Brake light detection
AssigneeFord Global Technologies, LLC
InventorsMaryam Moosaei, Guy Hotson, Parsa Mahmoudieh, Vidya Nariyambut Murali
Life of this patent
Estimating the term…
Abstract
Systems, methods, and devices for detecting brake lights are disclosed herein. A system includes a mode component, a vehicle region component, and a classification component. The mode component is configured to select a night mode or day mode based on a pixel brightness in an image frame. The vehicle region component is configured to detect a region corresponding to a vehicle based on data from a range sensor when in a night mode or based on camera image data when in the day mode. The classification component is configured to classify a brake light of the vehicle as on or off based on image data in the region corresponding to the vehicle.
Claims20
A method comprising:
- selecting a night mode or a day mode based on a pixel brightness in an image frame;
- classifying an image region of the image frame as comprising a vehicle by:
- calculating density-based clustering on range sensor data when the night mode is selected;
- or
- extracting feature maps from camera image data when the day mode is selected;
- and
- providing a portion of the image region corresponding to a brake light of the vehicle to a deep neural network trained on a dataset of brake lights to classify the brake light of the vehicle as on or off based on the portion of the image region.
A system comprising:
- a range sensor;
- a camera;
- and
- one or more processors programmable to execute instructions stored in non-transitory computer readable storage media, the instructions comprising:
- receiving an image frame from the camera;
- selecting a night mode or a day mode based on a pixel brightness in the image frame;
- classifying an image region of the image frame as comprising a vehicle by calculating density-based clustering on range sensor data from the range sensor when the night mode is selected or extracting feature maps from camera image data received from the camera when the day mode is selected;
- and
- providing a portion of the image region corresponding to a brake light of the vehicle to a deep neural network trained on a dataset of brake lights to classify the brake light of the vehicle as on or off based on the portion of the image region.
The system of 9, wherein the instructions further comprise identifying the portion of the image region corresponding to the brake light of the vehicle based on the LAB color space converted camera image data when the night mode is selected or the HSV color space converted camera image data when the day mode is selected.
Non-transitory computer readable storage medium storing instructions for execution by one or more processors, the instructions comprising:
- selecting a night mode or a day mode based on a pixel brightness in an image frame;
- classifying an image region of the image frame as comprising a vehicle by calculating density-based clustering on range sensor data when the night mode is selected or extracting a feature map from camera image data when the day mode is selected;
- and
- providing a portion of the image region corresponding to a brake light of the vehicle to a deep neural network trained on a dataset of brake lights to classify the brake light of the vehicle as on or off based on the portion of the image region.
Dependencies are inferred from the claim text.