ROAD LANE DETECTION USING MACHINE LEARNING
ABSTARCT :
Road lane detection systems play a crucial role in the context of Advanced Driver Assistance Systems (ADASs) and autonomous driving. Such systems can lessen road accidents and increase driving safety by alerting the driver in risky traffic situations. Additionally, the detection of ego lanes with their left and right boundaries along with the recognition of their types is of great importance as they provide contextual information. Lane detection is a challenging problem since road conditions and illumination vary while driving. In this contribution, we investigate the use of a CNN-based regression method for detecting ego lane boundaries. After the lane detection stage, following a projective transformation, the classification stage is performed with a RseNet101 network to verify the detected lanes or a possible road boundary. We applied our framework to real images collected during drives in an urban area with the RoadLAB instrumented vehicle. Our experimental results show that our approach achieved promising results in the detection stage with an accuracy of 94.52% in the lane classification stage.
EXISTING SYSTEM :
? The robustness and accuracy of lane recognition remain to be further improved for the complex road environment, especially the existence of a large number of shadows and illumination changes.
? The existence of disturbance captured in the image will interrupt the accurate detection of the edges, so one can activate filters to get rid of noises.
? If an automobile crosses a lane confinement then vehicles enabled with predicting lane borders system directs the vehicles to prevent collisions and generates an alarming condition.
DISADVANTAGE :
? Deep learning-based methods have been employed to provide reliable solutions to the lane detection problem.The GAN network is employed to address the imbalance problem by synthesizing the anomalous data.
? These traditional approaches suffer from performance issues when they encounter challenging illumination conditions and complex road scenes.
? Lane detection becomes a hot issue in the filed of intelligent transportation, and the correct identification of lane is the basis of the lane departure warning systems and some other driver driving assistant systems.
PROPOSED SYSTEM :
• In order to improve accuracy and robustness of the lane detection in complex conditions, such as the shadows and illumination changing, a novel detection algorithm was proposed based on machine learning.
• A novel lane detection algorithm based on machine learning is proposed in this paper to solve the hard detection in complex conditions.
• A lane detection algorithm is proposed based on machine learning. Haar-like feature extraction and boosting are combined to design a classifier.
ADVANTAGE :
? This is advantageous as isolated bright objects like street lights and taillights of cars would influence the global threshold, the adaptive method would not be easily altered.
? Moreover, performance of the driver can also be monitored, Road Transportation Offices can use the setup to check and report the negligence of drivers and lack of attention on the roads.
? Efficiency per minute of the system can be measured to check the accuracy of the system. Moreover, neighbouring vehicles and the lightning from their headlights appeared to have very less to no changes on the average efficiency estimation.
|