Abstract
Background estimation is an efficient infrared (IR) small target detection method. However, to deal with unknown targets, the estimation window in existing algorithms should be adjusted to perform multiscale detection and requires a lot of calculations. Besides, the stages during and after estimation have received wide attention in existing algorithms, but the research on the stages before estimation is insufficient. Moreover, existing algorithms typically regard the maximum value of different orientations as the estimation value. However, when a dim target is adjacent to high-brightness background, it is easily submerged. This article proposes a three-layer estimation window to detect targets of different sizes with only a single-scale calculation. The enhanced closest-mean background estimation method is then proposed and carefully designed before, during, and after the estimation. Before estimation, the matched filter is adopted to improve the image signal-to-noise ratio. During estimation, the principle of closest-mean is proposed to suppress high-brightness background. After estimation, a ratio-difference operation is performed to enhance the true target and suppress the background simultaneously. A simple checking mechanism is proposed to further improve the detection performance. Experiments on some IR images demonstrate the effectiveness and robustness of the proposed method. Compared with existing algorithms, the proposed method has better target enhancement, background suppression, and computational efficiency.
Highlights
I N INFRARED (IR) precise guidance [1], early warning [2], space tracking [3], maritime target searching [4], and other fields, the target is usually very far from the detector
Due to the presence of trees, houses, clouds, sea waves, and other clutter, there are usually various types of complex backgrounds in the raw IR image, such as high-brightness background [6], background edge [7], and pixel-sized noise with high brightness (PNHB) [8], and they may cause severe interferences and bring low signal-to-clutter ratio (SCR) [9], which may lead to a high false alarm rate
4 will be ignored, and the darker background in other orientations will be taken as Closest-Mean Background Estimation (CMBE)
Summary
I N INFRARED (IR) precise guidance [1], early warning [2], space tracking [3], maritime target searching [4], and other fields, the target is usually very far from the detector. The wavelet transform [12] and Butterworth high-pass filter [13] decompose the image through some frequency-domain methods; the sparse representation [14] and the robust principal component analysis [15] decompose the whole image under constraints of sparse and low rank These algorithms require huge computations since the whole image information is needed to estimate the background of each pixel. The local contrast measure (LCM) [25], improved LCM (ILCM) [8], and multiscale patch-based contrast measure (MPCM) [26] adopt an image patch with a 3 × 3 cell estimation window They first calculate the average value of the eight surrounding cells and, take the maximum value as the background.
Sign-in/Register to view highlights & summary 
Published Version (
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