Traffic-sign recognition

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search
Traffic-sign (speed limit) recognition

Traffic-sign recognition (TSR) is a technology by which a vehicle is able to recognize the traffic signs put on the road e.g. "speed limit" or "children" or "turn ahead". This is part of the features collectively called ADAS. The technology is being developed by a variety of automotive suppliers. It uses image processing techniques to detect the traffic signs. The detection methods can be generally divided into color based, shape based and learning based methods.

History[edit]

The Vienna Convention on Road Signs and Signals is a treaty signed in 1968 which has been able to standardize traffic signs across different countries. About 52 countries have signed this treaty, which includes 31 countries from Europe. The convention has broadly classified the road signs into seven categories designated with letters A to H. This standardization has been the main drive for helping the development of traffic-sign recognition systems that can be used globally.

A speed limit sign in the United States

Traffic-sign recognition first appeared, in the form of speed limit sign recognition, in 2008 for the 2009 Vauxhall Insignia.[1] Later in 2009 they appered on the new BMW 7 Series, and the following year on the Mercedes-Benz S-Class. At that time, these systems only detected the round speed limit signs found all across Europe (e.g.[2]).

Second-generation systems can also detect overtaking restrictions. It was introduced in 2008 in the Opel Insignia,[3] later followed by the Opel Astra and the Saab 9-5. This technology is also available on the 2011 Volkswagen Phaeton[4] and, since 2012, in the Volvo S80, V70, XC70, XC60, S60, V60 and V40, as a technology called Road Sign Information.[5] They are not able to recognize city limit signs, which in most European countries are associated with speed limits, as they are too similar to direction signs.

Such systems are expected to be mandatory on new cars sold in the EU from May 2022.

Working[edit]

How does a traffic-sign recognition system work?[edit]

Traffic signs can be analyzed using forward-facing cameras in many modern cars, vehicles and trucks. One of the basic use cases of a traffic-sign recognition system is for speed limits. Most of the GPS data would procure speed information, but additional speed limit traffic signs can also be used to extract information and display it in the dashboard of the car to alert the driver about the road sign. This is an advanced driver-assistance feature available in most high-end cars, mainly in European vehicles.

An example algorithm for traffic-sign detection

Modern traffic-sign recognition systems are being developed using convolutional neural networks, mainly driven by the requirements of autonomous vehicles and self-driving cars. In these scenarios, the detection system needs to identify a variety of traffic signs and not just speed limits. This is where the Vienna Convention on Road Signs and Signals comes to help. A convolutional neural network can be trained to take in these predefined traffic signs and 'learn' using Deep Learning techniques.

The neural net in turn uses Image Processing and Computer Vision to train the network with its potential outcomes. The trained neural net can then be used in real time to detect new traffic signs in real time. Self driving car companies including Waymo and Uber are generating and outsourcing traffic-sign data sets along with map and navigation companies like Tom Tom.[6] Advanced computer vision and neural network techniques make this goal highly efficient and achievable in real time.

An example implementation of the image preprocessing steps in a traffic-sign detection algorithm

There are diverse algorithms for traffic-sign recognition. Common ones are those based on the shape of the sign board. Typical sign board shapes like hexagons, circles, and rectangles define different types of signs, which can be used for classification. Other major algorithms for character recognition includes Haar-like features, Freeman Chain code, AdaBoost detection and deep learning neural networks methods. Haar-like features can be used to create cascaded classifiers which can then help detect the sign board characters.

Deep learning can be incorporated into traffic-sign detection. Polygonal approximation of digital curves using Ramer–Douglas–Peucker algorithm can be used to detect the shape of the sign boards and methods like Support Vector Machines and Byte-MCT with an AdaBoost classifier has been used in one of the methods to detect traffic signs.[7]

Vehicles using traffic-sign recognition[edit]

Vehicles with a current battery electric version are shown in lime  E .

Vehicles with a current hydrogen fuel cell version are shown in aquamarine  C .

Vehicles with a current plug-in hybrid version are shown in deep sky blue  P .

Vehicles with a current full hybrid version are shown in yellow  F .

Vehicles with a current mild hybrid version are shown in magenta  M .

Vehicles with a current CNG version are shown in orange  N .

Vehicles with a current LPG version are shown in dark violet  L .


Aston Martin Aurus BAIC BMW BYD Brilliance
BMW MINI Rolls-Royce Zinoro

Senat

1 Series[8]
2 Series
3 Series  P 
4 Series
5 Series  P 
5 Series Gran Turismo
6 Series
7 Series  P 
8 Series
X1
X2
X3
X4
X5  P 
X6
X7
Z4
i3  E 
i8  P 

Clubman
Countryman  P 
Hatch

Chang'an Chery Daimler Dongfeng
Chana/Oushang Chang'an Oushan Ruixing Mercedes-Benz Smart

CS55
CS95

A-Class
B-Class  E 
C-Class  P   F   M 
CLA-Class
CLS-Class  M 
E-Class  P   F   M 
EQC  E 
G-Class
GLA-Class
GLC-Class
GLE-Class  P   M 
GLS-Class
S-Class  P   F   M 
SL-Class
Sprinter
V-Class
X-Class

