ROBUST TRAFFIC LIGHT DETECTION AND CLASSIFICATION UNDER DAY AND NIGHT CONDITIONS

被引：0

作者：

Phuc Manh Nguyen ^{[1
]}

Vu Cong Nguyen ^{[1
]}

Son Ngoc Nguyen ^{[1
]}

Linh My Thi Dang ^{[1
]}

Ha Xuan Nguyen ^{[2
]}

Vinh Dinh Nguyen ^{[2
]}

机构：

[1] Eastern Int Univ, Sch Comp & Informat Technol, Dept Software Engn, Binh Duong, Vietnam

[2] Sungkyunkwan Univ, Sch Informat & Commun Engn, Dept Elect & Comp Engn, Suwon, South Korea

来源：

2020 20TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS (ICCAS) | 2020年

关键词：

Traffic light detection; hand-craft feature; deep learning; adverse weather condition; RECOGNITION;

D O I：

10.23919/iccas50221.2020.9268343

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Recently, traffic light detection and classification systems have been studied and developed to build an autonomous car by many research institutes, universities, and companies. However, the results of existing traffic light detection systems are still not stable under day and night conditions. It is difficult to detect the location of traffic light due to their small size. Moreover, traffic lights' shapes are also similar to advertisement lights in a city road. Therefore, this paper proposed a new approach to improve the performance of existing traffic light detection systems by using the benefits of hand-crafted features and deep learning techniques. Experimental results show that the proposed system obtained the detection rate of 80% under night conditions, while the color-based density method only got the detection rate of 50.43% under night conditions.

引用

页码：565 / 570

页数：6

共 25 条

[1]

[Anonymous], 2012, INT C COMP VIS THEOR

[2]

Barnes D, 2015, IEEE INT VEH SYM, P573, DOI 10.1109/IVS.2015.7225746

[3] Automatic large-scale data acquisition via crowdsourcing for crosswalk classification: A deep learning approach [J].

Berriel, Rodrigo F. ;

Rossi, Franco Schmidt ;

de Souza, Alberto F. ;

Oliveira-Santos, Thiago .

COMPUTERS & GRAPHICS-UK, 2017, 68 :32-42

[4] Deep Learning-Based Large-Scale Automatic Satellite Crosswalk Classification [J].

Berriel, Rodrigo F. ;

Lopes, Andre Teixeira ;

de Souza, Alberto F. ;

Oliveira-Santos, Thiago .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2017, 14 (09) :1513-1517

[5]

Cai Z., 2012, Computational Intelligence for Security and Defence Applications (CISDA), 2012 IEEE Symposium on, P1, DOI DOI 10.1109/CISDA.2012.6291516

[6]

Chiang CC, 2011, INT J INNOV COMPUT I, V7, P6919

[7] Traffic Light Recognition using Image Processing Compared to Learning Processes [J].

de Charette, Raoul ;

Nashashibi, Fawzi .

2009 IEEE-RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, 2009, :333-338

[8] Real Time Visual Trafric Lights Recognition Based on Spot Light Detection and Adaptive Traffic Lights Templates [J].

de Charette, Raoul ;

Nashashibi, Fawzi .

2009 IEEE INTELLIGENT VEHICLES SYMPOSIUM, VOLS 1 AND 2, 2009, :358-363

[9] Robust real-time traffic light detection and distance estimation using a single camera [J].

Diaz-Cabrera, Moises ;

Cerri, Pietro ;

Medici, Paolo .

EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (08) :3911-3923

[10] Semantic Segmentation Based Traffic Light Detection at Day and at Night [J].

Haltakov, Vladimir ;

Mayr, Jakob ;

Unger, Christian ;

Ilic, Slobodan .

PATTERN RECOGNITION, GCPR 2015, 2015, 9358 :446-457

← 1 2 3 →