Abstract: In accordance with one disclosed method, a computing device may determine that a plurality of frames of image data represent an object of a first type and may further determine at least first and second parameters indicative of first and second positions of a bounding box of the object within first and second frames, respectively. The computing device may calculate, using at least the first parameter and the second parameter, a rate at which a position of the bounding box is moving from frame to frame within the plurality of frames and may determine a variable that is based at least in part on the rate. Based at least in part on the variable satisfying a criterion, the computing device may cause acquired video to be recorded in a datastore.