Abstract: A system and method of detecting a sobriety of a subject utilizing a mobile device. The mobile device includes a processor and a memory storing historical data including movements indicating a drunk state, movements indicating a sober state, or a combination of both. The mobile device further includes a user interface, a recorder operable to capture a recording, and an accelerometer operable to generate acceleration values of movements of the recording. When the mobile device captures the recording of a subject performing movements, the processor compares the data on the memory with the acceleration values of the movements of the subject and produces an indication of either a drunk state of the subject or a sober state of the subject on the user interface.

Abstract: A video monitoring method that involves determining motion changes in a set of video frames to find potential objects is described. One or more bounding boxes are defined around the potential objects. These bounding boxes are spatially and temporally filtered to eliminate potential object candidates, with only potential objects in the bounding boxes remaining after filtering being classified or identified.

Abstract: A method for processing arrival or removal of packages within the field of view of a video camera includes providing a database for recording packages placed in the field of view. Based on real-time analysis of successive image frames in the camera, a human person's entry and exit from the field of view of the camera is also detected. Delivery or removal of objects is recorded in the database. In one embodiment, the method also determines whether or not a newly arrived package is placed alongside or on top of an existing package.

Abstract: A system and method of detecting a sobriety of a subject utilizing a mobile device. The mobile device includes a processor and a memory storing historical data including movements indicating a drunk state, movements indicating a sober state, or a combination of both. The mobile device further includes a user interface, a recorder operable to capture a recording, and an accelerometer operable to generate acceleration values of movements of the recording. When the mobile device captures the recording of a subject performing movements, the processor compares the data on the memory with the acceleration values of the movements of the subject and produces an indication of either a drunk state of the subject or a sober state of the subject on the user interface.

Abstract: A method for processing arrival or removal of packages within the field of view of a video camera includes providing a database for recording packages placed in the field of view. Based on real-time analysis of successive image frames in the camera, a human person's entry and exit from the field of view of the camera is also detected. Delivery or removal of objects is recorded in the database. In one embodiment, the method also determines whether or not a newly arrived package is placed alongside or on top of an existing package.

Abstract: A video monitoring method that involves determining motion changes in a set of video frames to find potential objects is described. One or more bounding boxes are defined around the potential objects. These bounding boxes are spatially and temporally filtered to eliminate potential object candidates, with only potential objects in the bounding boxes remaining after filtering being classified or identified.

Abstract: Embodiments of the present disclosure include a non-transitory computer-readable medium with computer-executable instructions stored thereon executed by one or more processors to perform a method to select and implement a neural network for an embedded system. The method includes selecting a neural network from a library of neural networks based on one or more parameters of the embedded system, the one or more parameters constraining the selection of the neural network. The method also includes training the neural network using a dataset. The method further includes compressing the neural network for implementation on the embedded system, wherein compressing the neural network comprises adjusting at least one float of the neural network.