본문

서브메뉴

Enhancing Pedestrian Safety by Detecting Pedestrian Activities and Using Multi-Modal Sensors for Pedestrian Detection
Enhancing Pedestrian Safety by Detecting Pedestrian Activities and Using Multi-Modal Senso...
Enhancing Pedestrian Safety by Detecting Pedestrian Activities and Using Multi-Modal Sensors for Pedestrian Detection

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105225
ISBN  
9798291566619
DDC  
629.8
저자명  
Kanu-Asiegbu, Asiegbu Miracle.
서명/저자  
Enhancing Pedestrian Safety by Detecting Pedestrian Activities and Using Multi-Modal Sensors for Pedestrian Detection
발행사항  
[Sl] : University of Michigan, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
98 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
주기사항  
Advisor: Du, Xiaoxiao;Vasudevan, Ramanarayan.
학위논문주기  
Thesis (Ph.D.)--University of Michigan, 2025.
초록/해제  
요약Pedestrians are some of the most vulnerable road users, facing a high risk of injury in vehicle-pedestrian collisions. To make safe autonomous driving a reality, accurately detecting pedestrians with real-world sensor data is crucial. In this thesis, I propose a series of deep learning-based algorithms aimed at improving pedestrian safety by analyzing real-world time-series data. In part one, I detect non-walking pedestrian activities by explicitly incorporating temporal information through pedestrian trajectories, and in part two, I perform pedestrian detection by leveraging sequences of multimodal images taken at different time steps to capture motion patterns and temporal context, which implicitly incorporates temporal information. The first part of this work introduces two novel unsupervised approaches for detecting walking and non-walking events using anomaly detection. In this context, non-walking pedestrians-such as running, biking, or skateboarding-are anomalous because they often cover longer distances over short periods, increasing the risk of collisions. Therefore, accurately identifying non-walking pedestrians is critical for ensuring pedestrian safety. Both methods follow three main steps: (1) pedestrian detection, (2) trajectory prediction, and (3) anomaly detection. For pedestrian detection, pedestrians are identified in RGB camera images by extracting either bounding boxes or human pose coordinates, which are then used to construct their trajectories. Next, for trajectory prediction, the predictor is trained exclusively on walking data and forecasts future pedestrian movements based on observed trajectories. Finally, for anomaly detection, I compare predicted and actual trajectories: large prediction errors indicate anomalous (non-walking) behavior, allowing for fully unsupervised activity detection. Both approaches achieve competitive results. The second part of this work addresses pedestrian detection in both daytime and nighttime conditions. While RGB cameras perform effectively in well-lit environments, their performance deteriorates significantly in low-light or nighttime scenarios. However, thermal imagery captures the heat signatures of pedestrians, enabling detection in challenging lighting conditions. This section proposes two multimodal methods that fuse sequences of thermal and visible images. Both methods leverage image sequences rather than single frames, which improves detection accuracy of heavily occluded pedestrians. A key challenge in multimodal fusion is the spatial misalignment between thermal and visible image pairs, which can degrade performance if not properly addressed. The first method, MambaST, assumes well-aligned image sequences and focuses on real-time fusion of thermal and visible images for pedestrian detection. The second method, Strip-Fusion, inspired by multi-layer perceptrons, is robust to well-aligned and misaligned sequences and uses Kullback-Leibler divergence loss to encourage the feature distribution of the less reliable modality to resemble the more reliable modality. Followed by a post-processing step, which effectively ensures that a pedestrian is detected in both thermal and visible detection heads. Experimental results demonstrate that our methods achieve competitive performance on the well-aligned and misaligned datasets, highlighting the effectiveness and adaptability of our proposed approaches. The first part of the thesis distinguishes between walking and non-walking pedestrians using visible images. It can be generalized to detect anomalous activities, which is a core problem in vision. This work extends the current literature on using prediction-based methods for anomaly detection and can benefit safety-critical applications such as autonomous driving, surveillance, and human-robot interaction. The second part of the thesis uses both visible and thermal images to improve pedestrian detection in challenging lighting conditions. This work extends the current literature and proposes new efficient and robust approaches to address spatial-temporal multispectral pedestrian detection.
일반주제명  
Robotics
일반주제명  
Computer science
일반주제명  
Mechanical engineering
키워드  
Pedestrian detection
키워드  
Video anomaly detection
키워드  
Trajectory prediction
키워드  
Low light conditions
키워드  
Collisions
기타저자  
University of Michigan Mechanical Engineering
기본자료저록  
Dissertations Abstracts International. 87-03B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017359852
■00520260202105225
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798291566619
■035    ▼a(MiAaPQ)AAI32271844
■035    ▼a(MiAaPQ)umichrackham006213
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.8
■1001  ▼aKanu-Asiegbu,  Asiegbu  Miracle.
