Forward vehicle deceleration detection system for motorcycle at nighttime

Jian Kai Feng, Meng Lin Chiang, Shih Hsien Chuang, Chiung Yao Fang, Sei Wang Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes a forward vehicle (cars and motorcycles) deceleration detection system for motorcycles at nighttime. Compared with cars, motorcycles are more unstable and dangerous for drivers. However, vision-based driver assistance systems are seldom developed for motorcycles because the tilt rotation of the cameras on the motorcycles cause difficulties. Our proposed method solves this problem to stably detect the deceleration of forward vehicles at nighttime. The proposed system has four main stages: region of interest (ROI) adjustment and idling detection, taillight detection, taillight tracking, and brake light detection. The system first dynamically adjusts the size and position of the ROI and then detects the motions of forward vehicles using the Lucas-Kanade optical flow method. Second, the system detects the candidates of vehicle taillights and uses a support vector machine (SVM) model to identify and locate the position of taillights. Third, a Kalman filter technique is used to track the detected taillights. Since the taillights and brake lights of many vehicles are designed to overlap or be or very close, this step helps to detect the brake lights. Finally, a brake-light-activated threshold adjustment algorithm is applied to detect the starting moment of the brake lights of forward vehicles. The experimental results show that this proposed method obtains a stable result for forward vehicle detection for the motorcycle at nighttime.

Original languageEnglish
Title of host publication2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages515-521
Number of pages7
ISBN (Electronic)9781538683392
DOIs
Publication statusPublished - 2018 Dec
Event4th IEEE International Conference on Computer and Communications, ICCC 2018 - Chengdu, China
Duration: 2018 Dec 72018 Dec 10

Publication series

Name2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018

Conference

Conference4th IEEE International Conference on Computer and Communications, ICCC 2018
CountryChina
CityChengdu
Period18/12/718/12/10

Fingerprint

Motorcycles
Deceleration
Brakes
Railroad cars
Optical flows
Kalman filters
Support vector machines
Cameras

Keywords

  • Brake light detection
  • Kalman filter
  • Optical flow
  • Support vector machine (SVM)
  • Taillight detection
  • Vehicle deceleration detection system

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Cite this

Feng, J. K., Chiang, M. L., Chuang, S. H., Fang, C. Y., & Chen, S. W. (2018). Forward vehicle deceleration detection system for motorcycle at nighttime. In 2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018 (pp. 515-521). [8781069] (2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CompComm.2018.8781069

Forward vehicle deceleration detection system for motorcycle at nighttime. / Feng, Jian Kai; Chiang, Meng Lin; Chuang, Shih Hsien; Fang, Chiung Yao; Chen, Sei Wang.

2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 515-521 8781069 (2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Feng, JK, Chiang, ML, Chuang, SH, Fang, CY & Chen, SW 2018, Forward vehicle deceleration detection system for motorcycle at nighttime. in 2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018., 8781069, 2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018, Institute of Electrical and Electronics Engineers Inc., pp. 515-521, 4th IEEE International Conference on Computer and Communications, ICCC 2018, Chengdu, China, 18/12/7. https://doi.org/10.1109/CompComm.2018.8781069
Feng JK, Chiang ML, Chuang SH, Fang CY, Chen SW. Forward vehicle deceleration detection system for motorcycle at nighttime. In 2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 515-521. 8781069. (2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018). https://doi.org/10.1109/CompComm.2018.8781069
Feng, Jian Kai ; Chiang, Meng Lin ; Chuang, Shih Hsien ; Fang, Chiung Yao ; Chen, Sei Wang. / Forward vehicle deceleration detection system for motorcycle at nighttime. 2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 515-521 (2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018).
@inproceedings{a06e8997a1b7433fb70e3eeec7f4c971,
title = "Forward vehicle deceleration detection system for motorcycle at nighttime",
abstract = "This paper proposes a forward vehicle (cars and motorcycles) deceleration detection system for motorcycles at nighttime. Compared with cars, motorcycles are more unstable and dangerous for drivers. However, vision-based driver assistance systems are seldom developed for motorcycles because the tilt rotation of the cameras on the motorcycles cause difficulties. Our proposed method solves this problem to stably detect the deceleration of forward vehicles at nighttime. The proposed system has four main stages: region of interest (ROI) adjustment and idling detection, taillight detection, taillight tracking, and brake light detection. The system first dynamically adjusts the size and position of the ROI and then detects the motions of forward vehicles using the Lucas-Kanade optical flow method. Second, the system detects the candidates of vehicle taillights and uses a support vector machine (SVM) model to identify and locate the position of taillights. Third, a Kalman filter technique is used to track the detected taillights. Since the taillights and brake lights of many vehicles are designed to overlap or be or very close, this step helps to detect the brake lights. Finally, a brake-light-activated threshold adjustment algorithm is applied to detect the starting moment of the brake lights of forward vehicles. The experimental results show that this proposed method obtains a stable result for forward vehicle detection for the motorcycle at nighttime.",
keywords = "Brake light detection, Kalman filter, Optical flow, Support vector machine (SVM), Taillight detection, Vehicle deceleration detection system",
author = "Feng, {Jian Kai} and Chiang, {Meng Lin} and Chuang, {Shih Hsien} and Fang, {Chiung Yao} and Chen, {Sei Wang}",
year = "2018",
month = "12",
doi = "10.1109/CompComm.2018.8781069",
language = "English",
series = "2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "515--521",
booktitle = "2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018",

