ABSTRACT
In this paper, we design a new approach which combines the Gabor filter with the principle of selective search algorithm applied in Fast RCNN to extract and enhance the texture of the satellite image, to solve the problems of low detection precision, high probability of missed detection and error detection of ships in satellite images. Experiments show that the texture enhancement method based on Gabor filter fits the principle of selective search algorithm, which increases the number of positive samples in region proposal. The mAP of ship detection in satellite images reached 75.21%. And the detection accuracy of moving ships increased by 10%.
- S S Li, J B An, C G Li, J Meng (2018). A Method of Motion Ship Detection Based on Background Difference and Visual Significance[J]. Internet of Things Technology, 8(01), 17--20. (in Chinses) Conference Name: ACM Woodstock conference.Google Scholar
- C Liu (2014). Research on motion ship detection technology based on infrared image[D]. Wuhan University of Technology. (in Chinses)Google Scholar
- Z Y Qiu (2015). Algorithm and implementation of hull size video detection based on motion trajectory [D]. Nanjing University. (in Chinses)Google Scholar
- C K Zhu (2014). Research on Tracking and Counting of Sports Ships Based on OpenCV[D]. Wuhan University of Technology. (in Chinses)Google Scholar
- Y Q Wang, L Ma, Y Tian (2011). Summary of Ship Target Detection and Recognition Based on Optical Remote Sensing Images[J]. Acta Automatica Sinica, 37(09), 1029--1039. (in Chinses)Google Scholar
- J C Ren (2000). Research on the wave velocity field of ship[D]. Fudan University. (in Chinses)Google Scholar
- R Girshick, et al. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. in IEEE Conference on Computer Vision and Pattern Recognition, 580--587.Google ScholarDigital Library
- R Girshick (2015). Fast R-CNN, in IEEE International Conference on Computer Vision. 1440--1448.Google ScholarDigital Library
- W F Mi (2017). Research on target detection and recognition technology of surface ship based on satellite remote sensing image[D]. Harbin Engineering University. (in Chinses)Google Scholar
- T F Wang (2017). Research on high-resolution remote sensing image depth learning ship detection technology [D]. Harbin Institute of Technology. (in Chinses)Google Scholar
- J Huang, Z G Jiang, H P Zhang, Y Yuan (2017). Ship Target Detection Based on Convolutional Neural Network for Remote Sensing Images[J]. Journal of Beijing University of Aeronautics and Astronautics, 43(09), 1841--1848. (in Chinses)Google Scholar
- G Hu, et al. (2018). Aircraft detection in remote sensing images based on saliency and convolution neural network. EURASIP Journal on Wireless Communications and Networking, 26.Google Scholar
- X Wang, A Shrivastava, A Gupta (2017). A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection. in IEEE Conference on Computer Vision and Pattern Recognition, 3039--3048.Google ScholarCross Ref
- S Ren, K He, R Girshick, et al.(2015). Faster R-CNN: towards real-time object detection with region proposal networks[C]. International Conference on Neural Information Processing Systems.Google Scholar
- Y Ge, S L Jiang, F M Ye, Q G Xu, Y L Tang (2016). Remote Sensing Image Retrieval of Visual Word Bag and Gabor Texture Fusion[J]. Opto-Electronic Engineering, 43(02), 76--88. (in Chinses)Google Scholar
- X Pu (2011). Extraction of palmprint texture features based on Gabor filter[J]. Science and Technology Innovation Review, 03, 24--26. (in Chinses)Google Scholar
- R Kong, B Zhang (2012). Parameter setting of Gabor filter[J]. Control and Decision, 27(08), 1277--1280. (in Chinses)Google Scholar
- Y N Zhao, J Y Yang, X Q Meng (2006). A Practical Parameter Setting Method for Gabor Filter Banks[J]. Computer Engineering, 19, 173--175. (in Chinses)Google Scholar
Index Terms
- Ship Detection Method Based on Gabor Filter and Fast RCNN Model in Satellite Images of Sea
Recommendations
Ship Detection Using Texture Statistics from Optical Satellite Images
DICTA '11: Proceedings of the 2011 International Conference on Digital Image Computing: Techniques and ApplicationsThis paper presents a method for ship detection using texture statistics from optical satellite images. The proposed method focuses on the extraction of ship candidates. First, a structural texture descriptor derived from local multiple patterns is ...
Face recognition with local gabor textons
ICB'07: Proceedings of the 2007 international conference on Advances in BiometricsThis paper proposes a novel face representation and recognition method based on local Gabor textons. Textons, defined as a vocabulary of local characteristic features, are a good description of the perceptually distinguishable micro-structures on ...
YOLOv7-ship: An Efficient Method for Marine Ship Detection Based on Wave Glider
ICCPR '23: Proceedings of the 2023 12th International Conference on Computing and Pattern RecognitionShip detection based on wave gliders plays an important role in tasks such as maritime patrols, target tracking, and maritime traffic control. However, the complex and diverse sea environment, as well as the large differences in the appearance and scale ...
Comments