in

AR System New Technology for Maintenance and Repair

We are dealing with many issues in our actual life. Now we live in the era of science and know-how.so we are attempting to give any problem’s solution through the use of science and technology. I select this topic for some causes. A few months ago my cell phone just isn’t working. Everything was okay but incoming and outgoing calls are not allowed simply due to networking problem. I go to a mobile repairing shop and they charged me 1000tk to solve this issue.

Don’t waste time Get a verified expert to help you with Essay


But after some hours they mentioned me my phone is okay and networking system is also okay. They mentioned me to switch my sim card from buyer care. And they took 1000tk from me. On that time I was not something to say. And I waste my 1000tk. Not only I waste my money but additionally waste my time. I am a scholar of computer science and engineering so after a couple of days on that incident I heard about augmented actuality system in my artificial intelligence class.

My course instructor showed us a video where an electronic device is repaired by utilizing augmented actuality. It was like after we take our mobile phone in front the electrical swap board the mobile phone provides instruction how to solve the issue step by step. Then I thought it is going to be useful if we use this idea for repairing mobile phone then we are in a position to save our money, time, power and so on. Then I examine on this matter and give interest.

Already we now have a system which can read words from a book. Actually my involved field is synthetic intelligence and I wish to take my greater examine from this sector. If we are able to restore our digital devices through the use of AR then will most likely be very helpful for us.

The thought is fascinating however not totally applied. There are many works associated marker primarily based AR but when we will use marker less AR then it will be efficient for us. By using this we may be self-independent.

Introduction

Suppose, any of our digital gadgets like TV, fan, gentle, laptop, espresso maker and so on. doesn’t work. Then what is going to we do? We need to seek the guidance of with an skilled who can repair that. This is time consuming and expensive. Actually I assume tips on how to save time and money for repairing and maintenance. If there might be an augmented restore system which supplies us guidance about repairing then life turns into more easy. The system shows us all the steps the means to repair the issues. By using this method we can restore our digital devices. Current vision-based trackers are based mostly on tracking of markers. The use of markers increases robustness and reduces computational necessities. However, their use can be very sophisticated, as they require sure upkeep. Direct use of scene features for monitoring, therefore, is desirable. To this finish, we describe a basic system that tracks the place and orientation of a digicam observing a scene without any visual markers. Our method is predicated on a two-stage course of. In the primary stage, a set of features is realized with the assistance of an external tracking system whereas in motion. The second stage makes use of these learned features for digital camera monitoring when the system in the first stage decides that it is attainable to take action.

The system could be very general so that it can employ any out there characteristic tracking and pose estimation system for studying and tracking. Direct use of scene options for tracking as a substitute of the markers is way desirable, particularly when certain parts of the workspace don’t change in time. For example, a management panel has fixed buttons and knobs that stay the identical over its lifetime. The use of these rigid and unchanging options for tracking simplifies the preparation of the situations for scene augmentation as well. The developed AR system has been evaluated in quite a few checks in a real industrial context and demonstrated sturdy and secure conduct. Our system is based upon well-known ideas and algorithms and it is our opinion that it’s the right mixture of algorithms that led to a successful AR system. The second stage uses these discovered options for camera monitoring when the system in the first stage decides that it’s possible to do so. The system may be very basic so that it can make use of any obtainable feature tracking and pose estimation system for learning and tracking. We experimentally reveal the viability of the method in real-life examples.

Related work

In order to gauge the methods, earlier than going via the direct experiment we want to assess them for relative setups. Among two kinds of motion capture

Marker less is more comforting in accordance Ashish Shingade and Archana Ghotkar (2014). Because in Marker much less movement seize no character must put on go nicely with and digicam dealing with is little easier. From their survey of different motion capture strategies using Kinect digicam, it was observed that detecting skeleton joints and monitoring is important drawback to use the strategy.

To get depth data of human physique for reference Kinect Camera is preferable resolution. . P. Gerard and A. Gagalowicz(2000) mentioned In the latest years, many Industrial Augmented Reality (IAR) functions are shifting from video to nonetheless photographs to create a combined view. Since using AR in industrial applications is a promising and at the similar time difficult issue, several prototypical systems have already been developed. For this system marker less AR is used as a end result of markers could occlude elements of the workspace and have to be correctly calibrated to the tracked reference body. In addition, marker based monitoring techniques want a free line of sight between the camera and the marker which can not always be guaranteed in repair situations the place partial occlusions by worker’s hands and tools are common.

P.J. Huber. Robust Statistics(1981) found that Initialization and 2D feature tracking: In an initial step, a set of salient 2D depth corners are detected in the rst picture of the sequence. These 2D options are then tracked all through the image sequence by native feature matching with the KLT operator. If characteristic tracks are misplaced, new tracks are continuously reinitialized. The new tracks are merged with previous tracks in the 3D stage to avoid drift. 3D function monitoring and pose estimation: From the given2D function tracks, a SfM method may be utilized toestimatethemetriccameraposeand3Dfeaturepositions simultaneously.

