Dim small target detection based on convolutinal neural network in star image

The detection of dim target in star image is a challenging task because of the low SNR target and complex background. In this paper, we present a deep learning approach to detecting dim small targets in single-frame star image under uneven background and different kinds of noises. We propose a fully convolutional neural network to achieve pixel-wise classification, which can complete target-background separation in a single stage rapidly. To train this network, we also build a synthetic star image dataset covering various noises and background distribution. The precise annotations of the target regions and centroid positions provided by this dataset make the supervised learning approach possible. Experimental results show that the proposed method outperforms the state-of-the-art in terms of higher detection rate and less false alarm caused by noises.

[1]  Sylvie Buteau,et al.  Image processing technique for automatic detection of satellite streaks , 2007 .

[2]  Rogier A. Windhorst,et al.  REMOVING COSMIC-RAY HITS FROM MULTI-ORBIT HST WIDE FIELD CAMERA IMAGES , 1994 .

[3]  Yansheng Li,et al.  Adaptive top-hat filter based on quantum genetic algorithm for infrared small target detection , 2018, Multimedia Tools and Applications.

[4]  Wei Zhang,et al.  Algorithms for optical weak small targets detection and tracking: review , 2003, International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003.

[5]  Ian D. Reid,et al.  From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Larry S. Davis,et al.  An Analysis of Scale Invariance in Object Detection - SNIP , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Dario Spiller,et al.  A Novel Star Identification Technique Robust to High Presence of False Objects: the Multi-Poles Algorithm , 2017 .

[8]  Charles K. Chui,et al.  A universal noise removal algorithm with an impulse detector , 2005, IEEE Transactions on Image Processing.

[9]  Xinhang Song,et al.  Multi-Scale Multi-Feature Context Modeling for Scene Recognition in the Semantic Manifold , 2017, IEEE Transactions on Image Processing.

[10]  W. Pych.  A Fast Algorithm for Cosmic‐Ray Removal from Single Images , 2003, astro-ph/0311290.

[11]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[12]  Yiquan Wu,et al.  Infrared small target and background separation via column-wise weighted robust principal component analysis , 2016 .

[13]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[14]  Gang Liu,et al.  Infrared aerial small target detection based on digital image processing , 2016, Multimedia Tools and Applications.

[15]  Xiaowei Zhou,et al.  Automatic mitral leaflet tracking in echocardiography by outlier detection in the low-rank representation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  P. Dokkum.  Cosmic-Ray Rejection by Laplacian Edge Detection , 2001, astro-ph/0108003.

[17]  David Dunlap Observatory.  A Fast Algorithm for Cosmic Rays Removal from Single Images , 2003 .

[18]  Yanning Zhang,et al.  Centroid estimation based on MSER detection and Gaussian Mixture Model , 2014, 2014 12th International Conference on Signal Processing (ICSP).

[19]  张艳宁 Zhang Yan-ning,et al.  Detection of small space target based on iterative distance classification and trajectory association , 2012 .

[20]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[21]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[22]  Bir Bhanu,et al.  Automatic Target Recognition: State of the Art Survey , 1986, IEEE Transactions on Aerospace and Electronic Systems.

[23]  Yahong Han,et al.  Understanding the effective receptive field in semantic image segmentation , 2018, Multimedia Tools and Applications.

[24]  Wei Wei,et al.  Dynamic Programming Bipartite Belief Propagation For Hyper Graph Matching , 2017, IJCAI.

[25]  Yanning Zhang,et al.  A Dim Small Target Detection Method Based on Spatial-Frequency Domain Features Space , 2017, ICIG.

[26]  Robert Leitch,et al.  Sapphire: A Small Satellite System for the Surveillance of Space , 2010 .

[27]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[28]  Antonio Criminisi,et al.  TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation , 2006, ECCV.

[29]  Zhongyi Ni,et al.  RETRACTED ARTICLE: Visualized image segmentation for multi-object tracking by weak clustering technique , 2018, Multimedia Tools and Applications.

[30]  Ying Li,et al.  Detecting and tracking dim small targets in infrared image sequences under complex backgrounds , 2012, Multimedia Tools and Applications.

[31]  David B. Cooper,et al.  Accurately Estimating Sherd 3D Surface Geometry with Application to Pot Reconstruction , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[32]  Mario Rj Levesque.  Detection of Artificial Satellites in Images Acquired in Track Rate Mode , 2011 .

[33]  Jianbo Shi,et al.  Semantic Segmentation with Boundary Neural Fields , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Tomasz Maciejewski,et al.  Local neighbourhood extension of SMOTE for mining imbalanced data , 2011, 2011 IEEE Symposium on Computational Intelligence and Data Mining (CIDM).

[35]  Yujie He,et al.  Small infrared target detection based on low-rank and sparse representation , 2015 .

[36]  周军 Zhou Jun,et al.  Centroid location for space targets based on energy accumulation , 2011 .