Moving Target Detection Algorithm on Dynamic Water Surface Based on Sparse Model

A dynamic water surface image is divided into image blocks and they are similar. A sparse model is effective for representing these image blocks. Therefore, a sparse model-based algorithm is proposed for surface moving target detection. In this algorithm, training sample image blocks are collected from a moving target video, and then a dynamic water background dictionary is trained by using KSVD and OMP algorithms based on sparse representation theory. In moving target detection, a frame image is divided into image blocks sequentially and the water surface background is reconstructed by a sparse model. The initial moving target image is calculated. Finally, the initial moving target image is processed without interference. The final moving target image is obtained. Experimental results show that the proposed algorithm is effective in detecting moving targets on the dynamic water surface.

[1]  Matti Pietikäinen,et al.  Deep Learning for Generic Object Detection: A Survey , 2018, International Journal of Computer Vision.

[2]  Lei Zhang,et al.  Towards Human-Machine Cooperation: Self-Supervised Sample Mining for Object Detection , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Stéphane Mallat,et al.  Super-Resolution With Sparse Mixing Estimators , 2010, IEEE Transactions on Image Processing.

[4]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[5]  Kaiyanxie Xie,et al.  A new algorithm for small moving target detection on dynamic water surface , 2019, International Conference on Graphic and Image Processing.

[6]  Yaser Sheikh,et al.  Bayesian modeling of dynamic scenes for object detection , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Junzhou Huang,et al.  Learning with dynamic group sparsity , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[8]  Michael Elad,et al.  Double Sparsity: Learning Sparse Dictionaries for Sparse Signal Approximation , 2010, IEEE Transactions on Signal Processing.

[9]  Xiaogang Wang,et al.  Object Detection from Video Tubelets with Convolutional Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Thomas S. Huang,et al.  Image Super-Resolution Via Sparse Representation , 2010, IEEE Transactions on Image Processing.

[11]  Alan Fern,et al.  Budget-Aware Deep Semantic Video Segmentation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Constance S. Royden,et al.  The effect of monocular depth cues on the detection of moving objects by moving observers , 2016, Vision Research.

[13]  A. Bruckstein,et al.  K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation , 2005 .