Ship Detection in Panchromatic Optical Remote Sensing Images Based on Visual Saliency and Multi-Dimensional Feature Description

Abstract

Ship detection in panchromatic optical remote sensing images is faced with two major challenges, locating candidate regions from complex backgrounds quickly and describing ships effectively to reduce false alarms. Here, a practical method was proposed to solve these issues. Firstly, we constructed a novel visual saliency detection method based on a hyper-complex Fourier transform of a quaternion to locate regions of interest (ROIs), which can improve the accuracy of the subsequent discrimination process for panchromatic images, compared with the phase spectrum quaternary Fourier transform (PQFT) method. In addition, the Gaussian filtering of different scales was performed on the transformed result to synthesize the best saliency map. An adaptive method based on GrabCut was then used for binary segmentation to extract candidate positions. With respect to the discrimination stage, a rotation-invariant modified local binary pattern (LBP) description was achieved by combining shape, texture, and moment invariant features to describe the ship targets more powerfully. Finally, the false alarms were eliminated through SVM training. The experimental results on panchromatic optical remote sensing images demonstrated that the presented saliency model under various indicators is superior, and the proposed ship detection method is accurate and fast with high robustness, based on detailed comparisons to existing efforts.

Improved YOLOv3 Based on Attention Mechanism for Fast and Accurate Ship Detection in Optical Remote Sensing Images

“…For instance, Tang et al [41] proposed HSV-YOLO which applied the difference of HSV color space among remote sensing images to extract the RoIs and sent them into the YOLOv3 [39] network. This approach is similar to saliency-based approaches [13,42]. However, the HSV-YOLO is not end-to-end due to the complex preprocessing based on the HSV difference.…”

A Novel Coarse-to-Fine Method of Ship Detection in Optical Remote Sensing Images Based on a Deep Residual Dense Network

“…The second stage, ship candidate region extraction, aims to extract potential candidate regions of ship targets from remote sensing images. Some typical methods in this stage include sliding window [22,26], saliency-based methods [16,[27][28][29], and wavelet-transformation-based methods [17,19]. At the last ship classification stage, each candidate region will be usually identified as a ship target or a non-ship target by feature representation and binary classification.…”

“…At the last ship classification stage, each candidate region will be usually identified as a ship target or a non-ship target by feature representation and binary classification. Earlier related works on this stage mainly used specially designed hand-crafted features to detect ships, including shape [21], texture [14,26], ship histogram of oriented gradient (S-HOG) [16,22], gist [27], structure local binary pattern (structure-LBP) [30], and different combinations of these features [14,17,29]. With these features, a classifier will be used to distinguish ships from false alarms, such as AdaBoost [31], support vector machine (SVM) [14,15], and extreme learning machine (ELM) [19].…”

Automatic Detection and Segmentation on Gas Plumes from Multibeam Water Column Images

“…Isaacs achieved object detection using an in situ weighted highlight-shadow detector, and performed a recognition process using an Ada-boosted decision tree classifier for underwater unexploded ordnance detection on simulated real aperture sonar data [26]. Feature selection is one of the most important steps in these machine learning algorithms, and Haar-like and Local Binary Patterns (LBP) are classical and common features in target detection [27][28][29][30][31]. On the whole, there are few studies on target detection in MWC images using features and classifiers.…”