國立虎尾科技大學 |

DeepMapping2.5 : = Lightweight LiDAR Map Optimization.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	DeepMapping2.5 :/
Reminder of title:	Lightweight LiDAR Map Optimization.
Author:	Chen, Xianhui.
Description:	1 online resource (56 pages)
Notes:	Source: Masters Abstracts International, Volume: 85-08.
Contained By:	Masters Abstracts International85-08.
Subject:	Computer engineering. -
Online resource:	click for full text (PQDT)
ISBN:	9798381695304

DeepMapping2.5 : = Lightweight LiDAR Map Optimization.
Chen, Xianhui.

DeepMapping2.5 :Lightweight LiDAR Map Optimization. - 1 online resource (56 pages)

Source: Masters Abstracts International, Volume: 85-08.

Thesis (M.S.)--New York University Tandon School of Engineering, 2024.

Includes bibliographical references

Lidar mapping plays a crucial role in self-driving and mobile robotics. DeepMapping2 is a large-scaled LiDAR global optimization method. However, it increases parameter usage, leading to time-consuming computations. To tackle this issue, we propose DeepMapping2.5, which enhances generalization capability and resolves the problem of heavyweight parameters. The key innovations of DeepMapping2.5 involve stabilizing rotation representation using quaternions and reducing training time through knowledge distillation from DeepMapping2. Experimental results on the KITTI dataset demonstrate that DeepMapping2.5 achieves competitive performance compared to state-of-the-art LiDAR mapping methods, all while utilizing fewer training parameters and shorter training time.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798381695304Subjects--Topical Terms:

569006
Computer engineering.
Subjects--Index Terms:

DeepMapping2Index Terms--Genre/Form:

554714
Electronic books.

DeepMapping2.5 : = Lightweight LiDAR Map Optimization.
LDR:02038ntm a22003737 4500 001 1152023
005 20241125080213.5
006 m o d
007 cr mn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798381695304
035 $a (MiAaPQ)AAI30820330
035 $a AAI30820330
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Chen, Xianhui. $3 1478897
245 1 0 $a DeepMapping2.5 : $b Lightweight LiDAR Map Optimization.
264 0 $c 2024
300 $a 1 online resource (56 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 85-08.
500 $a Advisor: Feng, Chen.
502 $a Thesis (M.S.)--New York University Tandon School of Engineering, 2024.
504 $a Includes bibliographical references
520 $a Lidar mapping plays a crucial role in self-driving and mobile robotics. DeepMapping2 is a large-scaled LiDAR global optimization method. However, it increases parameter usage, leading to time-consuming computations. To tackle this issue, we propose DeepMapping2.5, which enhances generalization capability and resolves the problem of heavyweight parameters. The key innovations of DeepMapping2.5 involve stabilizing rotation representation using quaternions and reducing training time through knowledge distillation from DeepMapping2. Experimental results on the KITTI dataset demonstrate that DeepMapping2.5 achieves competitive performance compared to state-of-the-art LiDAR mapping methods, all while utilizing fewer training parameters and shorter training time.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer engineering. $3 569006
650 4 $a Information technology. $3 559429
653 $a DeepMapping2
653 $a Mobile robotics
653 $a LiDAR mapping
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0489
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a New York University Tandon School of Engineering. $b Electrical & Computer Engineering. $3 1437750
773 0 $t Masters Abstracts International $g 85-08.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30820330 $z click for full text (PQDT)