SIGNAL LIGHT STATE RECOGNITION METHOD, DEVICE AND VEHICLE-MOUNTED CONTROL TERMINAL AND MOTOR VEHICLE

WIPO Patent Application WO/2018/201835

A1

Embodiments of the present application provide a signal light state recognition method, device and vehicle-mounted control terminal, and a motor vehicle. The method comprises: acquiring an image to be recognized acquired by a target image acquisition device; and recognizing a traffic signal light image region in the image to be recognized; extracting a convolutional neural network (CNN) feature of the traffic signal light image region; determining, according to the CNN feature, a first traffic signal light state represented by the traffic signal light image region; and determining a traffic signal light state recognition result according to the first traffic signal light state. The embodiments of the present application can improve the accuracy of the traffic signal light state recognition.

WANG JUE (CN)
WANG BIN (CN)
LI YUMING (CN)
XING TENGFEI (CN)
LI CHENGJUN (CN)
SU KUIFENG (CN)
CHEN REN (CN)
XIANG NAN (CN)

PCT/CN2018/081575

November 08, 2018

April 02, 2018

Click for automatic bibliography generation  

TENCENT TECH SHENZHEN CO LTD (CN)

G06K9/00

CN106570494A	2017-04-19
CN106295605A	2017-01-04
CN101275839A	2008-10-01
CN106023605A	2016-10-12
CN103679194A	2014-03-26

V. JOHN ET AL.: "Saliency Map Generation by the Convolutional Neural Network for Real-Time Traffic Light Detection Using Template Matching", IEEE TRANS .COMPUTATIONAL IMAGING, vol. 1, no. 3, 30 September 2015 (2015-09-30), pages 159 - 173, XP011588186

KANGXIN PARTNERS, P.C. (CN)

View/Download PDF      PDF Help

Previous Patent: METHOD FOR REPORTING AND RECEIVING TERMINAL CAPACITY INFORMATION, TERMINAL AND NETWORK SIDE DEVICE

Next Patent: FOLDING CHAIR