위성영상 내 항공기 식별 시 오탐률 감소를 위한 결합된 CNN 알고리즘
A Coupled CNN Algorithm for the Reduction of False Positive Rate in Detecting Aircraft within Satellite Imagery
0
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
현재 영상 처리에 활발히 사용되고 있는 CNN 알고리즘은 고해상도/대규모 위성사진을 직접 처리하지 못한다. 이 문제를 해결하기 위해, 많은 연구에서 인공 신경망에 다양한 기술을 결합하려고 노력해왔다. 그러나 물체 식별과 검출에 영향을 미치는 여러 가지 요인에 의해 만족스러운 성과를 거두지 못하고 있는 실정이다. 특히 항공기 탐지의 경우 탑승구, 건물, 공항 내 교차로 등 항공기와 유사한 물체를 잘못된 탐지하는 문제가 제대로 해결되지 않았다. 본 논문은 이러한 오탐을 줄이기 위해 Mask R_CNN 알고리즘과 YOLO 알고리즘을 결합한 CNN 알고리즘을 제안한다. 제안된 접근방식의 성과를 평가하기 위해, 항공기와 유사한 물체가 다수 포함된 공항의 위성 영상에 대해 항공기 탐지 실험을 실시하였고, 그 결과 오탐이 상당히 감소함을 확인하였다.
Abstract
CNN algorithms, which are currently actively used for image processing, do not process high resolution/large-scale satellite images directly. To address this problem, many researchers have tried to combine various techniques into the artificial neural networks. However, many studies have not achieved satisfactory performance due to various factors affecting object identification and detection. Especially in the case of aircraft detection, the false detection of objects similar to aircraft, such as boarding gates, buildings, and intersections within the airport, is not solved properly. This paper proposes a coupled CNN algorithm that combines the Mask R_CNN algorithm with the YOLO algorithm to reduce such false detection. To evaluate the performance of the proposed approach, we conduct the aircraft detection test was conducted on satellite images of airports containing a number of objects similar to aircraft.
참고문헌 (33)
- 양성봉, "CNN 알고리즘의 개선을 통한 대형 이미지에서의 객체식별", 한국컴퓨터정보학회논문지, 25(1), pp.45~53 (2020), 한국컴퓨터정보학회[DOI]
- 이진수, "딥러닝 기반 객체 인식 기술 동향", 전자통신동향분석, 33(4), pp.23~32 (2018)
- C. Corbane, "Using SPOT-5 HRG data in panchromatic mode for operational detection of small ships in tropical area", Sensors, 8, pp.2959~2973 (2008)
- C. Yildiz, "Detection of stationary aircrafts from satellite images", Proceedings of the IEEE 19th Signal Processing and Communications Applications Conference (SIU). (2010)
- F. Zhang, "Weakly supervised learning based on coupled convolutional neural networks for aircraft detection", IEEE Transactions on Geoscience and Remote Sensing, 54, pp.5553~5563 (2016)
- G. Liu, "Aircraft recognition in high-resolution satellite images using coarse-to-fine shape prior", IEEE Geoscience and Remote Sensing Letters, 10(3), pp.573~577 (2013)
- G. Wang, "Feature Extraction by Rotation-Invariant Matrix Representation for Object Detection in Aerial Image", IEEE Transactions on Geoscience and Remote Sensing, 14, pp.851~855 (2017)
- H. Wu, "Fast aircraft detection in satellite images based on convolutional neural networks", Proceedings of the IEEE International Conference on Image Processing (ICIP) (2015)
- J. Redmon, "You Only Look Once: Unified, Real-Time Object Detection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)., pp.779~788 (2016)
- J. Redmon, "YOLO9000: Better, Faster, Stronger", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)., pp.6517~6525 (2017)
- J. Redmon, "YOLOv3: An Incremental Improvement", ~ (2018)
- J. R. R. Uijings, "Selective Search for Object Recognition", International Journal of Computer Vision, 104, pp.154~171 (2013)
- J. Tang, "Compressed-domain ship detection on spaceborne optical image using deep neural network and extreme learning machine", IEEE Transactions on Geoscience and Remote Sensing, 53, pp.1174~1185 (2015)
- K. He, "Mask R-CNN", IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(2), pp.386~397 (2020)
- K. He, "Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(9), pp.1904~1916 (2015)
- "YOLOv3: A Huge Improvement — Anand Sonawane —Medium" (2018)[URL]
- M. Peng, "NIRFaceNet: A Convolutional Neural Network for Near-Infrared Face Identification", Information, 7(4), pp.61~ (2016)
- N. R. Harvey, "Ship detection in satellite imagery using rankorder grayscale hit-or-miss transforms", proceedings of SPIE & Visual Information Processing XIX (2010)
- R. Girshick., "Fast R-CNN", Proceedings of the IEEE International Conference on Computer Vision (ICCV). (2015)
- R. Girshick, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)., pp.580~587 (2014)
- S. Ren, "Faster R-CNN: Towards real-time object detection with region proposal networks", IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(6), pp.1137~1149 (2017)
- T. Ophoff, "Vehicle and Vessel Detection on Satellite Imagery: A Comparative Study on Single-Shot Detectors", Remote Sensing, 12(7) (2020)
- "Batch normalization in Neural Networks — Towards Data Science" (2018)[URL]
- U. Kanjir, "Vessel detection and classification from spaceborne optical images: A literature survey", Remote Sensing of Environment, 207(15), pp.1~26 (2018)
- W. Li, "Robust airplane detection in satellite images", Proceedings of the 18th IEEE International Conference on Image Processing (2011)
- W. Liu, "SSD: Single Shot Multibox Detector", In Proceedings of the European Conference on Computer Vision, pp.21~37 (2016), ECCV
- W. Wang, "A novel method of aircraft detection based on high-resolution panchromatic optical remote sensing images", Sensors, 17, pp.1047~ (2017)
- W. Zhang, "Object detection in high-resolution remote sensing images using rotation invariant parts based model", IEEE Geoscience and Remote Sensing Letters, 11(1), pp.74~78 (2014)
- X. Chen, "Aircraft detection by deep belief nets", Proceedings of the 2nd IAPR Asian Conference on Pattern Recognition. (2013)
- X. NIE, "Attention Mask R-CNN for Ship Detection and Segmentation From Remote Sensing Images", IEEE Access, 8, pp.9325~9334 (2020)
- Y. Li, "An aircraft detection boxwork based on reinforcement learning and convolutional neural networks in remote sensing images", Remote Sensing, 10, pp.243~ (2018)
- Y. Tan, "Aircraft detection in highresolution SAR images based on a gradient textural saliency map", Sensors, 15, pp.23071~23094 (2015)
- Y. Xu, "Rapid Airplane Detection in Remote Sensing Images Based on Multilayer Feature Fusion in Fully Convolutional Neural Networks", Sensors, 18 (2018)