Automated camera mode selection using local motion vectors is described. An image capture device includes an image metric estimation unit to detect a presence or level of an image metric in a scene of an image to capture based on image metric inputs, a motion estimation unit to determine a level of movement within the scene using ratios of histograms based on local motion vectors, a mode selection unit to select a camera mode for capturing the image based on outputs of the image metric estimation unit and the motion estimation unit, and an image sensor to capture the image according to the selected camera mode. The motion estimation unit computes a norm for each local motion vector, generates a histogram from the computed norms, determines movement metrics based on the ratios of histograms associated with different norm thresholds, and identifies the level of movement based on the movement metrics.