Infrared small target detection via self-regularized weighted sparse model

Zhang, Tianfang; Peng, Zhenming; Wu, Hao; He, Yejun; Chao-hai, LI; Yang, Chunping

doi:10.1016/j.neucom.2020.08.065

Cited by 124 publications

(56 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The size is set to

. In this study, six salience features were extracted from the green channel, including the mean, standard deviation(SD), third moment (TM), energy, entropy, and contrast [ 25 , 26 , 27 ].…”

Section: Methodsmentioning

confidence: 99%

Local Structure Awareness-Based Retinal Microaneurysm Detection with Multi-Feature Combination

et al. 2022

Self Cite

View full text Add to dashboard Cite

Retinal microaneurysm (MA) is the initial symptom of diabetic retinopathy (DR). The automatic detection of MA is helpful to assist doctors in diagnosis and treatment. Previous algorithms focused on the features of the target itself; however, the local structural features of the target and background are also worth exploring. To achieve MA detection, an efficient local structure awareness-based retinal MA detection with the multi-feature combination (LSAMFC) is proposed in this paper. We propose a novel local structure feature called a ring gradient descriptor (RGD) to describe the structural differences between an object and its surrounding area. Then, a combination of RGD with the salience and texture features is used by a Gradient Boosting Decision Tree (GBDT) for candidate classification. We evaluate our algorithm on two public datasets, i.e., the e-ophtha MA dataset and retinopathy online challenge (ROC) dataset. The experimental results show that the performance of the trained model significantly improved after combining traditional features with RGD, and the area under the receiver operating characteristic curve (AUC) values in the test results of the datasets e-ophtha MA and ROC increased from 0.9615 to 0.9751 and from 0.9066 to 0.9409, respectively.

show abstract

“…The size is set to

. In this study, six salience features were extracted from the green channel, including the mean, standard deviation(SD), third moment (TM), energy, entropy, and contrast [ 25 , 26 , 27 ].…”

Section: Methodsmentioning

confidence: 99%

Local Structure Awareness-Based Retinal Microaneurysm Detection with Multi-Feature Combination

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Second, there are also recent advances in small target and texture-less segmentation in infrared and natural images. Researchers in [40] proposed a novel optimization method that formulates the infrared small target detection problem into sparse matrix reconstruction. They adopted overlapping edge information to enhance detection accuracy, and used self-regularization to mine background information.…”

Section: B Segmenting Small/texture-less Targetsmentioning

confidence: 99%

“…First, unlike infrared small target, the pancreas in CT images still carries important texture and shape information, and thus conventional CNN encoding layers are still important for feature extraction. Second, a popular assumption for the case of infrared small target [40], [42], [43] is that the background is low rank in nature which contains a large number of repeated elements, but this is not true for CT images. For pancreas segmentation, anywhere located outside of the pancreatic region is treated as ''background'', which could contain rich contextual information and large variations.…”

Section: B Segmenting Small/texture-less Targetsmentioning

confidence: 99%

MCMC Guided CNN Training and Segmentation for Pancreas Extraction

Mao

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Efficient organ segmentation is the precondition of various quantitative analysis. Segmenting the pancreas from abdominal CT images is a challenging task because of its high anatomical variability in shape, size and location. What's more, the pancreas only occupies a small portion in abdomen, and the organ border is very fuzzy. All these factors make the segmentation methods of other organs less suitable for pancreas. In this work, we propose a Markov Chain Monte Carlo (MCMC) guided convolutional neural network (CNN) approach, in order to handle such difficulties in morphological and photometric variabilities. Specifically, the proposed method mainly consists of three steps: First, registration is carried out to mitigate the body weight and location variability. Then, an MCMC scheme is designed to guide the adaptive selection of 3D patches, which are fed to the CNN for training. At the same time, the pancreas distribution is also learned for subsequent segmentation. Eventually, the same MCMC process guides the segmentation process with patch-wise predictions fused using a Bayesian voting scheme. This method is evaluated on the NIH pancreatic dataset including 82 abdominal contrast-enhanced CT volumes. We have achieved a competitive result of 78.13% Dice Similarity Coefficient value and 82.65% Recall value in testing data.

show abstract

“…A stable multisubspace learning (SMSL) [39] method uses multi-subspace characteristics to describe the data distribution in heterogeneous scenes, thereby providing improved target enhancement capabilities and excellent background suppression performance. Recently, a novel self-regularized weighted sparse (SRWS) [40] model uses overlapping edge information to detect background edges and structural information, and then applies it to constrained sparse items to improve the accuracy of the detection algorithm from the perspective of the target. The SRWS model is designed to assume that the background elements may come from multiple subspaces, and it converts the target detection problem into an optimization problem to effectively solve it.…”

Section: ) Image Decomposition Based On Optimization Theorymentioning

confidence: 99%

“…To verify the advantage of the proposed approach, nine state-of-the-art algorithms are executed for comparisons in this paper, including NSM [29], WNNM-MC [62], RLCM [26], TDGS [28], CF [30], IPI [37], NIPPS [38], SRWS [40], NWIE [36]. All competing algorithms are executed under fair conditions, and their detailed parameter settings are shown in Table IV.…”

Section: B Baselinesmentioning

confidence: 99%

Robust Infrared Superpixel Image Separation Model for Small Target Detection

Yan¹,

Xin²,

Liu³

et al. 2021

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

View full text Add to dashboard Cite

Accurate and rapid detection of small targets against complex background is a fundamental requirement of various computer vision systems. This work is the first attempt to apply the superpixel segmentation technology to the field of low resolution infrared small target detection in the extremely complex backgrounds. The main contributions are as follows. First of all, the simple linear iterative cluster (SLIC) algorithm is utilized to accurately classify the raw infrared image into three components: outlier superpixels, stable background superpixels and target superpixels, which appropriately aggregate similar background components as the basic unit of subsequent processing. In SLIC, an optional range of superpixels numbers is specified to robustly implement superpixel segmentation strategy on low resolution infrared images. Second, an outlier superpixel masking (OSM) model is proposed to perform accurate identification and masking of the outlier superpixels with highly heterogeneous backgrounds, thus minimizing false alarm rate. Specially, a 2D Gaussian filter matching the target distribution is introduced to blur the remaining boundary and pixel-sized noises with high brightness (PNHB) while maximizing the signal-to-noise ratio (SNR). Finally, a singular value truncation strategy with entropy weighted sparse factor (SVT-EW) is proposed to implement the final target extraction, which assigns specific sparsity weights for small infrared targets. SVT-EW effectively resolves the background residuals in gray-based threshold segmentation, and therefore generates precise target detection results. Extensive experimental results on fourteen extremely complex infrared natural scenes validate the superiority of the proposed method over the state-of-the-arts with respect to robustness and real-time performance.

show abstract

Infrared small target detection via self-regularized weighted sparse model

Cited by 124 publications

References 61 publications

Local Structure Awareness-Based Retinal Microaneurysm Detection with Multi-Feature Combination

Local Structure Awareness-Based Retinal Microaneurysm Detection with Multi-Feature Combination

MCMC Guided CNN Training and Segmentation for Pancreas Extraction

Robust Infrared Superpixel Image Separation Model for Small Target Detection

Contact Info

Product

Resources

About