東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Leveraging Pre-Trained Detection Net...

Walsh, Sean.

FindBook

Google Book

Amazon

博客來

Leveraging Pre-Trained Detection Networks for Label Generation on New Datasets.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Leveraging Pre-Trained Detection Networks for Label Generation on New Datasets./
作者:	Walsh, Sean.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:	57 p.
附註:	Source: Masters Abstracts International, Volume: 82-06.
Contained By:	Masters Abstracts International82-06.
標題:	Robotics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28025398
ISBN:	9798698545941

Leveraging Pre-Trained Detection Networks for Label Generation on New Datasets.
Walsh, Sean.

Leveraging Pre-Trained Detection Networks for Label Generation on New Datasets. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 57 p.

Source: Masters Abstracts International, Volume: 82-06.

Thesis (M.A.S.)--University of Toronto (Canada), 2020.

This item must not be sold to any third party vendors.

The development of 3D object detection solutions for autonomous driving requires labelled real-world datasets for training and evaluation, which are costly to produce. This thesis presents a 3D click labelling approach to individual scene labelling, in which annotators are provided a specially designed user interface to click on objects in the point cloud of each scene. The click labels are subsequently processed by a pre-trained network to generate a label for each click. The proposed annotation scheme demonstrates a 30x lower human annotation time. This thesis also presents a method for automatic labelling of static objects through the use of full drive sequences. In this work proposals from a pre-trained detection network, over the course of a drive sequence, are transformed into a global reference frame. Overlapping detections are processed to produce high recall label proposals for static vehicles in the sequence, eliminating the need for manual annotation.

ISBN: 9798698545941Subjects--Topical Terms:

519753
Robotics.
Subjects--Index Terms:

Pre-trained detection network

Leveraging Pre-Trained Detection Networks for Label Generation on New Datasets.
LDR:02093nmm a2200361 4500 001 2277347
005 20210521101703.5
008 220723s2020 ||||||||||||||||| ||eng d
020 $a 9798698545941
035 $a (MiAaPQ)AAI28025398
035 $a AAI28025398
040 $a MiAaPQ $c MiAaPQ
100 1 $a Walsh, Sean. $3 1293213
245 1 0 $a Leveraging Pre-Trained Detection Networks for Label Generation on New Datasets.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 57 p.
500 $a Source: Masters Abstracts International, Volume: 82-06.
500 $a Advisor: Waslander, Steven.
502 $a Thesis (M.A.S.)--University of Toronto (Canada), 2020.
506 $a This item must not be sold to any third party vendors.
520 $a The development of 3D object detection solutions for autonomous driving requires labelled real-world datasets for training and evaluation, which are costly to produce. This thesis presents a 3D click labelling approach to individual scene labelling, in which annotators are provided a specially designed user interface to click on objects in the point cloud of each scene. The click labels are subsequently processed by a pre-trained network to generate a label for each click. The proposed annotation scheme demonstrates a 30x lower human annotation time. This thesis also presents a method for automatic labelling of static objects through the use of full drive sequences. In this work proposals from a pre-trained detection network, over the course of a drive sequence, are transformed into a global reference frame. Overlapping detections are processed to produce high recall label proposals for static vehicles in the sequence, eliminating the need for manual annotation.
590 $a School code: 0779.
650 4 $a Robotics. $3 519753
650 4 $a Computer science. $3 523869
650 4 $a Information technology. $3 532993
650 4 $a Information science. $3 554358
653 $a Pre-trained detection network
653 $a Label generation
653 $a New datasets
690 $a 0771
690 $a 0984
690 $a 0489
690 $a 0723
710 2 $a University of Toronto (Canada). $b Aerospace Science and Engineering. $3 2105951
773 0 $t Masters Abstracts International $g 82-06.
790 $a 0779
791 $a M.A.S.
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28025398