■24510▼aEnhancing  Pedestrian  Safety  by  Detecting  Pedestrian  Activities  and  Using  Multi-Modal  Sensors  for  Pedestrian  Detection
■260    ▼a[Sl]▼bUniversity  of  Michigan▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a98  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-03,  Section:  B.
■500    ▼aAdvisor:  Du,  Xiaoxiao;Vasudevan,  Ramanarayan.
■5021  ▼aThesis  (Ph.D.)--University  of  Michigan,  2025.
■520    ▼aPedestrians  are  some  of  the  most  vulnerable  road  users,  facing  a  high  risk  of  injury  in  vehicle-pedestrian  collisions.  To  make  safe  autonomous  driving  a  reality,  accurately  detecting  pedestrians  with  real-world  sensor  data  is  crucial.  In  this  thesis,  I  propose  a  series  of  deep  learning-based  algorithms  aimed  at  improving  pedestrian  safety  by  analyzing  real-world  time-series  data.  In  part  one,  I  detect  non-walking  pedestrian  activities  by  explicitly  incorporating  temporal  information  through  pedestrian  trajectories,  and  in  part  two,  I  perform  pedestrian  detection  by  leveraging  sequences  of  multimodal  images  taken  at  different  time  steps  to  capture  motion  patterns  and  temporal  context,  which  implicitly  incorporates  temporal  information.  The  first  part  of  this  work  introduces  two  novel  unsupervised  approaches  for  detecting  walking  and  non-walking  events  using  anomaly  detection.  In  this  context,  non-walking  pedestrians-such  as  running,  biking,  or  skateboarding-are  anomalous  because  they  often  cover  longer  distances  over  short  periods,  increasing  the  risk  of  collisions.  Therefore,  accurately  identifying  non-walking  pedestrians  is  critical  for  ensuring  pedestrian  safety.  Both  methods  follow  three  main  steps:  (1)  pedestrian  detection,  (2)  trajectory  prediction,  and  (3)  anomaly  detection.  For  pedestrian  detection,  pedestrians  are  identified  in  RGB  camera  images  by  extracting  either  bounding  boxes  or  human  pose  coordinates,  which  are  then  used  to  construct  their  trajectories.  Next,  for  trajectory  prediction,  the  predictor  is  trained  exclusively  on  walking  data  and  forecasts  future  pedestrian  movements  based  on  observed  trajectories.  Finally,  for  anomaly  detection,  I  compare  predicted  and  actual  trajectories:  large  prediction  errors  indicate  anomalous  (non-walking)  behavior,  allowing  for  fully  unsupervised  activity  detection.  Both  approaches  achieve  competitive  results.  The  second  part  of  this  work  addresses  pedestrian  detection  in  both  daytime  and  nighttime  conditions.  While  RGB  cameras  perform  effectively  in  well-lit  environments,  their  performance  deteriorates  significantly  in  low-light  or  nighttime  scenarios.  However,  thermal  imagery  captures  the  heat  signatures  of  pedestrians,  enabling  detection  in  challenging  lighting  conditions.  This  section  proposes  two  multimodal  methods  that  fuse  sequences  of  thermal  and  visible  images.  Both  methods  leverage  image  sequences  rather  than  single  frames,  which  improves  detection  accuracy  of  heavily  occluded  pedestrians.  A  key  challenge  in  multimodal  fusion  is  the  spatial  misalignment  between  thermal  and  visible  image  pairs,  which  can  degrade  performance  if  not  properly  addressed.  The  first  method,  MambaST,  assumes  well-aligned  image  sequences  and  focuses  on  real-time  fusion  of  thermal  and  visible  images  for  pedestrian  detection.  The  second  method,  Strip-Fusion,  inspired  by  multi-layer  perceptrons,  is  robust  to  well-aligned  and  misaligned  sequences  and  uses  Kullback-Leibler  divergence  loss  to  encourage  the  feature  distribution  of  the  less  reliable  modality  to  resemble  the  more  reliable  modality.    Followed  by  a  post-processing  step,  which  effectively  ensures  that  a  pedestrian  is  detected  in  both  thermal  and  visible  detection  heads.  Experimental  results  demonstrate  that  our  methods  achieve  competitive  performance  on  the  well-aligned  and  misaligned  datasets,  highlighting  the  effectiveness  and  adaptability  of  our  proposed  approaches.  The  first  part  of  the  thesis  distinguishes  between  walking  and  non-walking  pedestrians  using  visible  images.  It  can  be  generalized  to  detect  anomalous  activities,  which  is  a  core  problem  in  vision.  This  work  extends  the  current  literature  on  using  prediction-based  methods  for  anomaly  detection  and  can  benefit  safety-critical  applications  such  as  autonomous  driving,  surveillance,  and  human-robot  interaction.  The  second  part  of  the  thesis  uses  both  visible  and  thermal  images  to  improve  pedestrian  detection  in  challenging  lighting  conditions.  This  work  extends  the  current  literature  and  proposes  new  efficient  and  robust  approaches  to  address  spatial-temporal  multispectral  pedestrian  detection.
■590    ▼aSchool  code:  0127.
■650  4▼aRobotics
■650  4▼aComputer  science
■650  4▼aMechanical  engineering
■653    ▼aPedestrian  detection
■653    ▼aVideo  anomaly  detection
■653    ▼aTrajectory  prediction
■653    ▼aLow  light  conditions
■653    ▼aCollisions
■690    ▼a0771
■690    ▼a0984
■690    ▼a0800
■690    ▼a0548
■71020▼aUniversity  of  Michigan▼bMechanical  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g87-03B.
■790    ▼a0127
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359852▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF15490 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.