FAW FCA Ferrari
Alfa Romeo Chrysler Dodge Fiat Jeep Lancia Maserati RAM

Giulia

500X  L 
Ducato  N 

Renegade

Ghibli
Levante
Quattroporte

Ford GAC Geely
Ford Lincoln Geely Jihe Lotus Lynk & Co Polestar Volvo

Edge/Endura
Everest
Explorer  P   F 
Fiesta
Focus
Kuga
Mondeo  F 
Ranger
S-MAX
Tourneo
Tourneo Connect
Tourneo Custom
Transit
Transit Connect
Transit Custom

Borui GE  P   M 
Jia Ji  P 

S60  P 
S80
S90
V40
V60
V70
V90  P 
XC40
XC60
XC70
XC90  P   M 

GM Great Wall
Buick Cadillac Chevrolet GMC Holden Great Wall Haval WEY

Acadia

F7
F7x

Honda Hyundai JAC Jiangling Karma Koenigsegg
Acura Honda Genesis Hyundai Kia

RDX

Accord
Civic[9]
CR-V  F 
HR-V
Insight  F 
Jazz
Passport

i30
i40
Kona
Kona Electric/Kona EV  E 
Nexo  C 
Santa Fe
Tucson  M 

Ceed
Niro  P 
Sorento
Sportage  M 
Stinger
e-Niro/Niro EV  E 

Lifan McLaren Mahindra Mazda Mitsubishi Morgan NIO Nissan
Mahindra SsangYong Infiniti Nissan

Korando
Rexton
Tivoli

3  M 
6
CX-5
CX-8
CX-9
MX-5

ES8  E 

Q30
Q60
QX30

Altima
Leaf  E 
Maxima
Micra
Murano
Pulsar
Qashqai
X-Trail  F 

PROTON PSA Pagani Perodua
Citroën DS Opel/Vauxhall Peugeot

Berlingo
C1
C3  L 
C3 Aircross
C4 Cactus
C4 Picasso/SpaceTourer
C5 Aircross
Grand C4 Picasso/SpaceTourer
Jumpy

3 Crossback
7 Crossback  P 

Astra  N 
Combo
Corsa  L 
Corsavan
Crossland X
Grandland X
Insignia
Mokka  L 
Vivaro

108
208
308
508
3008
5008
Expert
Partner
Rifter
Traveller
e-208  E 

Qoros Renault
Alpine Dacia Lada Renault Renault Samsung

Clio  L 
Espace
Kadjar
Koleos
Mégane
Scénic
Talisman

SAIC Saab Subaru Suzuki
Baojun LDV/Maxus MG Roewe

D90

9-5

Crosstrek  P 

Jimny
Vitara

Tata Toyota
Jaguar Land Rover Tata Lexus Toyota

E-Pace
F-Pace
I-Pace  E 
XE
XF

Land Rover Discovery
Range Rover
Range Rover Evoque  M 
Range Rover Sport  P   F 
Range Rover Velar

CT  F 
ES  F 
GS  F 
LC  F 
LS  F 
RC  F 
RX  F 
UX  F 

C-HR  F 
Camry  F 
Corolla  F 
Hilux
Land Cruiser
Mirai  C 
Prius  P   F 
Prius+  F 
ProAce
RAV4  F 
Supra
Yaris

Volkswagen
Audi Bentley Bugatti Jetta Lamborghini Porsche SEAT/Cupra Škoda Volkswagen

A3  N 
A3 Sportback e-tron  P 
A4  N 
A5  N 
A6  M 
A7  M 
A8  M 
Q2
Q3
Q5
Q7  M 
Q8  M 
S5
S6  M 
S7  M 
SQ5  M 
SQ7  M 
TT
e-tron  E 

Bentayga
Continental

911
Cayenne  P 
Macan
Panamera  P 

Alhambra
Ateca
León  N 
Tarraco

Karoq
Kodiaq
Octavia  N 
Superb

Arteon
Golf  N 
Passat
Phaeton
T-Roc
Tiguan
Touareg
Transporter  M 
e-Golf  E 

ZX Auto/Zhongxing Zenvo Zotye

References[edit]

  1. ^ "Vauxhall Insignia to read speed limit signs". Business Car. 18 June 2008. Retrieved 2 April 2019.
  2. ^ Eichner, M.; Breckon, T. (2008). "Integrated speed limit detection and recognition from real-time video" (PDF). IEEE International Intelligent Vehicles Symposium: 626–631. doi:10.1109/IVS.2008.4621285.
  3. ^ "Assistenzsystem von Opel - Das magische Auge". Retrieved 17 December 2010.
  4. ^ "Phaeton debuts with new design and new technologies". Retrieved 22 April 2010.
  5. ^ "Road Sign Information". Retrieved 19 February 2013.
  6. ^ "Whoever Owns the Maps Owns the Future of Self-Driving Cars".
  7. ^ "Lim K, Hong Y, Choi Y, Byun H (2017) Real-time traffic-sign recognition based on a general-purpose GPU and deep learning. PLoS ONE 12(3): e0173317".
  8. ^ "BMW 1 Series 3-door : Traffic Sign Recognition:". Retrieved 4 October 2012.
  9. ^ "Honda Launch 2014 - Mobileye". Retrieved 18 December 2015.

See also[edit]