Oil spill discrimination of multi-time-domain shipborne radar images using active contour model

Abstract

Accidental oil spills cause serious pollution to the ocean and are difficult to control in short time. It is an important guarantee for emergency disposal to effectively monitor oil spills. Remote sensing is the main means to monitor oil spills. High false alarm rate has been an important bottleneck of this technology. In this paper, a multi-time-domain shipborne radar images discrimination mechanism was proposed. Based on the improved Sobel operator, Otsu and linear interpolation, the co-frequency interference noises were detected and suppressed. Gray intensity correction model (GICM) and dual-threshold method were used to eliminate highlighted continuous pixels. Oil films were extracted by using an active contour model (ACM). Finally, a multi-time-domain discrimination mechanism based on variation range tolerance of identified oil films centroids was designed to reduce the false alarm rate. It can provide technical support for decision-making and emergency response.

Oil spill identification in X-band marine radar image using K-means and texture feature

“…The size of the each slice is generally the common factor of the length and width of the image, and the commonly used sizes are 8 × 8 pixels, 16 × 16 pixels, 32 × 32 pixels, 64 × 64 pixels, 128 × 128 pixels, and 256 × 256 pixels ( Xu et al, 2021a ; Xu et al, 2021b ). Considering the accuracy and efficiency, In this article, the de-noised image is cut into 64 × 64 pixels and 256 sub-images are generated.…”

“… Xu et al (2021a) ; Xu et al (2021b) used the Phansalkar algorithm for the segmentation of marine radar images to extract oil films. Yu et al (2017) adopted the improved Otsu algorithm for oil spill detection on SAR images.…”

“… Xu et al (2021a) ; Xu et al (2021b) conducted an oil spill extraction experiment using a combination of LBP and K-means (hereafter referred as Method 2). Here we use the same method to complete our experiment, the sliding window size is set to 128 pixels.…”

“…The original image needs to be preprocessed to extract the oil film region successfully. The pretreatment process referred to the methods adopted by Xu et al (2021a) ; Xu et al (2021b) , and the specific process is shown in Fig. 3 .…”

“…A modified K-means clustering was used to detect and segment the oil spill in the ocean ( Ganesan, 2015 ). By using a combination of LBP and K-means, the oil spill extraction experiment was operated successfully ( Xu et al, 2021a ; Xu et al, 2021b ). Two different artificial neural networks were employed to detect oil spills of SAR images which classified objects into oil spills or look-alikes ( Singha, Bellerby & Trieschmann, 2013 ).…”