Textural and Gradient Feature Extraction from JPEG2000 Codestream for Airfield Detection
Cheng Li, Chenwei Deng, Baojun Zhao · 2016
There has been huge growth in the use of optical images in object detection, and numerous images over satellite and aerial vehicle are typically stored and transmitted in the compressed form such as JPEG2000. However, most of the existing detection algorithms are built in the pixel domain, which leads to enlarge data volume and requires compulsory decompression before detecting. Hence, these issues may hinder their practical use in real-time and storage limited applications. In this paper, we extract textural and gradient features from JPEG2000 compressed codestream, and these robust features are utilized for coarse-to-fine airfield detection. The contributions of proposed work are as follows: 1) packet header is effectively exploited for presenting textural information of images, while gradient calculation is achieved in packet body, 2) a novel detection framework taking full advantage of compressed features is proposed. Validated by experiments with large optical images, the proposed method achieves faster computation with higher detection accuracy, in comparison with the existing relevant state-of-the-art approaches.