Abstract: A first image of a scene captured by a first camera is received. The first image is resized to have an instantaneous field of view (IFoV) corresponding to the IFoV of a second image of the scene captured by a second camera. A distortion-corrected resized first image is constructed. A resampled distortion-corrected, resized first image is constructed to provide a resampled, distortion-corrected, resized first image, thereby registering first image to the second image.

Abstract: A method to enhance image quality is disclosed. The method may include obtaining an infrared image from a vehicle infrared camera. The method may further include multiplying the infrared image with a fade mask, and generating a masked infrared image based on the multiplication. The method may additionally include obtaining a colored image from a vehicle colored camera. Responsive to obtaining the colored image, the method may include combining the masked infrared image with the colored image, and outputting a combined image based on the combination.

Abstract: A first image of a scene captured by a first camera is received. The first image is resized to have an instantaneous field of view (IFoV) corresponding to the IFoV of a second image of the scene captured by a second camera. A distortion-corrected resized first image is constructed. A resampled distortion-corrected, resized first image is constructed to provide a resampled, distortion-corrected, resized first image, thereby registering first image to the second image.

Abstract: A first calibration image of a calibration target is received and resized to provide a resized first calibration image. Pixel coordinates of the resized first calibration image are mapped to pixel coordinates of the first calibration image to provide a resizing map. The resized first calibration image is distortion-corrected to provide a distortion-corrected resized first calibration image. Pixel coordinates of the distortion-corrected resized first calibration image are mapped to pixel coordinates of the resized first calibration image to provide a distortion correction map. The distortion-corrected resized first calibration image is resampled to provide a resampled, distortion-corrected, resized calibration image. Pixel coordinates of the resampled, distortion-corrected, resized calibration image are mapped to pixel coordinates of the distortion-corrected, resized calibration image to provide a resampling map.

Abstract: A method to enhance image quality is disclosed. The method may include obtaining an infrared image from a vehicle infrared camera. The method may further include multiplying the infrared image with a fade mask, and generating a masked infrared image based on the multiplication. The method may additionally include obtaining a colored image from a vehicle colored camera. Responsive to obtaining the colored image, the method may include combining the masked infrared image with the colored image, and outputting a combined image based on the combination.

Abstract: A plurality of thermal images forward of a vehicle are collected. Thermal data in the plurality of thermal images is normalized based on an ambient air temperature to generate a plurality of normalized thermal images. The plurality of normalized thermal images are input to a machine learning program trained to output an identification of an object based on the ambient air temperature and a risk of collision between the vehicle and the object. A vehicle component is actuated based on the identification of the object and the risk of collision with the object.

Abstract: A system for mitigating glare from at least one light source while driving a vehicle. The system includes determining an occurrence of a glare condition based on, at least in part, a visible light video stream generated by a visible light sensor. Upon determining the occurrence of the glare condition, indicia are presented at the vehicle display to assist in navigation of the vehicle.

Abstract: A vehicle characterizes a sunload on the vehicle using an imaging system including at least one camera capturing image data (e.g., without using an ambient light sensor). The image data includes at least a portion of a passenger cabin. A region of interest (ROI) overlay receives the image data and extracts selected image data according to predetermined scene elements of the vehicle environment. An occupant overlay is configured to detect a vehicle occupant represented in the selected image data and configured to generate truncated image data by subtracting image data corresponding to the vehicle occupant from the selected image data. An ambient light model uses environmental parameters including a sun position to estimate an expected sunload range. A mapper generates a sunload map comprising respective sunload values for a plurality of locations on the vehicle according to the truncated image data and the expected sunload range.

Abstract: First objects are detected in an infrared image from an infrared camera and second objects are detected in a color image from a color camera. The first objects are compared with the second objects to determine pairs of matching first objects and second objects. For each matching pair, a respective region of an output image is colorized by setting colors of pixels in the region based on colors of the pixels of the second object in the matching pair. The pixels in the region have locations corresponding to the locations of the pixels in the first object of the matching pair. When the colorizing is complete, pixels not in the colorized regions have intensities of the infrared image. The output image is a version of the infrared image with a region colorized according to the color image.

Abstract: A vehicle characterizes a sunload on the vehicle using an imaging system including at least one camera capturing image data (e.g., without using an ambient light sensor). The image data includes at least a portion of a passenger cabin. A region of interest (ROI) overlay receives the image data and extracts selected image data according to predetermined scene elements of the vehicle environment. An occupant overlay is configured to detect a vehicle occupant represented in the selected image data and configured to generate truncated image data by subtracting image data corresponding to the vehicle occupant from the selected image data. An ambient light model uses environmental parameters including a sun position to estimate an expected sunload range. A mapper generates a sunload map comprising respective sunload values for a plurality of locations on the vehicle according to the truncated image data and the expected sunload range.

