Abstract
It is difficult for structural over-complete dictionaries such as the Gabor function and discriminative over-complete dictionary, which are learned offline and classified manually, to represent natural images with the goal of ideal sparseness and to enhance the difference between background clutter and target signals. This paper proposes an infrared dim target detection approach based on sparse representation on a discriminative over-complete dictionary. An adaptive morphological over-complete dictionary is trained and constructed online according to the content of infrared image by K-singular value decomposition (K-SVD) algorithm. Then the adaptive morphological over-complete dictionary is divided automatically into a target over-complete dictionary describing target signals, and a background over-complete dictionary embedding background by the criteria that the atoms in the target over-complete dictionary could be decomposed more sparsely based on a Gaussian over-complete dictionary than the one in the background over-complete dictionary. This discriminative over-complete dictionary can not only capture significant features of background clutter and dim targets better than a structural over-complete dictionary, but also strengthens the sparse feature difference between background and target more efficiently than a discriminative over-complete dictionary learned offline and classified manually. The target and background clutter can be sparsely decomposed over their corresponding over-complete dictionaries, yet couldn't be sparsely decomposed based on their opposite over-complete dictionary, so their residuals after reconstruction by the prescribed number of target and background atoms differ very visibly. Some experiments are included and the results show that this proposed approach could not only improve the sparsity more efficiently, but also enhance the performance of small target detection more effectively.
Highlights
IntroductionThe distance between man-made satellites and ground-based EO sensors is usually more than
The distance between man-made satellites and ground-based EO sensors is usually more than30,000 km, and the angle between the object and ground-based EO sensor is so small that the target on a EO sensor is a small blob with only several pixels
An adaptive morphological over-complete dictionary is built according to infrared image content by a K-singular value decomposition (K-SVD) algorithm [21], and a target over-complete dictionary is discriminated automatically from a background over-complete dictionary by the criteria that the atoms representing dim target signals could be decomposed more sparsely over a Gaussian over-complete dictionary than the one in a background over-complete dictionary
Summary
The distance between man-made satellites and ground-based EO sensors is usually more than. The discriminative over-complete dictionary trained manually could greatly improve the sparsity of the representation coefficient vector and improve the performance of dim target detection. Its serious limitation is that the atoms couldn’t adapt to moving targets and changing backgrounds effectively, so it is necessary to distinguish the atoms automatically for the discriminative over-complete dictionary in order to further enhance the capability of dim target detection. An infrared dim target detection approach based on sparse representation over discriminative over-complete dictionary learned online is proposed in this paper. An adaptive morphological over-complete dictionary is built according to infrared image content by a K-singular value decomposition (K-SVD) algorithm [21], and a target over-complete dictionary is discriminated automatically from a background over-complete dictionary by the criteria that the atoms representing dim target signals could be decomposed more sparsely over a Gaussian over-complete dictionary than the one in a background over-complete dictionary.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
