The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Nous proposons une méthode qui détecte les véhicules à partir d'images de caméra monoculaire embarquées capturées pendant la conduite de nuit. La détection des véhicules à partir de leur forme est difficile la nuit ; cependant, de nombreuses méthodes de détection de véhicules axées sur la lumière ont été proposées. Nous détectons les points lumineux par binarisation appropriée en fonction des caractéristiques des feux du véhicule telles que la luminosité et la couleur. De plus, comme les points lumineux détectés incluent des lumières autres que celles des véhicules, nous devons distinguer les feux du véhicule des autres points lumineux. Par conséquent, les points lumineux ont été distingués à l’aide de Random Forest, un algorithme d’apprentissage automatique de classification multiclasse. Les caractéristiques des points lumineux non associés aux véhicules ont été utilisées efficacement dans la détection des véhicules dans la méthode proposée. Plus précisément, la détection des véhicules est effectuée en attribuant des pondérations aux résultats de la forêt aléatoire sur la base des caractéristiques des points lumineux du véhicule et des caractéristiques des points brillants non liés au véhicule. Notre méthode proposée a été appliquée aux images nocturnes et a confirmé son efficacité.
Yuta SAKAGAWA
Shizuoka University
Kosuke NAKAJIMA
Shizuoka University
Gosuke OHASHI
Shizuoka University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Yuta SAKAGAWA, Kosuke NAKAJIMA, Gosuke OHASHI, "Vision Based Nighttime Vehicle Detection Using Adaptive Threshold and Multi-Class Classification" in IEICE TRANSACTIONS on Fundamentals,
vol. E102-A, no. 9, pp. 1235-1245, September 2019, doi: 10.1587/transfun.E102.A.1235.
Abstract: We propose a method that detects vehicles from in-vehicle monocular camera images captured during nighttime driving. Detecting vehicles from their shape is difficult at night; however, many vehicle detection methods focusing on light have been proposed. We detect bright spots by appropriate binarization based on the characteristics of vehicle lights such as brightness and color. Also, as the detected bright spots include lights other than vehicles, we need to distinguish the vehicle lights from other bright spots. Therefore, the bright spots were distinguished using Random Forest, a multiclass classification machine-learning algorithm. The features of bright spots not associated with vehicles were effectively utilized in the vehicle detection in our proposed method. More precisely vehicle detection is performed by giving weights to the results of the Random Forest based on the features of vehicle bright spots and the features of bright spots not related to the vehicle. Our proposed method was applied to nighttime images and confirmed effectiveness.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E102.A.1235/_p
Copier
@ARTICLE{e102-a_9_1235,
author={Yuta SAKAGAWA, Kosuke NAKAJIMA, Gosuke OHASHI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Vision Based Nighttime Vehicle Detection Using Adaptive Threshold and Multi-Class Classification},
year={2019},
volume={E102-A},
number={9},
pages={1235-1245},
abstract={We propose a method that detects vehicles from in-vehicle monocular camera images captured during nighttime driving. Detecting vehicles from their shape is difficult at night; however, many vehicle detection methods focusing on light have been proposed. We detect bright spots by appropriate binarization based on the characteristics of vehicle lights such as brightness and color. Also, as the detected bright spots include lights other than vehicles, we need to distinguish the vehicle lights from other bright spots. Therefore, the bright spots were distinguished using Random Forest, a multiclass classification machine-learning algorithm. The features of bright spots not associated with vehicles were effectively utilized in the vehicle detection in our proposed method. More precisely vehicle detection is performed by giving weights to the results of the Random Forest based on the features of vehicle bright spots and the features of bright spots not related to the vehicle. Our proposed method was applied to nighttime images and confirmed effectiveness.},
keywords={},
doi={10.1587/transfun.E102.A.1235},
ISSN={1745-1337},
month={September},}
Copier
TY - JOUR
TI - Vision Based Nighttime Vehicle Detection Using Adaptive Threshold and Multi-Class Classification
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1235
EP - 1245
AU - Yuta SAKAGAWA
AU - Kosuke NAKAJIMA
AU - Gosuke OHASHI
PY - 2019
DO - 10.1587/transfun.E102.A.1235
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E102-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 2019
AB - We propose a method that detects vehicles from in-vehicle monocular camera images captured during nighttime driving. Detecting vehicles from their shape is difficult at night; however, many vehicle detection methods focusing on light have been proposed. We detect bright spots by appropriate binarization based on the characteristics of vehicle lights such as brightness and color. Also, as the detected bright spots include lights other than vehicles, we need to distinguish the vehicle lights from other bright spots. Therefore, the bright spots were distinguished using Random Forest, a multiclass classification machine-learning algorithm. The features of bright spots not associated with vehicles were effectively utilized in the vehicle detection in our proposed method. More precisely vehicle detection is performed by giving weights to the results of the Random Forest based on the features of vehicle bright spots and the features of bright spots not related to the vehicle. Our proposed method was applied to nighttime images and confirmed effectiveness.
ER -