Small-Object Detection via Fast Discrete Curvelet Transform
- Tuesday, 01 July 2014
NASA’s Jet Propulsion Laboratory, Pasadena, California
The detection of distant objects in an image is relevant to applications in defense, security, and robotics. Successfully detecting objects of interest has been a common problem with respect to intelligent computer vision. Automatic target recognition (ATR) systems have been formulated and employed in numerous ways to tackle the difficulty of unsupervised targeting.
A new approach was developed in the selection of a potential target area or region of interest (ROI) in an image. An ROI from a particular image is simply a subset of an image whose size is dependent upon the user, or is chosen by an adaptive process. Each ROI should contain an object of interest or information that is pertinent to the user or system. The goal of this work is to reduce the amount of ROIs without the unintended loss of an object of interest.
The Fast Discrete Curvelet Transform (FDCT) was implemented as the first stage in this system’s framework in order to have a collection of sufficient Curvelet coefficients. The Curvelet coefficients sparsify the input image, and by this sparsification, one is able to locate and extract ROIs. Once the ROIs have been extracted, they are then passed to the second stage of the framework, which is the classification stage. In this stage, it is verified whether or not each ROI has an object of interest. After an image has been processed by this framework, the output should be the successful detection of meaningful objects or targets contained in the image.
Preliminary experiments showed an excellent detection of small artifacts of varying sizes in multiple datasets. The detection of small objects is nondiscriminatory compared to other methods commonly used for ROI extraction.