Robust Infrared Small Target Detection via Multidirectional Derivative-Based Weighted Contrast Measure

Lu, Richard; Yang, Xiaogang; Li, Weipeng; Fan, Jiwei; Li, Dalei; Xin, Jing

doi:10.1109/lgrs.2020.3026546

Cited by 60 publications

(42 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The comparison with the buoy measurements has a bias of 0.12 m/s and an RMSE of 1.42 m/s. A recent study [29] shows that the retrieval of SSWS by S1 HH−polarized data using the CMODH algorithm [12] resulted in a bias of 0.49 m/s and an RMSE of 2.05 m/s compared with NDBC buoy…”

Section: Comparison Of the S1−retrieved Ssws With In Situ Measurementsmentioning

confidence: 99%

Retrieval of Sea Surface Wind Speed from Spaceborne SAR over the Arctic Marginal Ice Zone with a Neural Network

Qin

2020

Remote Sensing

View full text Add to dashboard Cite

In this paper, we presented a method for retrieving sea surface wind speed (SSWS) from Sentinel-1 synthetic aperture radar (SAR) horizontal-horizontal (HH) polarization data in extra-wide (EW) swath mode, which have been extensively acquired over the Arctic for polar monitoring. In contrast to the conventional algorithm, i.e., using a geophysical model function (GMF) to retrieve SSWS by spaceborne SAR, we introduced an alternative retrieval method based on a GMF-guided neural network. The SAR normalized radar cross section, incidence angle, and wind direction are used as the inputs of a back propagation (BP) neural network, and the output is the SSWS. The network is developed based on 11,431 HH-polarized EW images acquired in the marginal ice zone (MIZ) of the Arctic from 2015 to 2018 and their collocated scatterometer wind measurements. Verification of the neural network based on the testing dataset yields a bias of 0.23 m/s and a root mean square error (RMSE) of 1.25 m/s compared to the scatterometer wind data for wind speeds less than approximately 30 m/s. Further comparison of the SAR retrieved SSWS with independent buoy measurements shows a bias and RMSE of 0.12 m/s and 1.42 m/s, respectively. We also analyzed the uncertainty of the retrieval when reanalysis model wind direction data are used as inputs to the neural network. By combining the detected sea ice cover information based on SAR data, sea ice and marine-meteorological parameters can be derived simultaneously by spaceborne SAR at a high spatial resolution in the Arctic.

show abstract

Section: Comparison Of the S1−retrieved Ssws With In Situ Measurementsmentioning

confidence: 99%

Retrieval of Sea Surface Wind Speed from Spaceborne SAR over the Arctic Marginal Ice Zone with a Neural Network

Qin

2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…These local contrastbased methods are easy to implement but have poor detection performance for infrared images with intricate background and strong clutters which will cause high false alarm rate. To address this problem, the multidirectional derivative-based weighted contrast measure (MDWCM) [27] was proposed to detect infrared small target by analyzing derivative subbands properties and division scheme of surrounding area. However, for infrared maritime images captured under strong wind condition, the derivative properties of strong waves are similar to small targets, which might cause serious false alarms.…”

Section: Introductionmentioning

confidence: 99%

Infrared Small Maritime Target Detection Based on Integrated Target Saliency Measure

Yang

Dong

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Robust and effective detection of small target in infrared maritime image is a key technology of maritime target search and tracking applications. Infrared small target detection is a challenging task due to the factors such as dim small targets and various complex backgrounds caused by sun glitters and strong waves. In this paper, the integrated target saliency measure (ITSM) based on local and nonlocal spatial information is proposed to improve target detection performance. We combine local heterogeneity property of targets and nonlocal self-correlation property of background with targets' sparsity to separate real targets from background clutters. Firstly, local heterogeneity calculation based on cross-window standard deviation (CSD) is proposed to extract candidate targets preliminarily, which enhances the local intensity difference between small targets and neighboring background. Meanwhile, low-rank representation (LRR) is applied to background prediction and removal, which is followed by adaptive threshold segmentation to enhance target saliency. Finally, we integrate the results obtained from the two steps above to further enhance targets and suppress background clutters. Then, real targets are extracted by an iterative threshold on the integrated map so as to generate the seed map, in addition, the target expansion strategy is exploited to keep full target areas. Experimental results on six data sets show that the proposed method outperforms the state-of-the-art methods in terms of robustness and target detection accuracy.

show abstract

“…Formation control is sparked off by the biological formation phenomena with local information transmissions, which refers to that multiple intelligent agents are able to spontaneously form and maintain some formation structures and no central processing node is required. Distributed formation can be utilized to finish various tasks, such as the multiple unmanned aerial vehicle cooperative surveillance with infrared small target detection, 14,15 the multi‐robot cooperative transportation, the satellite‐cluster seeking with large‐scale hyperspectral image, 16 and so forth.…”

Section: Introductionmentioning

confidence: 99%

Formation tracking for singular swarm systems subjected to energy constraints and switching transmission topologies

Cheng

et al. 2021

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

This article investigates admissible formation tracking for singular swarm systems under conditions of switching transmission topologies as well as the limited energy supply, where both switching transmission topologies containing a spanning tree and switching transmission topologies containing a joint spanning tree are addressed. First, a new formation control tracking protocol with switching transmission topologies is proposed to realize admissible formation tracking, where the total energy supply is predetermined. Afterwards, by a dual nonsingular transformation, the disagreement dynamics between followers and the leader is determined and the impacts of asymmetric structures of switching transmission topologies are eliminated. Sufficient conditions for admissible formation tracking design and analysis for singular swarm systems with switching transmission topologies containing a spanning tree and with switching transmission topologies containing a joint spanning tree are proposed, respectively, where the coupling relationship matrix between the total energy supply and the matrix variable is determined. Finally, two numerical simulations are presented to demonstrate the effectiveness of theoretical results.

show abstract

Robust Infrared Small Target Detection via Multidirectional Derivative-Based Weighted Contrast Measure

Cited by 60 publications

References 15 publications

Retrieval of Sea Surface Wind Speed from Spaceborne SAR over the Arctic Marginal Ice Zone with a Neural Network

Retrieval of Sea Surface Wind Speed from Spaceborne SAR over the Arctic Marginal Ice Zone with a Neural Network

Infrared Small Maritime Target Detection Based on Integrated Target Saliency Measure

Formation tracking for singular swarm systems subjected to energy constraints and switching transmission topologies

Contact Info

Product

Resources

About