Multi-task deep convolutional neural networks for efficient and robust traffic lane detection

摘要

Disclosed herein are devices, systems, and methods for detecting the presence and orientation of traffic lane markings. Deep convolutional neural networks are used with convolutional layers and max-pooling layers to generate fully connected nodes. After the convolutional and max-pooling layers, two sublayers are applied, one to determine presence and one to determine geometry. The presence of a lane marking segment as detected by the first sublayer can serve as a gate for the second sublayer by regulating the credit assignment for training the network. Only when the first sublayer predicts actual presence will the geometric layout of the lane marking segment contribute to the training of the overall network. This achieves advantages with respect to accuracy and efficiency and contributes to efficient robust model selection.