nanoll extt
Please use this identifier to cite or link to this item: http://lrcdrs.bennett.edu.in:80/handle/123456789/2027
Full metadata record
DC FieldValueLanguage
dc.contributor.authorManjari, Kanak-
dc.date.accessioned2023-10-08T17:06:12Z-
dc.date.available2023-10-08T17:06:12Z-
dc.date.issued2022-06-
dc.identifier.urihttps://shodhganga.inflibnet.ac.in/handle/10603/515231-
dc.description.abstractAccording to World Health Organization’s report, one­sixth of the world population is suffering from vision impairment. In the past decades, many efforts have been done in developing several devices/solutions to provide support to the visually impaired (VI) and enhance the quality of their lives by making them capable to lead normal life. Many of those devices are either heavy or costly for general purposes. It would be exceedingly unfair to leave the VI off in these day of technological developments, where humans are exploring it in every field. As the figures of VI are increasing, the necessity of having a solution for navigation and orientation has also increased. The main focus of this work is to develop solutions to help VI. First of all, a survey has been done to know about all the existing solutions developed for them. A brief comparison has been done between all those solutions based on the various evaluation parameters to understand their limitations. Once the survey is done, a hardware integrated software solution in the form of cane has been developed to assist them in the general day­to­day activities such as object detection, text detection, and path texture detection. The cane has been shaped using edge device, Nvidia Jetson NANO/raspberry pi, a 3D camera, and other sensory devices attached to it. For the initial testing, existing detection models have been used and deployed on it. To understand the memory constraints and the compatibility of different models on edge devices, experiments have been performed. This helped in knowing how the edge devices performed when a certain model, either lightweight or heavy, was deployed on them in terms of detection time and accuracy. The custom­developed deep learning models have also been deployed on the edge device attached to the cane and then the performance analysis has been performed.en_US
dc.language.isoen_USen_US
dc.publisherBennett universityen_US
dc.subjectComputer Scienceen_US
dc.subjectComputer Science Software Engineeringen_US
dc.titleAssistive technological solutions for visually impaireden_US
dc.typeThesisen_US
Appears in Collections:School of Computer Science Engineering and Technology (SCSET)

Files in This Item:
File Description SizeFormat 
Kanak_thesis_non_highlighted 1.pdf51.77 MBAdobe PDFView/Open

Contact admin for Full-Text

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