}

TY - GEN

T1 - Forward vehicle deceleration detection system for motorcycle at nighttime

AU - Feng, Jian Kai

AU - Chiang, Meng Lin

AU - Chuang, Shih Hsien

AU - Fang, Chiung Yao

AU - Chen, Sei Wang

PY - 2018/12

Y1 - 2018/12

N2 - This paper proposes a forward vehicle (cars and motorcycles) deceleration detection system for motorcycles at nighttime. Compared with cars, motorcycles are more unstable and dangerous for drivers. However, vision-based driver assistance systems are seldom developed for motorcycles because the tilt rotation of the cameras on the motorcycles cause difficulties. Our proposed method solves this problem to stably detect the deceleration of forward vehicles at nighttime. The proposed system has four main stages: region of interest (ROI) adjustment and idling detection, taillight detection, taillight tracking, and brake light detection. The system first dynamically adjusts the size and position of the ROI and then detects the motions of forward vehicles using the Lucas-Kanade optical flow method. Second, the system detects the candidates of vehicle taillights and uses a support vector machine (SVM) model to identify and locate the position of taillights. Third, a Kalman filter technique is used to track the detected taillights. Since the taillights and brake lights of many vehicles are designed to overlap or be or very close, this step helps to detect the brake lights. Finally, a brake-light-activated threshold adjustment algorithm is applied to detect the starting moment of the brake lights of forward vehicles. The experimental results show that this proposed method obtains a stable result for forward vehicle detection for the motorcycle at nighttime.

AB - This paper proposes a forward vehicle (cars and motorcycles) deceleration detection system for motorcycles at nighttime. Compared with cars, motorcycles are more unstable and dangerous for drivers. However, vision-based driver assistance systems are seldom developed for motorcycles because the tilt rotation of the cameras on the motorcycles cause difficulties. Our proposed method solves this problem to stably detect the deceleration of forward vehicles at nighttime. The proposed system has four main stages: region of interest (ROI) adjustment and idling detection, taillight detection, taillight tracking, and brake light detection. The system first dynamically adjusts the size and position of the ROI and then detects the motions of forward vehicles using the Lucas-Kanade optical flow method. Second, the system detects the candidates of vehicle taillights and uses a support vector machine (SVM) model to identify and locate the position of taillights. Third, a Kalman filter technique is used to track the detected taillights. Since the taillights and brake lights of many vehicles are designed to overlap or be or very close, this step helps to detect the brake lights. Finally, a brake-light-activated threshold adjustment algorithm is applied to detect the starting moment of the brake lights of forward vehicles. The experimental results show that this proposed method obtains a stable result for forward vehicle detection for the motorcycle at nighttime.

KW - Brake light detection

KW - Kalman filter

KW - Optical flow

KW - Support vector machine (SVM)

KW - Taillight detection

KW - Vehicle deceleration detection system

UR - http://www.scopus.com/inward/record.url?scp=85070806328&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070806328&partnerID=8YFLogxK

U2 - 10.1109/CompComm.2018.8781069

DO - 10.1109/CompComm.2018.8781069

M3 - Conference contribution

AN - SCOPUS:85070806328

T3 - 2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018

SP - 515

EP - 521

BT - 2018 IEEE 4th International Conference on Computer and Communications, ICCC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -