Abstract: The disclosure extends to methods, systems, and apparatuses for automated fixation generation and more particularly relates to generation of synthetic saliency maps. A method for generating saliency information includes receiving a first image and an indication of one or more sub-regions within the first image corresponding to one or more objects of interest. The method includes generating and storing a label image by creating an intermediate image having one or more random points. The random points have a first color in regions corresponding to the sub-regions and a remainder of the intermediate image having a second color. Generating and storing the label image further includes applying a Gaussian blur to the intermediate image.

Abstract: Disclosures herein teach applying a set of sections spanning a down-sampled version of an image of a road-scene to a low-fidelity classifier to determine a set of candidate sections for depicting one or more objects in a set of classes. The set of candidate sections of the down-sampled version may be mapped to a set of potential sectors in a high-fidelity version of the image. A high-fidelity classifier may be used to vet the set of potential sectors, determining the presence of one or more objects from the set of classes. The low-fidelity classifier may include a first Convolution Neural Network (CNN) trained on a first training set of down-sampled versions of cropped images of objects in the set of classes. Similarly, the high-fidelity classifier may include a second CNN trained on a second training set of high-fidelity versions of cropped images of objects in the set of classes.

Abstract: Disclosures herein teach applying a set of sections spanning a down-sampled version of an image of a road-scene to a low-fidelity classifier to determine a set of candidate sections for depicting one or more objects in a set of classes. The set of candidate sections of the down-sampled version may be mapped to a set of potential sectors in a high-fidelity version of the image. A high-fidelity classifier may be used to vet the set of potential sectors, determining the presence of one or more objects from the set of classes. The low-fidelity classifier may include a first Convolution Neural Network (CNN) trained on a first training set of down-sampled versions of cropped images of objects in the set of classes. Similarly, the high-fidelity classifier may include a second CNN trained on a second training set of high-fidelity versions of cropped images of objects in the set of classes.

Abstract: Disclosures herein teach applying a set of sections spanning a down-sampled version of an image of a road-scene to a low-fidelity classifier to determine a set of candidate sections for depicting one or more objects in a set of classes. The set of candidate sections of the down-sampled version may be mapped to a set of potential sectors in a high-fidelity version of the image. A high-fidelity classifier may be used to vet the set of potential sectors, determining the presence of one or more objects from the set of classes. The low-fidelity classifier may include a first Convolution Neural Network (CNN) trained on a first training set of down-sampled versions of cropped images of objects in the set of classes. Similarly, the high-fidelity classifier may include a second CNN trained on a second training set of high-fidelity versions of cropped images of objects in the set of classes.

Abstract: Disclosures herein teach applying a set of sections spanning a down-sampled version of an image of a road-scene to a low-fidelity classifier to determine a set of candidate sections for depicting one or more objects in a set of classes. The set of candidate sections of the down-sampled version may be mapped to a set of potential sectors in a high-fidelity version of the image. A high-fidelity classifier may be used to vet the set of potential sectors, determining the presence of one or more objects from the set of classes. The low-fidelity classifier may include a first Convolution Neural Network (CNN) trained on a first training set of down-sampled versions of cropped images of objects in the set of classes. Similarly, the high-fidelity classifier may include a second CNN trained on a second training set of high-fidelity versions of cropped images of objects in the set of classes.

Abstract: The disclosure extends to methods, systems, and apparatuses for automated fixation generation and more particularly relates to generation of synthetic saliency maps. A method for generating saliency information includes receiving a first image and an indication of one or more sub-regions within the first image corresponding to one or more objects of interest. The method includes generating and storing a label image by creating an intermediate image having one or more random points. The random points have a first color in regions corresponding to the sub-regions and a remainder of the intermediate image having a second color. Generating and storing the label image further includes applying a Gaussian blur to the intermediate image.

Abstract: The disclosure extends to methods, systems, and apparatuses for automated fixation generation and more particularly relates to generation of synthetic saliency maps. A method for generating saliency information includes receiving a first image and an indication of one or more sub-regions within the first image corresponding to one or more objects of interest. The method includes generating and storing a label image by creating an intermediate image having one or more random points. The random points have a first color in regions corresponding to the sub-regions and a remainder of the intermediate image having a second color. Generating and storing the label image further includes applying a Gaussian blur to the intermediate image.

Abstract: Example systems and methods for detecting an animal proximate a vehicle are described. In one implementation, a wearable device carried by an animal is activated when the wearable device is within a predetermined distance of a vehicle. The vehicle receives a signal from the wearable device and determines an approximate distance between the wearable device and the vehicle. An alert is generated to warn a driver that an animal is near the vehicle. The alert has an intensity level that corresponds to the approximate distance between the wearable device and the vehicle.

Abstract: The disclosure extends to methods, systems, and apparatuses for automated fixation generation and more particularly relates to generation of synthetic saliency maps. A method for generating saliency information includes receiving a first image and an indication of one or more sub-regions within the first image corresponding to one or more objects of interest. The method includes generating and storing a label image by creating an intermediate image having one or more random points. The random points have a first color in regions corresponding to the sub-regions and a remainder of the intermediate image having a second color. Generating and storing the label image further includes applying a Gaussian blur to the intermediate image.

Abstract: The disclosure extends to methods, systems, and apparatuses for automated fixation generation and more particularly relates to generation of synthetic saliency maps. A method for generating saliency information includes receiving a first image and an indication of one or more sub-regions within the first image corresponding to one or more objects of interest. The method includes generating and storing a label image by creating an intermediate image having one or more random points. The random points have a first color in regions corresponding to the sub-regions and a remainder of the intermediate image having a second color. Generating and storing the label image further includes applying a Gaussian blur to the intermediate image.

