Artificial intelligence-enabled alarm for detecting passengers locked in vehicle

A non-transitory computer-readable storage medium for tangibly storing computer program instructions capable of being executed by a computer processor, the computer program instructions defining the steps of:

• receiving signaling from a transmission control unit (TCU) of a vehicle, the signaling indicating that the vehicle has stopped, was placed in a parked state, and was locked after a driver of the vehicle exited the vehicle;
• activating at least one camera;
• adjusting a field of view of the at least one camera responsive to receiving the signaling;
• recording at least one image of an interior of the vehicle using the at least one camera in response to receiving the signaling while the vehicle is in the parked state;
• classifying the at least one image using a machine learning model;
• operating at least one subsystem of the vehicle in response to detecting that classifying indicates that a person or animal is present in the at least one image;
• and
• stepping down a frequency of classifying in response to detecting that classifying does not indicate that the person or the animal is present in the at least one image, the stepping down comprising one or both of lengthening an amount of time in between capturing later images of the interior of the vehicle and classifying the later images using the machine learning model, the amount of time determined as a fraction of a preconfigured value stored in a vehicle profile, wherein the stepping down is performed iteratively until the amount of time exceeds the preconfigured value.

An apparatus comprising:

• a processor;
• and
• a storage medium for tangibly storing thereon program logic for execution by the processor, the stored program logic causing the processor to perform the operations of:
• receiving signaling from a transmission control unit (TCU) of a vehicle, the signaling indicating that the vehicle has stopped, was placed in a parked state, and was locked after a driver of the vehicle exited the vehicle,
• activating at least one camera,
• adjusting a field of view of the at least one camera responsive to receiving the signaling,
• recording at least one image of an interior of the vehicle using the at least one camera in response to receiving the signaling while the vehicle is in the parked state,
• classifying the at least one image using a machine learning model,
• operating at least one subsystem of the vehicle in response to detecting that classifying indicates that a person or animal is present in the at least one image, and
• stepping down a frequency of classifying in response to detecting that classifying does not indicate that the person or the animal is present in the at least one image, the stepping down comprising one or both of lengthening an amount of time in between capturing later images of the interior of the vehicle and classifying the later images using the machine learning model, the amount of time determined as a fraction of a preconfigured value stored in a vehicle profile, wherein the stepping down is performed iteratively until the amount of time exceeds the preconfigured value.