Pedestrian and Cyclist Detection and Intent Estimation for Autonomous Vehicles: A Survey

Research output: Contribution to journalArticle

1 Citation (Scopus)
13 Downloads (Pure)

Abstract

As autonomous vehicles become more common on the roads, their advancement draws on safety concerns for vulnerable road users, such as pedestrians and cyclists. This paper presents a review of recent developments in pedestrian and cyclist detection and intent estimation to increase the safety of autonomous vehicles, for both the driver and other road users. Understanding the intentions of the pedestrian/cyclist enables the self-driving vehicle to take actions to avoid incidents. To make this possible, development of methods/techniques, such as deep learning (DL), for the autonomous vehicle will be explored. For example, the development of pedestrian detection has been significantly advanced using DL approaches, such as; Fast Region-Convolutional Neural Network (R-CNN) , Faster R-CNN and Single Shot Detector (SSD). Although DL has been around for several decades, the hardware to realise the techniques have only recently become viable. Using these DL methods for pedestrian and cyclist detection and applying it for the tracking, motion modelling and pose estimation can allow for a successful and accurate method of intent estimation for the vulnerable road users. Although there has been a growth in research surrounding the study of pedestrian detection using vision-based approaches, further attention should include focus on cyclist detection. To further improve safety for these vulnerable road users (VRUs), approaches such as sensor fusion and intent estimation should be investigated.
Original languageEnglish
Article number2335
JournalApplied Sciences (Switzerland)
Volume9
Issue number11
DOIs
Publication statusPublished - 6 Jun 2019

Fingerprint

roads
vehicles
learning
safety
Neural networks
multisensor fusion
Fusion reactions
shot
Detectors
Hardware
hardware
Deep learning
Sensors
detectors

Keywords

  • CNN
  • Cyclist detection
  • Deep learning
  • Fast R-CNN
  • Faster R-CNN
  • Intent estimation
  • Motion modelling
  • Pedestrian detection
  • Pose estimation
  • Tracking

ASJC Scopus subject areas

  • Materials Science(all)
  • Instrumentation
  • Engineering(all)
  • Process Chemistry and Technology
  • Computer Science Applications
  • Fluid Flow and Transfer Processes

Cite this

@article{adf6b6c66a19482399ee6a48b996b749,
title = "Pedestrian and Cyclist Detection and Intent Estimation for Autonomous Vehicles: A Survey",
abstract = "As autonomous vehicles become more common on the roads, their advancement draws on safety concerns for vulnerable road users, such as pedestrians and cyclists. This paper presents a review of recent developments in pedestrian and cyclist detection and intent estimation to increase the safety of autonomous vehicles, for both the driver and other road users. Understanding the intentions of the pedestrian/cyclist enables the self-driving vehicle to take actions to avoid incidents. To make this possible, development of methods/techniques, such as deep learning (DL), for the autonomous vehicle will be explored. For example, the development of pedestrian detection has been significantly advanced using DL approaches, such as; Fast Region-Convolutional Neural Network (R-CNN) , Faster R-CNN and Single Shot Detector (SSD). Although DL has been around for several decades, the hardware to realise the techniques have only recently become viable. Using these DL methods for pedestrian and cyclist detection and applying it for the tracking, motion modelling and pose estimation can allow for a successful and accurate method of intent estimation for the vulnerable road users. Although there has been a growth in research surrounding the study of pedestrian detection using vision-based approaches, further attention should include focus on cyclist detection. To further improve safety for these vulnerable road users (VRUs), approaches such as sensor fusion and intent estimation should be investigated.",
keywords = "CNN, Cyclist detection, Deep learning, Fast R-CNN, Faster R-CNN, Intent estimation, Motion modelling, Pedestrian detection, Pose estimation, Tracking",
author = "Sarfraz Ahmed and Huda, {M. Nazmul} and Sujan Rajbhandari and Chitta Saha and Mark Elshaw and Stratis Kanarachos",
year = "2019",
month = "6",
day = "6",
doi = "10.3390/app9112335",
language = "English",
volume = "9",
journal = "Applied Sciences",
issn = "2076-3417",
publisher = "MDPI",
number = "11",

}

TY - JOUR

T1 - Pedestrian and Cyclist Detection and Intent Estimation for Autonomous Vehicles: A Survey

AU - Ahmed, Sarfraz

AU - Huda, M. Nazmul

AU - Rajbhandari, Sujan

AU - Saha, Chitta

AU - Elshaw, Mark

AU - Kanarachos, Stratis

PY - 2019/6/6

Y1 - 2019/6/6

N2 - As autonomous vehicles become more common on the roads, their advancement draws on safety concerns for vulnerable road users, such as pedestrians and cyclists. This paper presents a review of recent developments in pedestrian and cyclist detection and intent estimation to increase the safety of autonomous vehicles, for both the driver and other road users. Understanding the intentions of the pedestrian/cyclist enables the self-driving vehicle to take actions to avoid incidents. To make this possible, development of methods/techniques, such as deep learning (DL), for the autonomous vehicle will be explored. For example, the development of pedestrian detection has been significantly advanced using DL approaches, such as; Fast Region-Convolutional Neural Network (R-CNN) , Faster R-CNN and Single Shot Detector (SSD). Although DL has been around for several decades, the hardware to realise the techniques have only recently become viable. Using these DL methods for pedestrian and cyclist detection and applying it for the tracking, motion modelling and pose estimation can allow for a successful and accurate method of intent estimation for the vulnerable road users. Although there has been a growth in research surrounding the study of pedestrian detection using vision-based approaches, further attention should include focus on cyclist detection. To further improve safety for these vulnerable road users (VRUs), approaches such as sensor fusion and intent estimation should be investigated.

AB - As autonomous vehicles become more common on the roads, their advancement draws on safety concerns for vulnerable road users, such as pedestrians and cyclists. This paper presents a review of recent developments in pedestrian and cyclist detection and intent estimation to increase the safety of autonomous vehicles, for both the driver and other road users. Understanding the intentions of the pedestrian/cyclist enables the self-driving vehicle to take actions to avoid incidents. To make this possible, development of methods/techniques, such as deep learning (DL), for the autonomous vehicle will be explored. For example, the development of pedestrian detection has been significantly advanced using DL approaches, such as; Fast Region-Convolutional Neural Network (R-CNN) , Faster R-CNN and Single Shot Detector (SSD). Although DL has been around for several decades, the hardware to realise the techniques have only recently become viable. Using these DL methods for pedestrian and cyclist detection and applying it for the tracking, motion modelling and pose estimation can allow for a successful and accurate method of intent estimation for the vulnerable road users. Although there has been a growth in research surrounding the study of pedestrian detection using vision-based approaches, further attention should include focus on cyclist detection. To further improve safety for these vulnerable road users (VRUs), approaches such as sensor fusion and intent estimation should be investigated.

KW - CNN

KW - Cyclist detection

KW - Deep learning

KW - Fast R-CNN

KW - Faster R-CNN

KW - Intent estimation

KW - Motion modelling

KW - Pedestrian detection

KW - Pose estimation

KW - Tracking

UR - http://www.scopus.com/inward/record.url?scp=85067255010&partnerID=8YFLogxK

U2 - 10.3390/app9112335

DO - 10.3390/app9112335

M3 - Article

VL - 9

JO - Applied Sciences

JF - Applied Sciences

SN - 2076-3417

IS - 11

M1 - 2335

ER -