A learning algorithm for model based object detection

Detecting objects in images and videos is a difficult task that has challenged the field of computer vision. Most of the algorithms for object detection are sensitive to background clutter and occlusion, and cannot localize the edge of the object. An objects shape is typically the most discriminative cue for its recognition by humans. This paper introduces a model based object detection method which uses only shape-fragment features. The object shape model is learned from a very small set of training images. And the object model is composed of shape fragments. The model of the object is in multi-scales. The results presented in this paper are competitive with other state-of-the-art object detection methods. The major contributions of this paper are the application of learned shape fragments based model for object detection in complex environment and a novel two-stage object detection framework.