MERAL Myanmar Education Research and Learning Portal
Item
{"_buckets": {"deposit": "6e89cd60-28d6-46f4-88b5-5aa289bcc688"}, "_deposit": {"created_by": 73, "id": "7926", "owner": "73", "owners": [73], "owners_ext": {"displayname": "", "username": ""}, "pid": {"revision_id": 0, "type": "depid", "value": "7926"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/00007926", "sets": ["user-miit"]}, "communities": ["miit"], "control_number": "7926", "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "Transparent Object Detection Using Faster R-CNN", "subitem_1551255648112": "en"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "\"Recently, object detection has become a popular area \nin computer vision and object recognition. In many robotic \nresearches, the most basic step is to perform object detection so \nthat the reaction can be taken after detecting object location \nand its category. One of the main tasks for domestic robots is\nhousehold object detection. In this paper, we intend to detect\ntransparent objects such as glass in images. Compared with\nother kinds of objects, the detection of transparent object is \nvery difficult to be performed using classical computer vision \nalgorithms. Most of the classical computer vision algorithms \nimplement the object detection based on their appearance such \nas colour or texture of the objects. However, the appearance of \ntransparent objects changes according to different\nbackgrounds and illumination conditions. With the popularity \nof object detection researches, deep learning algorithms now \noffer a high performance in detection of objects. Therefore, we \napply one of the deep learning models called Faster R-CNN \n(Regions with Convolutional Neural Network) to perform \ndetection of transparent objects and evaluate the performance \nof the system. According to experimental results, the system \nachieves 89.8% mAP in the detection of transparent objects.\nKeywords – Computer vision and object recognition, Deep \nlearning, Domestic robots, Faster R-CNN, Transparent object \ndetection\n\""}]}, "item_1583103120197": {"attribute_name": "Files", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_access", "date": [{"dateType": "Available", "dateValue": "2021-01-29"}], "displaytype": "preview", "download_preview_message": "", "file_order": 0, "filename": "Transparent Object Detection Using Faster R-CNN.pdf", "filesize": [{"value": "1009 KB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_3", "mimetype": "application/pdf", "size": 1009000.0, "url": {"url": "https://meral.edu.mm/record/7926/files/Transparent Object Detection Using Faster R-CNN.pdf"}, "version_id": "1a487eb7-f2eb-456a-8ca8-49f26fdae6a1"}]}, "item_1583103147082": {"attribute_name": "Conference papers", "attribute_value_mlt": [{"subitem_acronym": "CSTD", "subitem_c_date": "Oct. 30-31, 2018", "subitem_conference_title": "Conference on Science and Technology 2018", "subitem_place": "Pyin Oo Lwin, Myanmar", "subitem_website": "www.cstd.com.mm"}]}, "item_1583105942107": {"attribute_name": "Authors", "attribute_value_mlt": [{"subitem_authors": [{"subitem_authors_fullname": "May Phyo Khaing"}, {"subitem_authors_fullname": "Ei Khaing Win"}]}]}, "item_1583108359239": {"attribute_name": "Upload type", "attribute_value_mlt": [{"interim": "Publication"}]}, "item_1583108428133": {"attribute_name": "Publication type", "attribute_value_mlt": [{"interim": "Conference paper"}]}, "item_1583159729339": {"attribute_name": "Publication date", "attribute_value": "2018-10-06"}, "item_title": "Transparent Object Detection Using Faster R-CNN", "item_type_id": "21", "owner": "73", "path": ["1582963674932", "1597396989070"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000007926", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2018-10-06"}, "publish_date": "2018-10-06", "publish_status": "0", "recid": "7926", "relation": {}, "relation_version_is_last": true, "title": ["Transparent Object Detection Using Faster R-CNN"], "weko_shared_id": -1}
Transparent Object Detection Using Faster R-CNN
http://hdl.handle.net/20.500.12678/0000007926
http://hdl.handle.net/20.500.12678/00000079264404d526-d934-4a30-b385-fb41f02df64e
6e89cd60-28d6-46f4-88b5-5aa289bcc688
Name / File | License | Actions |
---|---|---|
![]() |
Publication type | ||||||
---|---|---|---|---|---|---|
Conference paper | ||||||
Upload type | ||||||
Publication | ||||||
Title | ||||||
Title | Transparent Object Detection Using Faster R-CNN | |||||
Language | en | |||||
Publication date | 2018-10-06 | |||||
Authors | ||||||
May Phyo Khaing | ||||||
Ei Khaing Win | ||||||
Description | ||||||
"Recently, object detection has become a popular area in computer vision and object recognition. In many robotic researches, the most basic step is to perform object detection so that the reaction can be taken after detecting object location and its category. One of the main tasks for domestic robots is household object detection. In this paper, we intend to detect transparent objects such as glass in images. Compared with other kinds of objects, the detection of transparent object is very difficult to be performed using classical computer vision algorithms. Most of the classical computer vision algorithms implement the object detection based on their appearance such as colour or texture of the objects. However, the appearance of transparent objects changes according to different backgrounds and illumination conditions. With the popularity of object detection researches, deep learning algorithms now offer a high performance in detection of objects. Therefore, we apply one of the deep learning models called Faster R-CNN (Regions with Convolutional Neural Network) to perform detection of transparent objects and evaluate the performance of the system. According to experimental results, the system achieves 89.8% mAP in the detection of transparent objects. Keywords – Computer vision and object recognition, Deep learning, Domestic robots, Faster R-CNN, Transparent object detection " |
||||||
Conference papers | ||||||
CSTD | ||||||
Oct. 30-31, 2018 | ||||||
Conference on Science and Technology 2018 | ||||||
Pyin Oo Lwin, Myanmar | ||||||
www.cstd.com.mm |