Robust obstacle detection for advanced driver assistance systems using distortions of inverse perspective mapping of a monocular camera

Charan D. Prakash, Farshad Akhbari, Lina Karam

Research output: Contribution to journalArticle

Abstract

This paper presents a robust method for generic obstacle detection and collision warning in Advanced Driver Assistance Systems (ADAS). The highlight of our method is the ability to detect all obstacles without prior knowledge and detect partially occluded obstacles including the obstacles that have not completely appeared in the frame (truncated obstacles). Our results show an improvement of 90% more true positives per frame compared to one of the state-of-the-art methods. Our proposed method is robust to variations in illumination and to a wide variety of vehicles and obstacles that are encountered while driving. Distortions are introduced when Inverse Perspective Mapping (IPM) projects the camera image onto the road surface plane. In this paper, we first show that the angular distortion in the IPM domain belonging to obstacle edges varies as a function of their corresponding 2D location in the camera plane. We use this information to perform proposal generation. We propose a novel proposal assessment method based on fusing statistical properties from both the IPM image and the camera image to perform robust outlier elimination and false positive reduction. We also present an annotated obstacle detection dataset derived from various source videos that can serve as a benchmark for the evaluation of future obstacle detection algorithms. The source videos containing diverse illumination and traffic conditions are derived from multiple publicly available datasets.

Original languageEnglish (US)
Pages (from-to)172-186
Number of pages15
JournalRobotics and Autonomous Systems
Volume114
DOIs
StatePublished - Apr 1 2019

Fingerprint

Advanced driver assistance systems
Obstacle Detection
Driver Assistance
Camera
Cameras
Lighting
Information use
Illumination
Robust Methods
False Positive
Prior Knowledge
Statistical property
Outlier
Elimination
Collision
Traffic
Vary
Benchmark
Evaluation

Keywords

  • Advanced Driver Assistance Systems (ADAS)
  • Fused statistical properties
  • Inverse Perspective Mapping (IPM)
  • Obstacle detection
  • Occlusion
  • Proposal assessment
  • Selective Edge Filtering (SEF)

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Mathematics(all)
  • Computer Science Applications

Cite this

Robust obstacle detection for advanced driver assistance systems using distortions of inverse perspective mapping of a monocular camera. / Prakash, Charan D.; Akhbari, Farshad; Karam, Lina.

In: Robotics and Autonomous Systems, Vol. 114, 01.04.2019, p. 172-186.

Research output: Contribution to journalArticle

@article{fc9afd21107d44fd9f67a662b63f8b9f,
title = "Robust obstacle detection for advanced driver assistance systems using distortions of inverse perspective mapping of a monocular camera",
abstract = "This paper presents a robust method for generic obstacle detection and collision warning in Advanced Driver Assistance Systems (ADAS). The highlight of our method is the ability to detect all obstacles without prior knowledge and detect partially occluded obstacles including the obstacles that have not completely appeared in the frame (truncated obstacles). Our results show an improvement of 90{\%} more true positives per frame compared to one of the state-of-the-art methods. Our proposed method is robust to variations in illumination and to a wide variety of vehicles and obstacles that are encountered while driving. Distortions are introduced when Inverse Perspective Mapping (IPM) projects the camera image onto the road surface plane. In this paper, we first show that the angular distortion in the IPM domain belonging to obstacle edges varies as a function of their corresponding 2D location in the camera plane. We use this information to perform proposal generation. We propose a novel proposal assessment method based on fusing statistical properties from both the IPM image and the camera image to perform robust outlier elimination and false positive reduction. We also present an annotated obstacle detection dataset derived from various source videos that can serve as a benchmark for the evaluation of future obstacle detection algorithms. The source videos containing diverse illumination and traffic conditions are derived from multiple publicly available datasets.",
keywords = "Advanced Driver Assistance Systems (ADAS), Fused statistical properties, Inverse Perspective Mapping (IPM), Obstacle detection, Occlusion, Proposal assessment, Selective Edge Filtering (SEF)",
author = "Prakash, {Charan D.} and Farshad Akhbari and Lina Karam",
year = "2019",
month = "4",
day = "1",
doi = "10.1016/j.robot.2018.12.004",
language = "English (US)",
volume = "114",
pages = "172--186",
journal = "Robotics and Autonomous Systems",
issn = "0921-8890",
publisher = "Elsevier",

}

TY - JOUR

T1 - Robust obstacle detection for advanced driver assistance systems using distortions of inverse perspective mapping of a monocular camera

AU - Prakash, Charan D.

AU - Akhbari, Farshad

AU - Karam, Lina

PY - 2019/4/1

Y1 - 2019/4/1

N2 - This paper presents a robust method for generic obstacle detection and collision warning in Advanced Driver Assistance Systems (ADAS). The highlight of our method is the ability to detect all obstacles without prior knowledge and detect partially occluded obstacles including the obstacles that have not completely appeared in the frame (truncated obstacles). Our results show an improvement of 90% more true positives per frame compared to one of the state-of-the-art methods. Our proposed method is robust to variations in illumination and to a wide variety of vehicles and obstacles that are encountered while driving. Distortions are introduced when Inverse Perspective Mapping (IPM) projects the camera image onto the road surface plane. In this paper, we first show that the angular distortion in the IPM domain belonging to obstacle edges varies as a function of their corresponding 2D location in the camera plane. We use this information to perform proposal generation. We propose a novel proposal assessment method based on fusing statistical properties from both the IPM image and the camera image to perform robust outlier elimination and false positive reduction. We also present an annotated obstacle detection dataset derived from various source videos that can serve as a benchmark for the evaluation of future obstacle detection algorithms. The source videos containing diverse illumination and traffic conditions are derived from multiple publicly available datasets.

AB - This paper presents a robust method for generic obstacle detection and collision warning in Advanced Driver Assistance Systems (ADAS). The highlight of our method is the ability to detect all obstacles without prior knowledge and detect partially occluded obstacles including the obstacles that have not completely appeared in the frame (truncated obstacles). Our results show an improvement of 90% more true positives per frame compared to one of the state-of-the-art methods. Our proposed method is robust to variations in illumination and to a wide variety of vehicles and obstacles that are encountered while driving. Distortions are introduced when Inverse Perspective Mapping (IPM) projects the camera image onto the road surface plane. In this paper, we first show that the angular distortion in the IPM domain belonging to obstacle edges varies as a function of their corresponding 2D location in the camera plane. We use this information to perform proposal generation. We propose a novel proposal assessment method based on fusing statistical properties from both the IPM image and the camera image to perform robust outlier elimination and false positive reduction. We also present an annotated obstacle detection dataset derived from various source videos that can serve as a benchmark for the evaluation of future obstacle detection algorithms. The source videos containing diverse illumination and traffic conditions are derived from multiple publicly available datasets.

KW - Advanced Driver Assistance Systems (ADAS)

KW - Fused statistical properties

KW - Inverse Perspective Mapping (IPM)

KW - Obstacle detection

KW - Occlusion

KW - Proposal assessment

KW - Selective Edge Filtering (SEF)

UR - http://www.scopus.com/inward/record.url?scp=85061628277&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061628277&partnerID=8YFLogxK

U2 - 10.1016/j.robot.2018.12.004

DO - 10.1016/j.robot.2018.12.004

M3 - Article

VL - 114

SP - 172

EP - 186

JO - Robotics and Autonomous Systems

JF - Robotics and Autonomous Systems

SN - 0921-8890

ER -