Target detection techniques play an important role in automatic target recognition (ATR) systems because overall ATR performance depends closely on detection results. In this paper, a novel method for fusion detection of infrared weak targets based on multifeature distance map (MFDM) in image sequences is proposed. As for small weak targets, there are many features, such as local entropy, average gradient strength. These features depict the characteristics of small infrared targets and can be extracted. Multifeature-based fusion techniques are applied to detect such weak targets. The problem of detecting small targets is converted to search peak values in specified feature space where multifeature vectors space (MFVS) is considered. Distance map (DM) can be derived according to feature vectors and target detection is performed in DM. In order to accumulate energy of targets deeply and suppress background and clutters to a great extent, five distance maps obtained by corresponding five consecutive frames are utilized to fuse with average weight, which results in the fact that the contrast between targets and background including clutters are enlarged and that the feature peaks of targets are obvious different from background and clutters. After these steps, a contrast segmentation method is used to extract targets from complicated background on the fused DM. Actual infrared image sequences in background of sea and sky are applied to validate the proposed approach. Experimental results demonstrate the robustness of the proposed method with high performance.
[1]
Mark L. Burton,et al.
Comparison Of Imaging Infrared Detection Algorithms
,
1982,
Optics & Photonics.
[2]
Yair Barniv,et al.
Dynamic Programming Solution for Detecting Dim Moving Targets
,
1985,
IEEE Transactions on Aerospace and Electronic Systems.
[3]
Heesung Kwon,et al.
Adaptive multisensor target detection using feature-based fusion
,
2002
.
[4]
Steven D. Blostein,et al.
Detecting small, moving objects in image sequences using sequential hypothesis testing
,
1991,
IEEE Trans. Signal Process..
[5]
E. Abdelkawy,et al.
Small infrared target detection using two-dimensional fast orthogonal search (2D-FOS)
,
2003,
SPIE Defense + Commercial Sensing.
[6]
Sheng Wen,et al.
Multi-Resolution Distance Map Based Small Target Detection in Infrared Image
,
2002
.
[7]
John K. Goutsias,et al.
Automatic target detection and tracking in forward-looking infrared image sequences using morphological connected operators
,
2004,
J. Electronic Imaging.
[8]
Roger Fortin,et al.
Detection of dim targets in digital infrared imagery by morphological image processing
,
1996
.