Full Record

New Search | Similar Records

Publication Date
Date Available
Degree MASc
Degree Level masters
University/Publisher McMaster University

This thesis proposes a novel multiple traffic light recognition system based on videos captured by a monocular camera. Advanced driver assistance system (ADAS) and autonomous driving system (ADS) are becoming increasingly important to help drivers maneuvering vehicles and increase the vehicle and road safety in modern life. Traffic light recognition system is a significant part of ADAS and ADS, which can detect traffic light on the road and recognize different types of traffic lights to provide useful signal information for drivers. The proposed method can be applied to real complex environment only based on a monocular camera and is tested in real-world scenarios. This system consists of three parts: multiple traffic light detection, multi-target tracking and state classification. For the first step, a supervised machine learning method, support vector machine (SVM) with two integral features - histogram of oriented gradients (HOG) and histogram of CIELAB color space (HCIELAB), are used to detect traffic lights in the captured image. Then, a new multi-target tracking algorithm is presented to improve the accuracy of detection, reduce the number of false alarm and missing targets, by means of nearest neighbor data association, motion model analysis and Lucas-Kanade optical flow tracking and the region of interest (ROI) prediction. Finally, a SVM-based and a convolution neural network (CNN) based classifiers are introduced to classify the state of traffic lights, that provides the stop, go, warning, straight and turn information. Various experiments have been conducted to demonstrate the practicability of the proposed method. Both GPU-based and CPU-based programming can run real-time on the real street environment.


Master of Applied Science (MASc)

Subjects/Keywords multiple traffic light recognition
Contributors Kirubarajan, Thia; Electrical and Computer Engineering
Language en
Country of Publication ca
Record ID handle:11375/23081
Repository mcmaster
Date Indexed 2020-08-12

Sample Search Hits | Sample Images | Cited Works

…Multiple traffic lights recognition NN - Nearest neighbor RNN - Recurrent neural network vii ROI - Region of interest SVM - Support vector machine TL - Traffic light TLR - Traffic light recognition viii Contents Abstract iv…

…Acknowledgements vi Notation and abbreviations vii 1 INTRODUCTION 1 1.1 Multiple Traffic Light Recognition System . . . . . . . . . . . . . . . 1 1.2 Contributions of the Thesis . . . . . . . . . . . . . . . . . . . . . . . 5 1.3 Organization of the…

…52 5.7 Some failing classification TL . . . . . . . . . . . . . . . . . . . . . . 52 xiii Chapter 1 INTRODUCTION 1.1 Multiple Traffic Light Recognition System Traffic light recognition (TLR) system based on a monocular camera plays…

…methods to address it. Existing TLR algorithms can be divided into three categories, model-based methods, learning-based methods and mapping-based methods. Model-based methods have been widely used to deal with multiple traffic light recognition (MTLR…

…system such as multiple classes, color tone shifting, occlusion, false positives from other lights and synchronization issues [30]. More specifically, the challenges can be multiple structures of the traffic light (TL) detection, for a…

…10] proposed a general framework to improve the performance of object detection for a given 3D occurrence prior. [33] proposed an automated method mapping the 3D position of TL and robustly detect the state of traffic light on-board…

…majority of model-based methods, the color information is affected by different illumination condition and TL templates are difficult to model for all the TL in the world. 1.2 Contributions of the Thesis In this thesis, a novel multiple traffic light

…practical traffic system, the orientation (vertical and horizontal), color(green, red and yellow), aspect ratio (3-lamp, 4-lamp, 3*3-lamp and so on) and shape (circle and arrow) of the TL being different from country…