Abstract: A system for detecting and mitigating an unsafe condition in a vehicle includes an image sensor configured to generate and output image data of one or more seats in a cabin of the vehicle and a processing system operably connected to the image sensor and including at least one processor. The processing system is configured to receive the image data from the image sensor, process the image data to determine a location of at least one passenger in the cabin, detect that the at least one passenger is located outside of the one or more seats based on the determined location of the at least one passenger in the cabin, and operate at least one component of the vehicle in a predefined manner in response to detecting that the at least one passenger is located outside of the one or more seats.

Abstract: A system for detecting and resolving an abnormal settling event in a vehicle includes an image sensor and a processing system. The processing system is configured to, upon commencement of a passenger entry into the vehicle, receive image data from the image sensor, process the image data to determine a location of at least one passenger in the cabin, detect that the at least one passenger is located outside of the one or more seats of the vehicle, after a first predetermined time period has elapsed from the commencement of the passenger entry into the vehicle, based on the determined location of the at least one passenger in the cabin, and operate at least one component of the vehicle in a predefined manner in response to detecting that the at least one passenger is located outside of the one or more seats after the first predetermined time period has elapsed.

Abstract: Low energy deep-learning networks for generating auditory features such as mel frequency cepstral coefficients in audio processing pipelines are provided. In various embodiments, a first neural network is trained to output auditory features such as mel-frequency cepstral coefficients, linear predictive coding coefficients, perceptual linear predictive coefficients, spectral coefficients, filter bank coefficients, and/or spectro-temporal receptive fields based on input audio samples. A second neural network is trained to output a classification based on input auditory features such as mel-frequency cepstral coefficients. An input audio sample is provided to the first neural network. Auditory features such as mel-frequency cepstral coefficients are received from the first neural network. The auditory features such as mel-frequency cepstral coefficients are provided to the second neural network. A classification of the input audio sample is received from the second neural network.

Abstract: A system for detecting and resolving an abnormal settling event in a vehicle includes an image sensor and a processing system. The processing system is configured to, upon commencement of a passenger entry into the vehicle, receive image data from the image sensor, process the image data to determine a location of at least one passenger in the cabin, detect that the at least one passenger is located outside of the one or more seats of the vehicle, after a first predetermined time period has elapsed from the commencement of the passenger entry into the vehicle, based on the determined location of the at least one passenger in the cabin, and operate at least one component of the vehicle in a predefined manner in response to detecting that the at least one passenger is located outside of the one or more seats after the first predetermined time period has elapsed.

Abstract: A system for detecting and mitigating an unsafe condition in a vehicle includes an image sensor configured to generate and output image data of one or more seats in a cabin of the vehicle and a processing system operably connected to the image sensor and including at least one processor. The processing system is configured to receive the image data from the image sensor, process the image data to determine a location of at least one passenger in the cabin, detect that the at least one passenger is located outside of the one or more seats based on the determined location of the at least one passenger in the cabin, and operate at least one component of the vehicle in a predefined manner in response to detecting that the at least one passenger is located outside of the one or more seats.

Abstract: Low energy deep-learning networks for generating auditory features such as mel frequency cepstral coefficients in audio processing pipelines are provided. In various embodiments, a first neural network is trained to output auditory features such as mel-frequency cepstral coefficients, linear predictive coding coefficients, perceptual linear predictive coefficients, spectral coefficients, filter bank coefficients, and/or spectro-temporal receptive fields based on input audio samples. A second neural network is trained to output a classification based on input auditory features such as mel-frequency cepstral coefficients. An input audio sample is provided to the first neural network. Auditory features such as mel-frequency cepstral coefficients are received from the first neural network. The auditory features such as mel-frequency cepstral coefficients are provided to the second neural network. A classification of the input audio sample is received from the second neural network.