Learning model for object detection based on local edge features

We present a learning model for object detection that uses a novel local edge features. The novel features are motivated by the scheme that use the chamfer distance as a shape comparison measure. The features can be calculated very quickly using a look-up table. Adaboost algorithm is used to select a discriminative edge features set from an over-complete local edge features pool and combine them to form an object detector. To demonstrate our method we trained a system to detect car in complex natural scenes using a single shape model. Experimental results show that our system can extremely rapidly detect objects in varying conditions (translation, scaling, occlusion and illumination) with high detection rate. The results are very competitive with other published object detection schemes. The learning techniques can be extended to detect other objects such as airplanes or pedestrian.