Abstract: A plurality of thermal images forward of a vehicle are collected. Thermal data in the plurality of thermal images is normalized based on an ambient air temperature to generate a plurality of normalized thermal images. The plurality of normalized thermal images are input to a machine learning program trained to output an identification of an object based on the ambient air temperature and a risk of collision between the vehicle and the object. A vehicle component is actuated based on the identification of the object and the risk of collision with the object.

Abstract: Advanced automotive active-safety systems, in general, and autonomous vehicles, in particular, rely heavily on visual data to classify and localize objects, most notably pedestrians and other nearby cars, to assist the corresponding vehicles maneuver safely in their environment. However, the performance of object detection methods is anticipated to degrade under challenging rainy conditions. Nevertheless, and despite major advancements in the development of deraining approaches, the impact of rain on object detection has largely been understudied, especially in the context of autonomous systems. This disclosure analyzes this problem space and presents an improved system for detecting objects under rainy conditions.

Abstract: Real-time wind data for a location is determined based on a detected movement of an object relative to a vehicle. The real-time wind data includes a wind speed and a wind direction. Upon receiving stored wind data for the location from a remote computer, a crosswind risk is determined based on the real-time wind data and the stored wind data. A vehicle component is actuated to compensate for the crosswind risk.

Abstract: Real-time wind data for a location is determined based on a detected movement of an object relative to a vehicle. The real-time wind data includes a wind speed and a wind direction. Upon receiving stored wind data for the location from a remote computer, a crosswind risk is determined based on the real-time wind data and the stored wind data. A vehicle component is actuated to compensate for the crosswind risk.

Abstract: Advanced automotive active-safety systems, in general, and autonomous vehicles, in particular, rely heavily on visual data to classify and localize objects, most notably pedestrians and other nearby cars, to assist the corresponding vehicles maneuver safely in their environment. However, the performance of object detection methods is anticipated to degrade under challenging rainy conditions. Nevertheless, and despite major advancements in the development of deraining approaches, the impact of rain on object detection has largely been understudied, especially in the context of autonomous systems. This disclosure analyzes this problem space and presents an improved system for detecting objects under rainy conditions.

Abstract: Methods and apparatus are disclosed for concealed fiducial markers for vehicle camera calibration. An example vehicle includes a frame, at least one panel coupled to the frame, and fiducial markers arranged in a predefined grid. The fiducial markers are configured to be detectable by a camera and concealed from observation by the human eye. The predefined grid of the fiducial markers is arranged to facilitate calibration of the thermal camera.

Abstract: Exemplary embodiments described in this disclosure are generally directed to systems and methods for providing cautionary driving notifications to a driver of an automobile. The cautionary driving notifications may be generated and stored by the driver himself/herself after driving along a travel route a few times or by a different driver who has driven along the travel route a few times. The notifications, which may be provided in various ways such as by audible warnings or beeps, warn the driver of a driving hazard or a driving limitation that is coming up as the automobile is subsequently driven along the travel route. Some examples of a driving hazard can include a traffic accident or a bad road condition. Some examples of a driving limitation can include a speed limit due to a blind curve in the road or in a school zone during certain times of the day.

Abstract: Methods and apparatus are disclosed to facilitate environmental visibility determination. An example vehicle comprises a sensor and a processor and memory. The sensor is to generate road image information. The processor and memory are in communication with the sensor and are configured to: detect vanishing points of lane markings in the road image information, convert an average pixel row value of the vanishing points to a distance value, and if the distance value is below a threshold, stop execution of at least one road condition monitoring feature.

Abstract: Method and apparatus are disclosed for vehicle security monitoring in a key-off state. An example vehicle includes low-power sensors and high-power sensors for security monitoring, a communication module, and a controller. The controller is to, when in a key-off state, determine a first score based on the low-power sensors. The controller also is to, responsive the first score exceeding a first threshold, activate the high-power sensors and determine a second score based on the high-power sensors. The controller also is to, responsive the second score exceeding a second threshold, send an alert via the communication module.

Abstract: Methods and apparatus are disclosed to facilitate environmental visibility determination. An example vehicle comprises a sensor and a processor and memory. The sensor is to generate road image information. The processor and memory are in communication with the sensor and are configured to: detect vanishing points of lane markings in the road image information, convert an average pixel row value of the vanishing points to a distance value, and if the distance value is below a threshold, stop execution of at least one road condition monitoring feature.