Informative and compressed features for aircraft detection in object recognition system

It is a challenging task to build efficient and robust model for aircraft detection. In our object recognition system, aircraft detection is a main task, which faces various problems, such as blur, occlusion, and shape variation and so on. Existing approaches always require a set of complex classification model and a large number of training samples, which is inefficient and costly. In order to deal with these problems, we employ location based informative features to reduce the complexity of training data. With the employment of location based informative features, simple classifiers will manifest high performance instead of complex classifier which requires more complicated strategy for training. Further, our system needs to update the model frequently which is similar to online learning method, in order to reducing computational complexity, a very sparse measurement matrix is applied to extract features from feature space. The construction of this sparse matrix is based on the theory of sparse representation and compressed sensing. From the experimental results, the detection rate and cost of our proposed method is better than other traditional method.