Abstract: A system for flow-count includes one or more cameras and a processing system. The one more cameras are configured to capture image data comprising a sequence of frames. The processing system is configured to extract spatial features and temporal features based on the sequence of frames; construct, based on the spatial features and temporal features, a density map and/or a flow map corresponding to a frame of the sequence of frames, wherein the density map comprises density values for the plurality of pixels, wherein the flow map comprises two-dimensional (2D) vectors for the plurality of pixels, and wherein a 2D vector indicates a speed and direction for a pixel of the plurality of pixels in the frame; and determine, based on the density map and/or the flow map, a count, a distribution, and/or movement of objects corresponding to the frame.