Object detection and tracking for automotive domain

S. Yildirim; Technische Universiteit Eindhoven (TUE). Stan Ackermans Instituut. Software Technology (ST)

Object detection and tracking for automotive domain

S. Yildirim, Technische Universiteit Eindhoven (TUE). Stan Ackermans Instituut. Software Technology (ST)

Research output: Thesis › EngD Thesis

Abstract

Computer vision to achieve object detection, tracking and recognition will become hugely important in future Advanced Driving Assistance Systems (ADAS). A variety of smart sensors has become available, including radar, lidar, ultra sound, and video cameras that monitor the environment around the vehicle. Camera-based systems have immensely progressed in recent years and will be an indispensable part of ADAS. Cameras are now cheaper, smaller, and of higher quality than ever before. Concurrently, computing power has dramatically increased. For that reason, NXP started an investigation into the principles, capabilities and future requirements of smart camera systems, being able to detect and track objects with a large degree of accuracy and confidence. In this project, insights about the feature extraction methods for object detection and tracking in automotive domain are gained. Various methods are compared with respect to their suitability for the major use cases, namely, vehicles, pedestrians, traffic signs, and lanes.

Original language	English
Awarding Institution
Supervisors/Advisors	Özçelebi, Tanir, Supervisor Raaijmakers, Han, External supervisor, External person
Award date	1 Oct 2014
Place of Publication	Eindhoven
Publisher	Technische Universiteit Eindhoven
Print ISBNs	978-90-444-1319-9
Publication status	Published - 1 Oct 2014

Bibliographical note

Eindverslag.

Cite this

@phdthesis{a3dfc18847b641e28ab62cb998c62cfe,

title = "Object detection and tracking for automotive domain",

abstract = "Computer vision to achieve object detection, tracking and recognition will become hugely important in future Advanced Driving Assistance Systems (ADAS). A variety of smart sensors has become available, including radar, lidar, ultra sound, and video cameras that monitor the environment around the vehicle. Camera-based systems have immensely progressed in recent years and will be an indispensable part of ADAS. Cameras are now cheaper, smaller, and of higher quality than ever before. Concurrently, computing power has dramatically increased. For that reason, NXP started an investigation into the principles, capabilities and future requirements of smart camera systems, being able to detect and track objects with a large degree of accuracy and confidence. In this project, insights about the feature extraction methods for object detection and tracking in automotive domain are gained. Various methods are compared with respect to their suitability for the major use cases, namely, vehicles, pedestrians, traffic signs, and lanes.",

author = "S. Yildirim and {Technische Universiteit Eindhoven (TUE). Stan Ackermans Instituut. Software Technology (ST)}",

note = "Eindverslag.",

year = "2014",

month = oct,

day = "1",

language = "English",

isbn = "978-90-444-1319-9",

series = "PDEng rapport",

publisher = "Technische Universiteit Eindhoven",

}

TY - THES

T1 - Object detection and tracking for automotive domain

AU - Yildirim, S.

AU - Technische Universiteit Eindhoven (TUE). Stan Ackermans Instituut. Software Technology (ST)

N1 - Eindverslag.

PY - 2014/10/1

Y1 - 2014/10/1

N2 - Computer vision to achieve object detection, tracking and recognition will become hugely important in future Advanced Driving Assistance Systems (ADAS). A variety of smart sensors has become available, including radar, lidar, ultra sound, and video cameras that monitor the environment around the vehicle. Camera-based systems have immensely progressed in recent years and will be an indispensable part of ADAS. Cameras are now cheaper, smaller, and of higher quality than ever before. Concurrently, computing power has dramatically increased. For that reason, NXP started an investigation into the principles, capabilities and future requirements of smart camera systems, being able to detect and track objects with a large degree of accuracy and confidence. In this project, insights about the feature extraction methods for object detection and tracking in automotive domain are gained. Various methods are compared with respect to their suitability for the major use cases, namely, vehicles, pedestrians, traffic signs, and lanes.

AB - Computer vision to achieve object detection, tracking and recognition will become hugely important in future Advanced Driving Assistance Systems (ADAS). A variety of smart sensors has become available, including radar, lidar, ultra sound, and video cameras that monitor the environment around the vehicle. Camera-based systems have immensely progressed in recent years and will be an indispensable part of ADAS. Cameras are now cheaper, smaller, and of higher quality than ever before. Concurrently, computing power has dramatically increased. For that reason, NXP started an investigation into the principles, capabilities and future requirements of smart camera systems, being able to detect and track objects with a large degree of accuracy and confidence. In this project, insights about the feature extraction methods for object detection and tracking in automotive domain are gained. Various methods are compared with respect to their suitability for the major use cases, namely, vehicles, pedestrians, traffic signs, and lanes.

M3 - EngD Thesis

SN - 978-90-444-1319-9

T3 - PDEng rapport

PB - Technische Universiteit Eindhoven

CY - Eindhoven

ER -

Object detection and tracking for automotive domain

Abstract

Bibliographical note

Fingerprint

Cite this