東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Enhancing Autonomous Vehicle Percept...

Cai, Kaiwen,

Linked to FindBook

Google Book

Amazon

博客來

Enhancing Autonomous Vehicle Perception: A Focus on Embedding Learning and Uncertainty Analysis /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Enhancing Autonomous Vehicle Perception: A Focus on Embedding Learning and Uncertainty Analysis // Kaiwen Cai.
Author:	Cai, Kaiwen,
Description:	1 electronic resource (128 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-03, Section: A.
Contained By:	Dissertations Abstracts International86-03A.
Subject:	Histograms. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31289863
ISBN:	9798384211747

Enhancing Autonomous Vehicle Perception: A Focus on Embedding Learning and Uncertainty Analysis /
Cai, Kaiwen,

Enhancing Autonomous Vehicle Perception: A Focus on Embedding Learning and Uncertainty Analysis /Kaiwen Cai. - 1 electronic resource (128 pages)

Source: Dissertations Abstracts International, Volume: 86-03, Section: A.

Perception plays a critical role in autonomous driving, encompassing key areas such as place recognition, semantic segmentation, and object detection. These areas have been extensively researched in the literature. Additionally, embedding learning forms the bedrock of these recognition tasks. It operates by developing a mapping function that arranges similar objects in close proximity within an embedding space.However, embedding learning is primarily based on Deep Neural Networks (DNNs). This reliance poses challenges in establishing trust in the learnt embeddings, especially in autonomous driving-a scenario sensitive to risks. This thesis focuses on enhancing the reliability and reducing the risks associated with embedding learning techniques in autonomous driving.We first focused on improving place recognition, a task of identifying previously visited places. Existing place recognition methods are susceptible to unfavorable environmental conditions due to the employment of visual cameras. To tackle this limitation, we leveraged a new millimeter wave sensor and developed several novel modules to make the most of it. These modules include eliminating objects based on radial velocities, spatial-temporal encoding of radar characteristics, and dynamic re-ranking of candidates through radar cross section measurements. Together, these proposed modules increase the accuracy and reliability of embedding learning in autonomous driving scenarios.In addition to hardware considerations, we also address the issue of minimizing risk from the model aspect. Our focus in the second part of this thesis is on estimating uncertainty in a common RGB-image-based place recognition task. To accomplish this, we introduce a teacher-student framework for embedding learning, in which networks share the same architecture and training data. The student net learns to generate well-calibrated uncertainty while maintaining predictive performance. Estimated uncertainty helps to identify unreliable predictions and thus reduce the risk of embedding learning.In the third section, we shift our focus from instance retrieval to object retrieval. We demonstrate the significance of point-level embedding learning in two dense prediction tasks: 3D semantic segmentation and geometric feature learning. We found that dense prediction generally is based on embedding learning network. Therefore, we propose the use of cross-point embeddings for uncertainty estimation in 3D dense prediction. By establishing a probabilistic embedding model and enforcing metric alignments in the embedding space, we obtain well-calibrated uncertainty estimation in these tasks.In the last section, rather than estimate uncertainty for prediction, we produce prediction based on the estimated uncertainty. We present Risk Controlled Image Retrieval (RCIR), which generates retrieval sets that are guaranteed to contain the true nearest neighbor with a user-specified probability. This is inspired by the fact that though uncertainty quantification can help by assessing uncertainty for query and database images, it can provide only a heuristic estimate rather than a guarantee. RCIR can be easily plugged into any uncertainty-aware image retrieval pipeline, agnostic to data distribution and model selection.In conclusion, this thesis presents a suite of solutions designed to bolster reliability and reduce risks in real-world embedding learning applications within autonomous driving. These applications span place recognition, 3D semantic segmentation, and geometric feature learning. The effectiveness of these proposed methods has been rigorously evaluated across multiple datasets, demonstrating their superiority over existing techniques.

