Abstract: Provided is a technique for determining a context of an image and an object depicted by the image based on the context. A trained context classification model may determine a context of an image, and a trained object recognition model may determine an object depicted by the image based on the image and the context. Provided is also a technique for determining an object depicted within an image based on an input location of an input detected by a display screen. An object depicted within an image may be detected based on a distance in feature space between an image feature vector of an image and a feature vector of the object, and a distance in pixel-space between an input location of an input and location of the object within the image.

Abstract: A system for providing media content to an occupant of a vehicle may include a user interface configured to provide the media content to the occupant and a controller coupled to the user interface and to a database configured to store media content. The controller may be configured to receive vehicle navigation data, select a subset of media content from the media content stored in the database based on the vehicle navigation data, and provide the subset of media content through the user interface.

Abstract: A system for providing media content to an occupant of a vehicle may include a user interface configured to provide the media content to the occupant and a controller coupled to the user interface and to a database configured to store media content. The controller may be configured to receive vehicle navigation data, select a subset of media content from the media content stored in the database based on the vehicle navigation data, and provide the subset of media content through the user interface.

Abstract: Provided is a process that includes: determining that a training set lacks an image of an object with a given pose, context, or camera; composing, based on the determination, a video capture task; obtaining a candidate video; selecting a subset of frames of the candidate video as representative; determining that a given frame among the subset depicts the object from the given pose, context, or camera; and augmenting the training set with the given frame.

Abstract: Provided is a technique for determining a context of an image and an object depicted by the image based on the context. A trained context classification model may determine a context of an image, and a trained object recognition model may determine an object depicted by the image based on the image and the context. Provided is also a technique for determining an object depicted within an image based on an input location of an input detected by a display screen. An object depicted within an image may be detected based on a distance in feature space between an image feature vector of an image and a feature vector of the object, and a distance in pixel-space between an input location of an input and location of the object within the image.

Abstract: Provided is a technique for determining a context of an image and an object depicted by the image based on the context. A trained context classification model may determine a context of an image, and a trained object recognition model may determine an object depicted by the image based on the image and the context. Provided is also a technique for determining an object depicted within an image based on an input location of an input detected by a display screen. An object depicted within an image may be detected based on a distance in feature space between an image feature vector of an image and a feature vector of the object, and a distance in pixel-space between an input location of an input and location of the object within the image.

Abstract: Provided is a process that includes: determining that a training set lacks an image of an object with a given pose, context, or camera; composing, based on the determination, a video capture task; obtaining a candidate video; selecting a subset of frames of the candidate video as representative; determining that a given frame among the subset depicts the object from the given pose, context, or camera; and augmenting the training set with the given frame.

Abstract: Provided is a technique for determining a context of an image and an object depicted by the image based on the context. A trained context classification model may determine a context of an image, and a trained object recognition model may determine an object depicted by the image based on the image and the context. Provided is also a technique for determining an object depicted within an image based on an input location of an input detected by a display screen. An object depicted within an image may be detected based on a distance in feature space between an image feature vector of an image and a feature vector of the object, and a distance in pixel-space between an input location of an input and location of the object within the image.

Abstract: Provided is a process that includes training a computer-vision object recognition model with a training data set including images depicting objects, each image being labeled with an object identifier of the corresponding object; obtaining a new image; determining a similarity between the new image and an image from the training data set with the trained computer-vision object recognition model; and causing the object identifier of the object to be stored in association with the new image, visual features extracted from the new image, or both.

Abstract: Methods, systems, and apparatuses for adaptive download of map information are presented which include obtaining a route from a start location to a destination location for a vehicle, acquiring projected environmental information associated with a first portion in the route the vehicle is expected to traverse, acquiring projected network availability information associated with a second portion in the route the vehicle is expected to traverse; and determining whether to download map information associated with the first portion of the route based on (1) the projected environmental information and (2) the projected network availability information.

Abstract: Certain embodiments may include methods and systems for receiving first audio data from a plurality of microphones disposed in a cabin of a vehicle, calculating phase differences between the first audio data received from different ones of the plurality of microphones, determining a location of a source of the first audio data based on the calculated phase differences, isolating second audio data received from the plurality of microphones, taking into account the determined location of the source, and controlling a function of the vehicle based on the isolated second audio data. Some embodiments can further include detecting voice data in the second audio data based on audio characteristics of the second audio data, and determining a voice command in the voice data, where the controlling the function of the vehicle is based on the voice command in the voice data in the second audio data.

