Multiscale algorithm for ship detection in mid, high and very high resolution optical imagery

Jubelin, Guillaume; Khenchaf, Ali

doi:10.1109/igarss.2014.6946927

Cited by 14 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic ship detection in optical satellite images has attracted intensive investigations (Bi et al, 2012 ; Jubelin and Khenchaf, 2014 ; Qi et al, 2015 ; Zou and Shi, 2016 ; Li et al, 2020 ). It plays a crucial role in a maritime surveillance system.…”

Section: Applications To Ship Detection In Optical Satellite Imagesmentioning

confidence: 99%

Visual Saliency via Multiscale Analysis in Frequency Domain and Its Applications to Ship Detection in Optical Satellite Images

Qian

2022

Front. Neurorobot.

View full text Add to dashboard Cite

This article proposes a bottom-up visual saliency model that uses the wavelet transform to conduct multiscale analysis and computation in the frequency domain. First, we compute the multiscale magnitude spectra by performing a wavelet transform to decompose the magnitude spectrum of the discrete cosine coefficients of an input image. Next, we obtain multiple saliency maps of different spatial scales through an inverse transformation from the frequency domain to the spatial domain, which utilizes the discrete cosine magnitude spectra after multiscale wavelet decomposition. Then, we employ an evaluation function to automatically select the two best multiscale saliency maps. A final saliency map is generated via an adaptive integration of the two selected multiscale saliency maps. The proposed model is fast, efficient, and can simultaneously detect salient regions or objects of different sizes. It outperforms state-of-the-art bottom-up saliency approaches in the experiments of psychophysical consistency, eye fixation prediction, and saliency detection for natural images. In addition, the proposed model is applied to automatic ship detection in optical satellite images. Ship detection tests on satellite data of visual optical spectrum not only demonstrate our saliency model's effectiveness in detecting small and large salient targets but also verify its robustness against various sea background disturbances.

show abstract

Section: Applications To Ship Detection In Optical Satellite Imagesmentioning

confidence: 99%

Visual Saliency via Multiscale Analysis in Frequency Domain and Its Applications to Ship Detection in Optical Satellite Images

Qian

2022

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…Wavelet decomposition is used to detect ships of any size in both optical and SAR imagery [4]. Difficult to process very high resolution optical images with whitecaps, even if the ships are detected it has more false alarm due to whitecaps DT-CWT highlight superior performance in parameter such as PSNR, RMSE compared to DWT and DWT-SWTMultiscale heterogeneities and contrario decision is used to detect ship [6].…”

Section: Iiliterature Surveymentioning

confidence: 99%

A Multiscale Approach Based Automatic Ship Detection

R¹,

Chetan²,

Deepika³

et al. 2019

IJCESR

View full text Add to dashboard Cite

This paper presents a new method for ship detection. It uses SAR image obtained by passing pulses of microwave signal and recording the reflected signal. SAR image is used for ship detection because it functions irrespective of weather conditions even at day and night. Speckle noise is inbuilt in SAR images are formed by recording the radar echo signals of EM signal multiplicative with granular noise;this noise degrades the quality of SAR images. Preprocessing is done using Lee filter to remove the speckle noise. Quality measurement like SNR, PSNR, SSIM and ENL is done. Image profile is verified to find effective noise suppression. After pre-processing the SAR image is enhanced using DWT (discrete wavelet transform) this wavelet transform preserves high frequency information and reduces artifacts. Enhanced image consists of many information from which the relevant image has to be extracted this process is called as feature extraction, feature extraction is done using k-means Clustering algorithm were the given data is grouped into k number of clusters. Finally, the ship detection image is obtained and it is compared with the ground truth image, quantitatively the ship Detection image is evaluated using confusion matrix.

show abstract

“…Previous research has used optical imagery for ship detection [4][5][6][7][8][9]. Such methods are usually composed of two parts: (i) A prescreening step to extract the ship candidates and (ii) a strengthening step to reduce the number of false alarms, as well as to detect the real ships.…”

Section: Introductionmentioning

confidence: 99%

Automatic Ship Detection Using the Artificial Neural Network and Support Vector Machine from X-Band Sar Satellite Images

Hwang

Jung

2018

Remote Sensing

View full text Add to dashboard Cite

In this paper, an automatic ship detection method using the artificial neural network (ANN) and support vector machine (SVM) from X-band SAR satellite images is proposed. When using machine learning techniques, the most important points to consider are (i) defining the proper input neurons and (ii) selecting the correct training data. We focused on generating two optimal input data neurons that (i) strengthened ship targets and (ii) mitigated noise effects by image processing techniques, including median filtering, multi-looking, etc. The median filter and multi-look operations were used to reduce the background noise, and the median filter operation was also used to remove ships in an image in order to maximize the difference between the pixel values of ships and the sea. Through the root-mean-square difference calculation, most ship targets, even including small ships, were emphasized in the images. We tested the performance of the proposed method using X-band high-resolution SAR images including COSMO-SkyMed, KOMPSAT-5, and TerraSAR-X images. An intensity difference map and a texture difference map were extracted from the X-band SAR single-look complex (SLC) images, and then, the maps were used as input neurons for the ANN and SVM machine learning techniques. Finally, we created ship-probability maps through the machine learning techniques. To validate the ANN and SVM results, optimal threshold values were obtained by using the statistical approach and then used to identify ships from the ship-probability maps. Consequently, the level of recall achieved was greater than 90% in most cases. This means that the proposed method enables the detection of most ship targets from X-band SAR images with a reduced number of false detections from negative effects.

show abstract

Multiscale algorithm for ship detection in mid, high and very high resolution optical imagery

Cited by 14 publications

References 6 publications

Visual Saliency via Multiscale Analysis in Frequency Domain and Its Applications to Ship Detection in Optical Satellite Images

Visual Saliency via Multiscale Analysis in Frequency Domain and Its Applications to Ship Detection in Optical Satellite Images

A Multiscale Approach Based Automatic Ship Detection

Automatic Ship Detection Using the Artificial Neural Network and Support Vector Machine from X-Band Sar Satellite Images

Contact Info

Product

Resources

About