Takashi Okuma, Takeshi Kurata, and Katsuhiko Sakau(2004) invented The problem of marker less AR has two elements:I) Tracking: If the edge worth is (‰€20) all options are deleted and the entire procedure is repeated by using the last estimated pose.Ii) Initialization: The part of initialization relates with the issue of figuring out a camera’s projection matrix without any constraints to the pose and with none knowledge of the earlier poses. The only constraint given the case is that the working with a calibrated camera and thus a recognized intrinsic matrix K.This drawback is solved when a sufciently large set of 2D-3D correspondences may be established. Given the 2D-3D level matches, the pose of the camera is computed using the algorithm by Tsai .An inner calibration is carried out for the camera earlier than the coaching to account for radial distortion up to 6th diploma.

A.J. Davison(2003) found that An online AR system that enables strong 3D digital camera tracking in complicated and uncooperative scenes the place parts of the scene could move independently. It is predicated on the SfM approach from computer vision. The 3D monitoring is based on robust digicam pose estimation utilizing structure from movement algorithms which are optimized for real time performance. These algorithms can handle measurement outliers from the 2D tracking using strong statistics.

Vincent Lepetit, and Pascal Fua(2004) stated Once the markers are calibrated, i.e., their positions are calculated, the entire cameras used within the experiments are internally calibrated utilizing these markers. We use Tsai’s technique [25] to permit radial distortion correction up to 6th diploma, which ensures a very good pose estimation for the digital camera when the proper correspondences are offered.

K. Pentenrieder, C. Bade, F. Doil, and P. Meier(2007) mentioned To improve the efficiency of the initialization process, we introducedatrainingproceduretoeliminateunreliablefeaturesduringthekeyframelearningstage. After the user provides a key frame to the storage, he’s asked to move the digital camera somewhat bit within the vicinity of the pose used to create the key body. As the user moves the camera, 2D features extracted from the key frame are tracked with KLT into each video frame. All features for which the monitoring fails are rejected and never saved in the key frame structure. As a consequence we obtain a more robust initialization, as the chance of a profitable tracking of a function that was saved with the necessary thing frame, will increase.

Since the usage of AR in industrial applications is a promising and on the identical time difficult concern, a number of prototypical techniques have already been developed. The system developed during the greatest GermanAR-Project-ARVIKA[2]aswellassystem[1]usemarkersforposeestimationwhichisnotpracticalinmanyrealindustrial scenarios because of the line of sight downside. On the other hand there are quite a few makes an attempt to unravel the pose estimation drawback with out using ducials (e.g., [6], [7], [9], [15]). Most of those attempts lack testing in real industrial purposes. An overview of the AR technology in manufacturing may be present in [4]. Most of the work associated to our tracking strategy has been described in [17]. We nevertheless use different feature detection and tracking algorithm as will be described in successive sections. Furthermore we do not use the native bundle adjustment method proposed in [17] but we do not experience a noticeable jitter. We use a restrictive function rejection technique which eliminates potential outliers throughout the tracking stage and abandons the necessity for RANSAC pre-processing of 2D-3D correspondences. In addition we use an enhanced algorithm for the training of key frames, which already permits the rejection of malign features during the studying stage making the initialization procedure more reliable.

To conduct this analysis, the potential answered questions would be

  1. How applicable your chosen methodology is for the research?
  2. What is augmented reality?
  3. Why we use marker less AR instead of marker based AR?
  4. What is the advantages of marker much less AR?
  5. How the person use the system?
  6. How would be the data collected?
  7. What sort of research methodology shall be followed?
  8. How would be the information analyzed?

Proposed Methodology

This research follows the experimental method as a outcome of it generates statically analyzable knowledge. As we’d like correct data so this methodology is ideal for this. In this work we introduce a complete AR system for upkeep and restore purposes. In the previous there have been a couple of makes an attempt to develop an AR system for industrial purposes. The resolution developed through the ARVIKA project [2] used marker based mostly optical monitoring together with a video-see-through setup worn by a technician. In some situations nevertheless this method turned out to be not relevant because markers may occlude parts of the workspace and must be properly calibrated to the tracked reference body. In addition, marker based mostly tracking methods want a free line of sight between the camera and the marker which cannot all the time be guaranteed in restore eventualities the place partial occlusions by worker’s palms and instruments are frequent.

Former hardware solutions compelled the user both to put on cumbersome computing units or to be related to them through a ‚exible cable. Our expertise confirmed that both options are sometimes not accepted in business for ergonomic causes and because of the threat of injuries. To overcome these problems we developed a marker much less monitoring system combined with a light weight cellular setup. In the proposed Given a camera’s pose Pt€’1 at some time t€’1, video pictures I t€’1 and It taken at time t€’1 and t, as nicely as a 3D work area mannequin M, estimate the present digital camera pose P.for this particular characteristic, becomes a combined 2D2D and 3D-2D matching and bundle adjustment downside. The system evaluates every set of feature correspondences to find a way to define whether or not this function is a steady one, which means that:.Over time the 3D function doesn’t move independently from the observer (i.e., static place on the earth coordinate system),.