English

ISBN: 9798384211747Subjects--Topical Terms:

3683681
Histograms.

Enhancing Autonomous Vehicle Perception: A Focus on Embedding Learning and Uncertainty Analysis /
LDR:05087nmm a22003973i 4500 001 2435908
005 20251014050539.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798384211747
035 $a (MiAaPQD)AAI31289863
035 $a (MiAaPQD)Liverpool_3179131
035 $a AAI31289863
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Cai, Kaiwen, $e author. $3 3826391
245 1 0 $a Enhancing Autonomous Vehicle Perception: A Focus on Embedding Learning and Uncertainty Analysis / $c Kaiwen Cai.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (128 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: Dissertations Abstracts International, Volume: 86-03, Section: A.
500 $a Advisors: Huang, Xiaowei; Lu, Chris Xiaoxuan.
502 $b Ph.D. $c The University of Liverpool (United Kingdom) $d 2024.
520 $a Perception plays a critical role in autonomous driving, encompassing key areas such as place recognition, semantic segmentation, and object detection. These areas have been extensively researched in the literature. Additionally, embedding learning forms the bedrock of these recognition tasks. It operates by developing a mapping function that arranges similar objects in close proximity within an embedding space.However, embedding learning is primarily based on Deep Neural Networks (DNNs). This reliance poses challenges in establishing trust in the learnt embeddings, especially in autonomous driving-a scenario sensitive to risks. This thesis focuses on enhancing the reliability and reducing the risks associated with embedding learning techniques in autonomous driving.We first focused on improving place recognition, a task of identifying previously visited places. Existing place recognition methods are susceptible to unfavorable environmental conditions due to the employment of visual cameras. To tackle this limitation, we leveraged a new millimeter wave sensor and developed several novel modules to make the most of it. These modules include eliminating objects based on radial velocities, spatial-temporal encoding of radar characteristics, and dynamic re-ranking of candidates through radar cross section measurements. Together, these proposed modules increase the accuracy and reliability of embedding learning in autonomous driving scenarios.In addition to hardware considerations, we also address the issue of minimizing risk from the model aspect. Our focus in the second part of this thesis is on estimating uncertainty in a common RGB-image-based place recognition task. To accomplish this, we introduce a teacher-student framework for embedding learning, in which networks share the same architecture and training data. The student net learns to generate well-calibrated uncertainty while maintaining predictive performance. Estimated uncertainty helps to identify unreliable predictions and thus reduce the risk of embedding learning.In the third section, we shift our focus from instance retrieval to object retrieval. We demonstrate the significance of point-level embedding learning in two dense prediction tasks: 3D semantic segmentation and geometric feature learning. We found that dense prediction generally is based on embedding learning network. Therefore, we propose the use of cross-point embeddings for uncertainty estimation in 3D dense prediction. By establishing a probabilistic embedding model and enforcing metric alignments in the embedding space, we obtain well-calibrated uncertainty estimation in these tasks.In the last section, rather than estimate uncertainty for prediction, we produce prediction based on the estimated uncertainty. We present Risk Controlled Image Retrieval (RCIR), which generates retrieval sets that are guaranteed to contain the true nearest neighbor with a user-specified probability. This is inspired by the fact that though uncertainty quantification can help by assessing uncertainty for query and database images, it can provide only a heuristic estimate rather than a guarantee. RCIR can be easily plugged into any uncertainty-aware image retrieval pipeline, agnostic to data distribution and model selection.In conclusion, this thesis presents a suite of solutions designed to bolster reliability and reduce risks in real-world embedding learning applications within autonomous driving. These applications span place recognition, 3D semantic segmentation, and geometric feature learning. The effectiveness of these proposed methods has been rigorously evaluated across multiple datasets, demonstrating their superiority over existing techniques.
546 $a English
590 $a School code: 0722
650 4 $a Histograms. $3 3683681
650 4 $a Visualization. $3 586179
650 4 $a Image retrieval. $3 3562846
650 4 $a Autonomous vehicles. $3 2179092
650 4 $a Neural networks. $3 677449
650 4 $a Semantics. $3 520060
650 4 $a Logic. $3 529544
650 4 $a Transportation. $3 555912
690 $a 0800
690 $a 0395
690 $a 0709
710 2 $a The University of Liverpool (United Kingdom). $e degree granting institution. $3 3767499
720 1 $a Huang, Xiaowei $e degree supervisor.
720 1 $a Lu, Chris Xiaoxuan $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-03A.
790 $a 0722
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31289863