Abstract: A system for providing media content to an occupant of a vehicle may include a user interface configured to provide the media content to the occupant and a controller coupled to the user interface and to a database configured to store media content. The controller may be configured to receive vehicle navigation data, select a subset of media content from the media content stored in the database based on the vehicle navigation data, and provide the subset of media content through the user interface.

Abstract: In some embodiments, a method for determining a vehicle malfunction includes receiving audio data from at least one microphone disposed on a vehicle, inputting the audio data into an analysis module having a trained model, and obtaining, from the analysis module, a hypothesized vehicular malfunction condition based on the audio data. The audio data may corresponding to sounds generated by the vehicle, and the trained model may associate various audio data and corresponding vehicular malfunction conditions. The method can further include inputting sensor data into the analysis module having the trained model, the sensor data from at least one sensor disposed on the vehicle. The trained model can further associates various sensor data, along with the various audio sounds, and the corresponding vehicular malfunction conditions, and the hypothesized vehicular malfunction condition obtained from the analysis module can be based on the audio data and the sensor data.

Abstract: Systems and methods are described for distributing multi-processor workload based on sensor data. A method for managing processing workload within a vehicle includes receiving at least one measurement corresponding to a first processor of a plurality of processors installed in the vehicle; determining that the at least one measurement has satisfied a threshold; identifying a second processor of the plurality of processors installed in the vehicle, based on a type of the second processor or a measurement of an environment associated with the second processor; and distributing workload from the first processor to the second processor.

Abstract: Systems and methods for automatic adaptive headlight control in a vehicle are disclosed. The systems and methods can detect one or more conditions, such as presence of a nearby object and/or poor visibility. The headlight can account for the one or more conditions by dynamically and automatically adjusting the total intensity of light output from the headlight, creating one or more different patterns of intensity of light, emitting different colors of light, or a combination thereof. In some examples, the headlight can include a plurality of independently controlled light emitters or a liquid crystal element. In some examples, one or more currents and/or duty cycle values can be adjusted. In some examples, the headlight can be divided into a plurality of sections, such that each section can emit different wavelengths (e.g., colors) of light.

Abstract: Methods, systems, and apparatuses for adaptive download of map information are presented which include obtaining a route from a start location to a destination location for a vehicle, acquiring projected environmental information associated with a first portion in the route the vehicle is expected to traverse, acquiring projected network availability information associated with a second portion in the route the vehicle is expected to traverse; and determining whether to download map information associated with the first portion of the route based on (1) the projected environmental information and (2) the projected network availability information.

Abstract: Certain embodiments may include methods and systems for receiving first audio data from a plurality of microphones disposed in a cabin of a vehicle, calculating phase differences between the first audio data received from different ones of the plurality of microphones, determining a location of a source of the first audio data based on the calculated phase differences, isolating second audio data received from the plurality of microphones, taking into account the determined location of the source, and controlling a function of the vehicle based on the isolated second audio data. Some embodiments can further include detecting voice data in the second audio data based on audio characteristics of the second audio data, and determining a voice command in the voice data, where the controlling the function of the vehicle is based on the voice command in the voice data in the second audio data.

Abstract: A method and system configures operating parameters associated with an operation of a connected accessory or second device in order to mitigate harmonic interference within an operating frequency band of a wireless communication device (WCD). In response to a connection between the WCD and the second device via a physical communications interface, Accessory Authentication and Configuration (AAC) logic of the WCD receives device identifying information about the second device. The AAC logic determines candidate values for each operating parameter, based on the device identifying information. The AAC logic dynamically selects a particular candidate value for each operating parameter, based on a current operating frequency band of the WCD, and an expected level of harmonic interference.

Abstract: A method and system configures operating parameters associated with an operation of a connected accessory or second device in order to mitigate harmonic interference within an operating frequency band of a wireless communication device (WCD). In response to a connection between the WCD and the second device via a physical communications interface, Accessory Authentication and Configuration (AAC) logic of the WCD receives device identifying information about the second device. The AAC logic determines candidate values for each operating parameter, based on the device identifying information. The AAC logic dynamically selects a particular candidate value for each operating parameter, based on a current operating frequency band of the WCD, and an expected level of harmonic interference.