Please use this identifier to cite or link to this item: https://rda.sliit.lk/handle/123456789/1489
Full metadata record
DC FieldValueLanguage
dc.contributor.authorRajakaruna, N-
dc.contributor.authorRathnayake, C-
dc.contributor.authorAbhayasinghe, N-
dc.contributor.authorMurray, I-
dc.date.accessioned2022-03-04T04:34:41Z-
dc.date.available2022-03-04T04:34:41Z-
dc.date.issued2014-10-27-
dc.identifier.citationN. Rajakaruna, C. Rathnayake, N. Abhayasinghe and I. Murray, "Inertial data based deblurring for vision impaired navigation," 2014 International Conference on Indoor Positioning and Indoor Navigation (IPIN), 2014, pp. 416-420, doi: 10.1109/IPIN.2014.7275510.en_US
dc.identifier.isbn978-1-4673-8054-6-
dc.identifier.urihttp://rda.sliit.lk/handle/123456789/1489-
dc.description.abstractImage stabilization is very important in vision based indoor/outdoor navigation systems. Blurring is one main cause of poor image quality, which can be caused by a movement of the camera at the time of taking the image, a movement of objects in front, atmospheric turbulence or out-of-focus. Out of these factors, camera movement is dominant in navigation systems as the camera is continuously moving. This paper presents the preliminary results of deblurring performed using point spread function (PSF) computed using synchronized inertial sensor data. It uses data of the accelerometer and gyroscope to derive a motion vector calculated from the motion of the smartphone during the image capturing period. This motion vector is applied to the captured image so that the effect of motion is reversed during the debrurring process. This work is a part of an indoor navigation project that aims to assist people with vision impairment. Image processing form a significant part of the proposed system and as such clearly defined edges are essential for path and obstruction identification. Different deblurring methods are compared for their performance in reversing the effect of camera movement. Results indicated that deblurring can be successfully performed using the motion vector and that the resulting images can be used as a readily approach to object and path identification in vision based navigation systems, especially for blind and vision impaired indoor/outdoor navigation. The paper also proposes a novel deblurring algorithm that uses PSF computed for different portions of the image to deblur that portion of the image.en_US
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.relation.ispartofseries2014 International Conference on Indoor Positioning and Indoor Navigation (IPIN);Pages 416-420-
dc.subjectInertial data baseden_US
dc.subjectdeblurringen_US
dc.subjectvisionen_US
dc.subjectimpaired navigationen_US
dc.titleInertial data based deblurring for vision impaired navigationen_US
dc.typeArticleen_US
dc.identifier.doi10.1109/IPIN.2014.7275510en_US
Appears in Collections:Research Papers - Department of Electrical and Electronic Engineering
Research Papers - SLIIT Staff Publications

Files in This Item:
File Description SizeFormat 
Inertial_data_based_deblurring_for_vision_impaired_navigation.pdf
  Until 2050-12-31
954.03 kBAdobe PDFView/Open Request a copy


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.