Fast Image Object Detector

摘要

A specified object in still images or video may be detected using a sliding search window technique, applied to the original image and its downscaled versions, in order to detect objects of different sizes. At each scale and each position of the sliding window, the technique may use a boosted tree classifier to determine whether the window contains the object. It may exit earlier if some intermediate sum falls below the certain threshold. To accelerate object detection, hybrid features are used in different boosted chains. For first boosted chains, the fastest features may be applied and then, after more complex (but slower) features and for the last few chains, the most powerful feature (but most computationally expensive) is used. This strategy may improve the speed of detection because for a majority of checking windows, only first boosted chains are used and so only the fastest features are calculated in some embodiments.

主权项

1. A method of detecting objects in an image comprising:
applying a sliding search window technique onto the image to detect the presence of an object of a predetermined size within a defined area of the image; applying, in the defined area where the sliding search window technique detects an object, a modified boosted tree classifier to determine whether the defined area contains an object or not; wherein the boosted tree classifier comprises a first group of boosted chains to detect an object based on a plurality of groups of weak classifiers; if an object is detected, apply a second group of boosted chains based on a plurality of groups of strong classifiers; and if an object is still detected, provide an output listing an object candidate and its position and size in the defined area of the image.