Ship recognition method combined with image segmentation and deep learning feature extraction in video surveillance

To solve the problem of ship recognition in video images, a ship recognition method based on Morphological Watershed image segmentation and Zemike moment is proposed. Firstly, the video frame image is pre-processed by gray algorithm, and then the gray image is filtered by wavelet transform to remove noise. After denoising, the Morphological Watershed algorithm is used to segment the image and extract the ship area in the image. Next, the feature of ship image is extracted based on deep learning convolution neural network (CNN) and Zemike moment method. Finally, the KNN-SVM classifier is trained according to the image features and class labels to realize the automatic recognition of ships. Experimental results show that the method can effectively identify 3 types of ships, with an average detection accuracy of 87%.

[1]  Ajay Boyat,et al.  Wavelet based image denoising using weighted highpass filtering coefficients and adaptive wiener filter , 2015, 2015 International Conference on Computer, Communication and Control (IC4).

[2]  Zengli Liu,et al.  A Wavelet Image Denoising Based on the New Threshold Function , 2015, 2015 11th International Conference on Computational Intelligence and Security (CIS).

[3]  Zhi Yang,et al.  Research on the Detection and Tracking Method of Ship Intrusion and Remaining , 2014, ICRA 2014.

[4]  Anupurba Nandi.  Detection of human brain tumour using MRI image segmentation and morphological operators , 2015, 2015 IEEE International Conference on Computer Graphics, Vision and Information Security (CGVIS).

[5]  Jung-San Lee,et al.  Selective scalable secret image sharing with verification , 2015, Multimedia Tools and Applications.

[6]  Aiguo Song,et al.  A new edge detection method using Gaussian-Zernike moment operator , 2010, 2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR 2010).

[7]  Giovanna Castellano,et al.  Fuzzy mathematical morphology for biological image segmentation , 2014, Applied Intelligence.

[8]  Haibo He,et al.  Comparisons of ADABOOST, KNN, SVM and Logistic Regression in Classification of Imbalanced Dataset , 2015, SCDS.

[9]  Chunhui Zhao,et al.  Hyperspectral anomaly detection based on stacked denoising autoencoders , 2017 .

[10]  Zhicheng Liu,et al.  A moving ship detection based on edge information of single image and background subtraction , 2013, Other Conferences.

[11]  Lihua Yue,et al.  A Novel Algorithm for Ship Detection Based on Dynamic Fusion Model of Multi-feature and Support Vector Machine , 2011, 2011 Sixth International Conference on Image and Graphics.

[12]  Weijian Mi,et al.  Ship Identification Algorithm Based on 3D Point Cloud for Automated Ship Loaders , 2015 .

[13]  Lei Xie,et al.  A New Method of Inland River Overloaded Ship Identification Using Digital Image Processing , 2013 .

[14]  Pradeep Kumar,et al.  Flaw detection in radiographic weldment images using morphological watershed segmentation technique , 2009 .

[15]  Wang Mei,et al.  SAR Image Target Recognition Based on Hu Invariant Moments and SVM , 2009, 2009 Fifth International Conference on Information Assurance and Security.

[16]  Xiao Han,et al.  Image Denoising Based on Mean Filter and Wavelet Transform , 2015, 2015 4th International Conference on Advanced Information Technology and Sensor Application (AITS).

[17]  Zhiguo Jiang,et al.  Ship detection in optical remote sensing images based on deep convolutional neural networks , 2017 .

[18]  John Reeder,et al.  Convolution neural networks for ship type recognition , 2016, SPIE Defense + Security.

[19]  Vipin Tyagi,et al.  An adaptive edge-preserving image denoising technique using patch-based weighted-SVD filtering in wavelet domain , 2015, Multimedia Tools and Applications.

[20]  Hsi-Jian Lee,et al.  Multi-frame ship detection and tracking in an infrared image sequence , 1990, Pattern Recognit..

[21]  Firas Mahmood Mustafa,et al.  A New Approach of Image Denoising Based on Discrete Wavelet Transform , 2016, 2016 World Symposium on Computer Applications & Research (WSCAR).

[22]  Hanung Adi Nugroho,et al.  Zemike moment feature extraction for classifying lesion's shape of breast ultrasound images , 2015, 2015 7th International Conference on Information Technology and Electrical Engineering (ICITEE).