Edge directional 2D LMS filter for infrared small target detection

Principal curvature for infrared small target detection

“…To compare the performance of these methods quantitatively, signal clutter ratio gain (SCRG) and background suppression factor (BSF) [7] are employed:…”

“…The target is fairly small and the SCR (signal-clutter ratio) is fairly low when the detection distance reaches 20 km or longer [2]. In recent years, many research works dedicated to the infrared small target detection have emerged [3][4][5][6][7][8][9][10][11][12][13]. In general, the detection algorithms include two parts: background suppression and detection/tracking (tracking before detection or detection before tracking).…”

“…In general, the detection algorithms include two parts: background suppression and detection/tracking (tracking before detection or detection before tracking). Conventional background suppression methods are mainly filter-based methods, such as morphological filter [3][4][5], 2D least mean squares filter [6,7], low pass filters [8], wavelet filter [9] etc. These methods are usually low time-consumption, and perform well when SCR is high.…”

Infrared small target detection based on directional zero-crossing measure

“…Then the WIPI model is transformed into an optimization problem. Bae et al [8] designed a novel filter named edge directional 2D least mean squares (2D LMS) filter to predict background. They preserve the good performance of 2D LMS filter while using the edge information to estimate background.…”

A sparse representation-based method for infrared dim target detection under sea–sky background

“…Zeng et al [6] used a Top-Hat morphological filter for infrared image target detection. Bae et al [7] introduced an edge directional two-dimensional least squares filter to detect a small target in infrared images. In addition, other researchers have applied fractal theory for infrared small objects detection [8,9] based on the fact that fractal dimension between man-made objects and the natural background is different.…”