Vehicle lane recognition apparatus

A vehicle lane recognition apparatus to be applied to a vehicle, the vehicle lane recognition apparatus comprising:

• an image capturer configured to capture an image of an external traveling environment;
• a disturbance determiner configured to:
• compare a traveling environment image depicting the traveling environment and a comparative image depicting a traveling environment equivalent to the traveling environment in the traveling environment image;
• and
• determine that a disturbance factor that impairs visibility is shown in the traveling environment image when a brightness average in the traveling environment image is lower than a brightness average in the comparative image and a difference between the brightness average in the traveling environment image and the brightness average in the comparative image is equal to or larger than a threshold;
• and
• a lane estimator configured to estimate a lane based on the traveling environment image by using an estimation model constructed by machine learning,
• wherein the lane estimator is configured to:
• generate a current feature map by performing a convolutional process for the traveling environment image;
• cause a memory to store, in time sequence, feature maps generated by the convolutional process for traveling environment images captured at individual set timings, each of the feature maps being stored together with a result of the determination by the disturbance determiner for a corresponding one of the traveling environment images;
• extract one or more feature maps from the memory;
• when the current feature map is based on the traveling environment image determined to show the disturbance factor, replace the current feature map with a feature map generated from a traveling environment image captured one frame or several frames earlier than the traveling environment image determined to show the disturbance factor;
• when an extracted feature map among the one or more feature maps extracted from the memory is based on a traveling environment image determined to show the disturbance factor, replace the extracted feature map with another feature map generated from another traveling environment image captured one frame or several frames earlier or later than the traveling environment image determined to show the disturbance factor;
• and
• estimate the lane by using the current feature map and the one or more feature maps obtained after performing any replacement of the current feature map and any replacement of the extracted feature map.