Abstract: A machine learning (“ML”) model may be used to detect a presence of an object in one or more frames received from a camera sensor. The ML model may insert bounding boxes around the object and annotate the bounding boxes with one or more attributes of the object. The one or more frames and the annotated bounding boxes may be stored in a database configured to be searchable by at least one attribute of the one or more attributes. It may be determined whether the object is true positive (“TP”) event or a false positive (“FP”) event. The ML model may be re-trained using one or more of the database and the determination. If the object is a TP event, an alert may be transmitted to one or more devices with a location of the object that is based off of location information received from the camera sensor.

Abstract: A gravity gradiometer having quadrupole responders in which a mass quadrupole is supported by a torsional spring forming a flexure allowing rotation of the mass quadrupole about its center of mass. The flexure can be a pair of spaced apart posts. The flexure can be made from glassy metal having at room temperature a high elastic limit, high stiffness, high strength and low internal damping. The flexure can alternatively be a web made of glassy metal.