The distribution of the intensity characteristics of the function doesn’t change considerably over time,.The characteristic is powerful enough that the system may find the best detection algorithm to extract it under the conventional changes in lighting conditions i.e., changes which usually occur within the workspace),.The feature is reconstructed and again projected, utilizing the motion estimated by the external tracker, with acceptable again projection error,.The subset of the steady options chosen want to permit correct localization, in comparison with the ground reality from the external tracker.The second set of experiments is performed to see if monitoring may be achieved utilizing cameras apart from the one used in training. Even with a really different tracker and studying digital camera, the system yields excellent pose during tracking. High radial distortion as a end result of larger field-of-view does not effect the accuracy and performance of the markerless tracking system.

REFERENCES

  1. AR Toolkit. YakupGenc, S.Riedel, FabriceSouvannavong, C.Akinlar, andNassir Nava. Marker-less monitoring for artwork: A learning-based strategy. In ISMAR, pages 295″304, 2002.
  2. Reinhardt Koch, Kevin Kosher, Birger Stracke, and Jan-Frisco EversSenne. Markerless image-based 3d monitoring for real-time augmented actuality functions. WIAMIS 2005, April 2005.
  3. Takashi Okuma, Takeshi Kurata, and Katsuhiko Sakaue. A natural feature-based 3d object monitoring methodology for wearable augmented reality. In The 8th IEEE International Workshop on Advanced Motion Control (AMC’04), pages 451″456, 2004.
  4. Donald W. Marquardt. An algorithm for least-squares estimation of nonlinear parameters. Journal of the Society for Industrial and Applied Mathematics, 11(2):431″441, June 1963.
  5. Luca Vacchetti, Vincent Lepetit, and Pascal Fua. Stable real-time 3d monitoring using on-line and of‚ine info. IEEE Trans. Pattern Anal. Mach. Intell., 26(10):1385″1391, 2004.
  6. P. Georgel, P. Schroeder, S. Benhimane, S. Hinterstoisser, M. Appel, and N. Navb. An Industrial Augmented Reality Solution For Discrepancy Check. ISMAR, 2007.
  7. K. Pentenrieder, C. Bade, F. Doil, and P. Meier. Augmented Reality primarily based Factory Planning – an Application Tailored to Industrial Needs. ISMAR, 2007.
  8. A.J. Davison. Real-time simultaneous localization and mapping with a single digicam. In Proceedings International Conference Computer Vision, Nice, 2003.
  9. A. J. Davison, Y. G. Cid, and N. Kita. Real-time 3D SLAM with wide-angle vision. In Proc. IFAC Symposium on Intelligent Autonomous Vehicles, Lisbon, July 2004.
  10. G. Ou, Y. Gao and Y. Liu, “Real- TimeVehicularTrafficViolationDetectioninTrafficMonitoringStream,” in 2012 IEEE/WIC/ACM , Beijing, China , 2012.
  11. Velastin S.A, J.H. Yin, A.c. Davies, M.A. Vicencio-Silva, R.E. AlIsop, and A. Penn (1994): “Automated Measurement of Crowd Density and Motion using Image Processing”, lEE 7th International Conference on Road Traffic Monitoring and Control, 26-28 April 1994, London, UK
  12. U. Neumann and Y. Cho. A selft racking augmented actuality system. In Proceedings of the ACM Symposium on Virtual Reality and Applications, pages 109-115, July 1996.
  13. U. Neumann and S. You. Natural characteristic tracking for augmented actuality. IEEE 1lransactions on Multimedia, 1(1):53-64, March 1999.
  14. S. Gupte, O. Masoud, R. F. K. Martin, and N. P. Papanikolopoulos, Detection and classification of vehicles, IEEE Trans. Intell. Transport. Syst., vol. 3, pp. 37″47, Mar. 2002.
  15. M. Kimachi, K. Kanayama, and K. Teramoto, Incident prediction by fuzzy picture sequence analysis, in Proc. IEEE Int. Conf. VNIS, 1994, pp. 51″57.[1] Kamijo, S., Matsushita, Y., Ikeuchi, K., & Sakauchi, M. (2000). Traffic monitoring and accident detection at intersections. IEEE Transactions on Intelligent Transportation Systems, 1(2), 108″118. doi:10.1109/6979.880968
  16. K. Meyer, H.L. Applewhite, and F.A. Biocca. A survey of position trackers. Presence: Teleoperators and Virtual Environments Vol. 1, No.2, pages 173-200, August 1992
  17. O.D. Faugeras. Three-Dimensional Computer Vision. MIT Press, 1993
  18. Zhang, X., Navab, N., and Liou, S.-P. 2000. E-Commerce direct marketing using augmented reality. In Proc. ICME2000 (IEEE Int. Conf. on Multimedia and Exposition), New York,
  19. Vlahakis, V., Ioannidis, N., Karigiannis, J., Tsotros, M., Gounaris, M., Stricker, D., Gleue, T., Daehne, P., and Almaida, L. 2002. Archeoguide: An augmented reality guide for archaeological sites. IEEE Computer Graphics and Applications, 22(5):52″59

Written by Essay Examples

Architecture and Repair of The Belfry Tower

Arabic Text Mining Using Associative Approach Computer Science Essay