Real Time Traffic Light Detection by Autonomous Vehicles using Artificial Neural Network Techniques

Autonomous vehicles are the reality of the future, they will open up the way for future advanced systems where computers are expected to take over the decision making of driving. These automobiles are capable of sensing their environment and moving with little or no human input. The main goal of this research is to detect traffic light in real-time for autonomous vehicles. Apart from taking decisions to navigate in the right manner the autonomous vehicles important task is to detect traffic lights, so that it can obey the traffic rules with sufficient precision. The work carried out in this research makes use of two Artificial Intelligence technique, these techniques are compared in accomplishing the task of traffic light detection in real time. The two models that are designed and implemented are Convolution neural network (CNN) and Deep Convolution Inverse Graphics Network (DCIGN). The results clearly show that DCIGN out performance CNN by 8%.

Download Full-text

Frequency Maps as Expert Instructions to Lessen Data Dependency on Real-time Traffic Light Recognition

10.20944/preprints202008.0138.v1 ◽

2020 ◽

Author(s):

Hendrik Macedo ◽

Thiago Almeida ◽

Leonardo Matos ◽

Bruno Prado

Keyword(s):

Real Time ◽

Autonomous Vehicles ◽

Machine Learning Algorithms ◽

Support Vector ◽

Background Suppression ◽

Processing Unit ◽

Traffic Light ◽

Traffic Lights ◽

Real Time Traffic ◽

Computational Resources

Research on Traffic Light Recognition (TLR) has grown in recent years, primarily driven by the growing interest in autonomous vehicles development. Machine Learning algorithms have been widely used to that purpose. Mainstream approaches, however, require large amount of data to properly work, and as a consequence, a lot of computational resources. In this paper we propose the use of Expert Instruction (IE) as a mechanism to reduce the amount of data required to provide accurate ML models for TLR. Given an image of the exterior scene taken from the inside of the vehicle, we stand the hypothesis that the picture of a traffic light is more likely to appear in the central and upper regions of the image. Frequency Maps of traffic light location were thus constructed to confirm this hypothesis. The frequency maps are the result of a manual effort of human experts in annotating each image with the coordinates of the region where the traffic light appears. Results show that EI increased the accuracy obtained by the classification algorithm in two different image datasets by at least 15%. Evaluation rates achieved by the inclusion of EI were also higher in further experiments, including traffic light detection followed by classification by the trained algorithm. The inclusion of EI in the PCANet achieved a precision of 83% and recall of 73% against 75.3% and 51.1%, respectively, of its counterpart. We finally presents a prototype of a TLR Device with that expert model embedded to assist drivers. The TLR uses a smartphone as a camera and processing unit. To show the feasibility of the apparatus, a dataset was obtained in real time usage and tested in an Adaptive Background Suppression Filter (AdaBSF) and Support Vector Machines (SVMs) algorithm to detect and recognize traffic lights. Results show precision of 100% and recall of 65%.

Download Full-text

Saliency Map Generation by the Convolutional Neural Network for Real-Time Traffic Light Detection Using Template Matching

IEEE Transactions on Computational Imaging ◽

10.1109/tci.2015.2480006 ◽

2015 ◽

Vol 1 (3) ◽

pp. 159-173 ◽

Cited By ~ 34

Author(s):

Vijay John ◽

Keisuke Yoneda ◽

Zheng Liu ◽

Seiichi Mita

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Real Time ◽

Template Matching ◽

Saliency Map ◽

Traffic Light ◽

Light Detection ◽

Real Time Traffic ◽

Map Generation

Download Full-text

Deep Learning Technique for Real-time Traffic Light Detection by Automated Vehicles

International Journal of Computer Sciences and Engineering ◽

10.26438/ijcse/v6i7.387392 ◽

2018 ◽

Vol 6 (7) ◽

pp. 387-392

Author(s):

Priyanka S.N. ◽

Shashidhara H.S.

Keyword(s):

Deep Learning ◽

Real Time ◽

Automated Vehicles ◽

Traffic Light ◽

Light Detection ◽

Real Time Traffic ◽

Learning Technique

Download Full-text

TRAFFIC LIGHT DETECTION USING CONIC SECTION GEOMETRY

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-annals-iii-1-191-2016 ◽

2016 ◽

Vol III-1 ◽

pp. 191-200

Author(s):

S. Hosseinyalmdary ◽

A. Yilmaz

Keyword(s):

Prior Knowledge ◽

Pose Estimation ◽

Open Problem ◽

Autonomous Vehicles ◽

Conic Section ◽

Traffic Light ◽

Light Detection ◽

State Recognition ◽

Traffic Lights ◽

Stereo Cameras

Traffic lights detection and their state recognition is a crucial task that autonomous vehicles must reliably fulfill. Despite scientific endeavors, it still is an open problem due to the variations of traffic lights and their perception in image form. Unlike previous studies, this paper investigates the use of inaccurate and publicly available GIS databases such as OpenStreetMap. In addition, we are the first to exploit conic section geometry to improve the shape cue of the traffic lights in images. Conic section also enables us to estimate the pose of the traffic lights with respect to the camera. Our approach can detect multiple traffic lights in the scene, it also is able to detect the traffic lights in the absence of prior knowledge, and detect the traffics lights as far as 70 meters. The proposed approach has been evaluated for different scenarios and the results show that the use of stereo cameras significantly improves the accuracy of the traffic lights detection and pose estimation.

Download Full-text

CTL-DNNet: Effective Circular Traffic Light Recognition with a Deep Neural Network

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001417500379 ◽

2017 ◽

Vol 31 (11) ◽

pp. 1750037 ◽

Cited By ~ 3

Author(s):

Di Wang ◽

Hong Bao ◽

Feifei Zhang

Keyword(s):

Neural Network ◽

Autonomous Vehicles ◽

Deep Neural Network ◽

Road Traffic ◽

High Accuracy ◽

Activation Functions ◽

Traffic Light ◽

Traffic Lights ◽

Learning Network ◽

Deep Learning Network

This paper proposed an algorithm for a deep learning network for identifying circular traffic lights (CTL-DNNet). The sample labeling process uses translation to increase the number of positive samples, and the similarity is calculated to reduce the number of negative samples, thereby reducing overfitting. We use a dataset of approximately 370[Formula: see text]000 samples, with approximately 20[Formula: see text]000 positive samples and approximately 350[Formula: see text]000 negative samples. The datasets are generated from images taken at the Beijing Garden Expo. To obtain a very robust method for the detection of traffic lights, we use different layers, different cost functions and different activation functions of the depth neural network for training and comparison. Our algorithm has evaluated autonomous vehicles in varying illumination and gets the result with high accuracy and robustness. The experimental results show that CTL-DNNet is effective at recognizing road traffic lights in the Beijing Garden Expo area.

Download Full-text