A fast-saliency method for real-time infrared small target detection

Qi, Shengxiang; Xu, Guowen; Mou, Zhiying; Huang, Duruo; Zheng, Xueli

doi:10.1016/j.infrared.2016.06.026

Cited by 48 publications

(27 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This category of methods is based on the assumption of background consistency of infrared images, and usually adopts filters to suppress background and clutter. The Tophat method [18], Max-Mean and Max-Median method [19], facet model method [20,21] have been proposed and applied to the field of infrared small target detection. However, the assumptions and principles of the background suppression based methods are relatively simple, and the detection effect is not ideal.…”

Section: Detection Before Trackmentioning

confidence: 99%

Infrared Small Target Detection Based on Non-Convex Optimization with Lp-Norm Constraint

et al. 2019

View full text Add to dashboard Cite

The infrared search and track (IRST) system has been widely used, and the field of infrared small target detection has also received much attention. Based on this background, this paper proposes a novel infrared small target detection method based on non-convex optimization with Lp-norm constraint (NOLC). The NOLC method strengthens the sparse item constraint with Lp-norm while appropriately scaling the constraints on low-rank item, so the NP-hard problem is transformed into a non-convex optimization problem. First, the infrared image is converted into a patch image and is secondly solved by the alternating direction method of multipliers (ADMM). In this paper, an efficient solver is given by improving the convergence strategy. The experiment shows that NOLC can accurately detect the target and greatly suppress the background, and the advantages of the NOLC method in detection efficiency and computational efficiency are verified.

show abstract

Section: Detection Before Trackmentioning

confidence: 99%

Infrared Small Target Detection Based on Non-Convex Optimization with Lp-Norm Constraint

et al. 2019

View full text Add to dashboard Cite

show abstract

“…There are Max-Median algorithm [22], Max-Mean algorithm [22], Fast-saliency algorithm [21], a local-contrast-method (LCM) algorithm [13] and improved LCM (ILCM) algorithm [14].…”

Section: Evaluation Metrics and Comparisonmentioning

confidence: 99%

“…Then a target-saliency map can be acquired and targets can be extracted from the target-saliency map. Inspired by DSBM method, both Yang et al [20] and Qi et al [21] presented small target detection methods by using a facet model to calculate second-order derivatives for enhancing target intensity and better performance are achieved.…”

Section: Introductionmentioning

confidence: 99%

“…The main idea of the method is to search different directional first-order zero-crossing points by using FODD filters. Different from above three methods [18,20,21], we calculate different FODD maps of original images rather than second-order derivatives by using a facet model. After that different directional first-order zero-crossing points are obtained based on different FODD maps.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Infrared small target detection based on directional zero-crossing measure

Zhang

Ding

Luo

et al. 2017

Infrared Physics & Technology

View full text Add to dashboard Cite

“…Based on the saliency detection, the original image is decomposed into second-order saliency maps in different directions, and the target can be detected. With the help of DSBM, Qi et al [15] proposed a fast detection algorithm based on the facet model. Yang et al [16] presented a multiscale facet model (MFM).…”

Section: Introductionmentioning

confidence: 99%