Abstract: Disclosures herein teach applying a set of sections spanning a down-sampled version of an image of a road-scene to a low-fidelity classifier to determine a set of candidate sections for depicting one or more objects in a set of classes. The set of candidate sections of the down-sampled version may be mapped to a set of potential sectors in a high-fidelity version of the image. A high-fidelity classifier may be used to vet the set of potential sectors, determining the presence of one or more objects from the set of classes. The low-fidelity classifier may include a first Convolution Neural Network (CNN) trained on a first training set of down-sampled versions of cropped images of objects in the set of classes. Similarly, the high-fidelity classifier may include a second CNN trained on a second training set of high-fidelity versions of cropped images of objects in the set of classes.

Abstract: Example systems and methods for communicating animal proximity to a vehicle are described. In one implementation, a device implanted in an animal is activated when the device is within a predetermined distance of a vehicle. The vehicle receives a signal from the device and determines an approximate distance between the device and the vehicle. A symbol is flashed to a driver of the vehicle at a frequency that corresponds to the approximate distance between the device and the vehicle.

Abstract: Disclosures herein teach applying a set of sections spanning a down-sampled version of an image of a road-scene to a low-fidelity classifier to determine a set of candidate sections for depicting one or more objects in a set of classes. The set of candidate sections of the down-sampled version may be mapped to a set of potential sectors in a high-fidelity version of the image. A high-fidelity classifier may be used to vet the set of potential sectors, determining the presence of one or more objects from the set of classes. The low-fidelity classifier may include a first Convolution Neural Network (CNN) trained on a first training set of down-sampled versions of cropped images of objects in the set of classes. Similarly, the high-fidelity classifier may include a second CNN trained on a second training set of high-fidelity versions of cropped images of objects in the set of classes.

Abstract: Example systems and methods for communicating animal proximity to a vehicle are described. In one implementation, a device implanted in an animal is activated when the device is within a predetermined distance of a vehicle. The vehicle receives a signal from the device and determines an approximate distance between the device and the vehicle. A symbol is flashed to a driver of the vehicle at a frequency that corresponds to the approximate distance between the device and the vehicle.

Abstract: Example systems and methods for detecting an animal proximate a vehicle are described. In one implementation, a wearable device carried by an animal is activated when the wearable device is within a predetermined distance of a vehicle. The vehicle receives a signal from the wearable device and determines an approximate distance between the wearable device and the vehicle. An alert is generated to warn a driver that an animal is near the vehicle. The alert has an intensity level that corresponds to the approximate distance between the wearable device and the vehicle.

Abstract: A controller for an autonomous vehicle receives audio signals from one or more microphones and identifies sounds. The controller further identifies an estimated location of the sound origin and the type of sound, i.e. whether the sound is a vehicle and/or the type of vehicle. The controller analyzes map data and attempts to identify a landmark within a tolerance from the estimated location. If a landmark is found corresponding to the estimated location and type of the sound origin, then the certainty is increased that the source of the sound is at that location and is that type of sound source. Collision avoidance is then performed with respect to the location of the sound origin and its type with the certainty as augmented using the map data. Collision avoidance may include automatically actuating brake, steering, and accelerator actuators in order to avoid the location of the sound origin.

Abstract: A controller for an autonomous vehicle receives audio signals from one or more microphones and identifies sounds. The controller further identifies an estimated location of the sound origin and the type of sound, i.e. whether the sound is a vehicle and/or the type of vehicle. The controller analyzes map data and attempts to identify a landmark within a tolerance from the estimated location. If a landmark is found corresponding to the estimated location and type of the sound origin, then the certainty is increased that the source of the sound is at that location and is that type of sound source. Collision avoidance is then performed with respect to the location of the sound origin and its type with the certainty as augmented using the map data. Collision avoidance may include automatically actuating brake, steering, and accelerator actuators in order to avoid the location of the sound origin.

Abstract: A controller for an autonomous vehicle receives an image stream from one or more imaging devices. The controller identifies vehicle images in the image stream. Vehicle images are compared to the color, shape, badging, markings, license plate, and driver of the autonomous vehicle. If the vehicle image is determined to match the autonomous vehicle, then the vehicle image is ignored as a potential obstacle. The location of a reflective surface that generated the vehicle image may be determined and added to a set of potential obstacles. The color and shape of a vehicle in a vehicle image may be evaluated first. Only if the color and shape in the vehicle image match the autonomous vehicle are other factors such as badging, markings, license plate, and driver considered. Vehicle images not matching the autonomous vehicle are included in a set of potential obstacles.

Abstract: Disclosures herein teach applying a set of sections spanning a down-sampled version of an image of a road-scene to a low-fidelity classifier to determine a set of candidate sections for depicting one or more objects in a set of classes. The set of candidate sections of the down-sampled version may be mapped to a set of potential sectors in a high-fidelity version of the image. A high-fidelity classifier may be used to vet the set of potential sectors, determining the presence of one or more objects from the set of classes. The low-fidelity classifier may include a first Convolution Neural Network (CNN) trained on a first training set of down-sampled versions of cropped images of objects in the set of classes. Similarly, the high-fidelity classifier may include a second CNN trained on a second training set of high-fidelity versions of cropped images of objects in the set of classes.

Abstract: The disclosure extends to methods, systems, and apparatuses for automated fixation generation and more particularly relates to generation of synthetic saliency maps. A method for generating saliency information includes receiving a first image and an indication of one or more sub-regions within the first image corresponding to one or more objects of interest. The method includes generating and storing a label image by creating an intermediate image having one or more random points. The random points have a first color in regions corresponding to the sub-regions and a remainder of the intermediate image having a second color. Generating and storing the label image further includes applying a Gaussian blur to the intermediate image.