipulatora. W badaniach testowano precyzję sterowania przez ruch ręki człowieka. Celem pracy było znalezienie nowej metody sterowania urządzeniami bez użycia powszechnie stosowanych joysticków, aby utworzyć interfejs komunikacji pomiędzy człowiekiem a maszyną.

18

Depth map color constancy

Ebner M., Hansen J.

Bio-Algorithms and Med-Systems

|

2013

|

Vol. 9, no. 4

167--177

EN

A human observer is able to determine the color of objects independent of the light illuminating these objects. This ability is known as color constancy. In the first stages of visual information processing, data are analyzed with respect to wavelength composition, orientation, motion, and depth. With this contribution, we investigate whether depth information can help in estimating the color of the objects. We assume that local space average color is computed in V4 through resistively coupled neurons to estimate the color of the illuminant. We show how this computational model can be extended to incorporate depth information.

19

Zastosowanie kontrolera Kinect oraz zestawu czujników inercyjnych do rejestracji ruchu człowieka dla potrzeb rzeczywistości wirtualnej oraz sterowania

Budziszewski P.

Pomiary Automatyka Robotyka

|

2012

|

R. 16, nr 2

189-193

PL

W artykule opisano sposób wykorzystania kontrolera Microsoft Kinect oraz zestawu czujników inercyjnych i magnetycznych do rejestracji ruchu człowieka dla potrzeb rzeczywistości wirtualnej. Za pomocą kontrolera Kinect rejestrowane jest położenie głowy oraz rąk człowieka. System inercyjny wykorzystywany jest do rejestracji rotacji. Jest ona wyznaczana na podstawie żyroskopu. Akcelerometr i magnetometr wykorzystywane są do wyznaczania położenia początkowego oraz kompensacji błędów całkowania sygnałów z żyroskopu.

EN

This paper describes the method of using Microsoft Kinect controller and a set of inertial and magnetic sensors for recording human movement for virtual reality applications. Positions of the head and hands are recorded using the Kinect controller. Inertial system is used to record the rotation. It is calculated on the basis of the gyroscope. Accelerometer and magnetometer are used to determine the initial position and compensation of gyroscope errors.

20

Natural User Interfaces (NUI): review

Glonek G., Pietruszka M.

Journal of Applied Computer Science

|

2012

|

Vol. 20, nr 2

27-45

EN

The article summarizes and systematizes knowledge concerning natural user interfaces. The most important facts related to this problem have been supplemented with examples of possible practical use of such type of human-computer communication. Moreover, the article contains descriptions of three most popular controllers: Microsoft Kinect, Nintendo Wii and Sony Move.