Aircraft Detection in High-Resolution SAR Images Based on a Gradient Textural Saliency Map

Tan, Yihua; Li, Qingyun; Li, Yansheng; Tian, Jinwen

doi:10.3390/s150923071

Cited by 38 publications

(23 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In many practical applications, it is not a simple task to label the accurate boundary of targets in the infrared imagery [106] or SAR imagery [107]. However, we can easily determine whether one image block (i.e., scene) contains the target of interest or not.…”

Section: Automatic Target Detection Under Scene-tag-supervisionmentioning

confidence: 99%

A Survey on Deep Learning-Driven Remote Sensing Image Scene Understanding: Scene Classification, Scene Retrieval and Scene-Guided Object Detection

Wang

2019

Applied Sciences

Self Cite

117

View full text Add to dashboard Cite

As a fundamental and important task in remote sensing, remote sensing image scene understanding (RSISU) has attracted tremendous research interest in recent years. RSISU includes the following sub-tasks: remote sensing image scene classification, remote sensing image scene retrieval, and scene-driven remote sensing image object detection. Although these sub-tasks have different goals, they share some communal hints. Hence, this paper tries to discuss them as a whole. Similar to other domains (e.g., speech recognition and natural image recognition), deep learning has also become the state-of-the-art technique in RSISU. To facilitate the sustainable progress of RSISU, this paper presents a comprehensive review of deep-learning-based RSISU methods, and points out some future research directions and potential applications of RSISU.

show abstract

Section: Automatic Target Detection Under Scene-tag-supervisionmentioning

confidence: 99%

A Survey on Deep Learning-Driven Remote Sensing Image Scene Understanding: Scene Classification, Scene Retrieval and Scene-Guided Object Detection

Wang

2019

Applied Sciences

Self Cite

117

View full text Add to dashboard Cite

show abstract

“…For the ACCA-ODV, the value of P fc is set equal to 10 −2 and the value of (N, p) set equal to (24,16).…”

Section: Multiple Target Situations With Different Number Of Interfermentioning

confidence: 99%

“…In [23], Smith and Varshney proposed the idea of variability index (VI) detection strategy. The VI-CFAR performs robustly in a homogeneous environment and multiple target situations [24]. However, its detection performance will also be deteriorated if the interfering targets are not restricted to a unilateral reference window [23].…”

Section: Introductionmentioning

confidence: 99%

Positive Definite Matrix Space Based Detector With Limited Training Samples for Multiple Target Situations

Wen¹,

Huang²,

Cui³

et al. 2017

PIER M

View full text Add to dashboard Cite

Abstract-Multiple target situation is a typical situation of nonhomogeneous clutter environment, which can cause excessive target masking in radar signal detection system. In order to reduce target masking caused by multiple target situations, this paper proposes a new detection structure based on positive-definite matrix space and limited training samples. The proposed detection structure uses a positive-definite matrix to estimate the background power level. In addition, with limited training samples, the detection structure is used to resist the multiple target situations. The simulation results show that the proposed detection structure exhibits a better detection performance than that of the well-known CA-CFAR in homogeneous environment. The detector also performs robustly in multiple target situations, even though 10 interfering targets exist in a length of 24 samples of reference window. Furthermore, the measured results validate the performance of the proposed method.

show abstract

“…Owing to the scattering mechanism in high-resolution SAR imagery, the airplane target in the image is presented as bright or dark scattering points [25], called sparsity (shown in Figure 1). Therefore, in some traditional detection algorithms, the object is divided into many small patches, making it difficult to be fully detected.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Component Selection-Based Discriminative Model for Object Detection in High-Resolution SAR Imagery

Xiong

et al. 2018

IJGI

View full text Add to dashboard Cite

This paper proposes an innovative Adaptive Component Selection-Based Discriminative Model (ACSDM) for object detection in high-resolution synthetic aperture radar (SAR) imagery. In order to explore the structural relationships between the target and the components, a multi-scale detector consisting of a root filter and several part filters is established, using Histogram of Oriented Gradient (HOG) features to describe the object from different resolutions. To make the detected components of practical significance, the size and anchor position of each component are determined through statistical methods. When training the root model and the corresponding part models, manual annotation is adopted to label the target in the training set. Besides, a penalty factor is introduced to compensate information loss in preprocessing. In the detection stage, the Small Area-Based Non-Maximum Suppression (SANMS) method is utilised for filtering out duplicate results. In the experiments, the aeroplanes in TerraSAR-X SAR images are detected by the ACSDM algorithm and different comparative methods. The results indicate that the proposed method has a lower false alarm rate and can detect the components accurately.

show abstract

Aircraft Detection in High-Resolution SAR Images Based on a Gradient Textural Saliency Map

Cited by 38 publications

References 22 publications

A Survey on Deep Learning-Driven Remote Sensing Image Scene Understanding: Scene Classification, Scene Retrieval and Scene-Guided Object Detection

A Survey on Deep Learning-Driven Remote Sensing Image Scene Understanding: Scene Classification, Scene Retrieval and Scene-Guided Object Detection

Positive Definite Matrix Space Based Detector With Limited Training Samples for Multiple Target Situations

Adaptive Component Selection-Based Discriminative Model for Object Detection in High-Resolution SAR Imagery

Contact Info

Product

Resources

About