Deviated state detection method in driving around curves based on naturalistic driving behavior database for driver assistance systems

2014 ◽  
Vol 15 (5) ◽  
pp. 749-755 ◽  
Author(s):  
M. Shino ◽  
H. Yoshitake ◽  
M. Hiramatsu ◽  
T. Sunda ◽  
M. Kamata
Keyword(s):  
Detection Method ◽  
Driving Behavior ◽  
Driver Assistance ◽  
Driver Assistance Systems ◽  
State Detection ◽  
Assistance Systems ◽  
Naturalistic Driving

Eye state detection for use in advanced driver assistance systems

2018 ◽  
Author(s):  
Shubham Sharma ◽  
Anuja Negi ◽  
Shantanu Singh ◽  
Dinesh Samuel Sathia Raj ◽  
Jasmine S. Graceline ◽  
...  
Keyword(s):  
Driver Assistance ◽  
Driver Assistance Systems ◽  
Advanced Driver Assistance Systems ◽  
State Detection ◽  
Assistance Systems

scholarly journals Effects of the driving context on the usage of Automated Driver Assistance Systems (ADAS) -Naturalistic Driving Study for ADAS evaluation

2020 ◽  
Vol 4 ◽  
pp. 100093 ◽  
Author(s):  
Julia Orlovska ◽  
Fjollë Novakazi ◽  
Bligård Lars-Ola ◽  
MariAnne Karlsson ◽  
Casper Wickman ◽  
...  
Keyword(s):  
Driver Assistance ◽  
Driver Assistance Systems ◽  
Naturalistic Driving Study ◽  
Assistance Systems ◽  
Naturalistic Driving

scholarly journals RS-Lane: A Robust Lane Detection Method Based on ResNeSt and Self-Attention Distillation for Challenging Traffic Situations

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Ronghui Zhang ◽  
Yueying Wu ◽  
Wanting Gou ◽  
Junzhou Chen
Keyword(s):  
Detection Method ◽  
Autonomous Driving ◽  
Lane Detection ◽  
Feature Representation ◽  
Driver Assistance ◽  
Driver Assistance Systems ◽  
Advanced Driver Assistance Systems ◽  
Assistance Systems ◽  
Light And Shadow ◽  
Instance Segmentation

Lane detection plays an essential part in advanced driver-assistance systems and autonomous driving systems. However, lane detection is affected by many factors such as some challenging traffic situations. Multilane detection is also very important. To solve these problems, we proposed a lane detection method based on instance segmentation, named RS-Lane. This method is based on LaneNet and uses Split Attention proposed by ResNeSt to improve the feature representation on slender and sparse annotations like lane markings. We also use Self-Attention Distillation to enhance the feature representation capabilities of the network without adding inference time. RS-Lane can detect lanes without number limits. The tests on TuSimple and CULane datasets show that RS-Lane has achieved comparable results with SOTA and has improved in challenging traffic situations such as no line, dazzle light, and shadow. This research provides a reference for the application of lane detection in autonomous driving and advanced driver-assistance systems.

Sign in / Sign up

Export Citation Format

Share Document