TY - GEN
T1 - A novel nearest feature learning classifier for ship target detection in optical remote sensing images
AU - Huang, Bo
AU - Xu, Tingfa
AU - Luo, Yuxin
AU - Chen, Sining
AU - Liu, Bo
AU - Yuan, Bo
N1 - Publisher Copyright:
© Springer Nature Singapore Pte Ltd. 2019.
PY - 2019
Y1 - 2019
N2 - Satellite remote sensing data is becoming more and more abundant, In order to realize automatic detection of ships on the sea surface, this paper presents an adaptive intelligent ship detection method, a novel nearest feature learning classifier (NFLC), which combines the scale invariant feature transform (SIFT) feature extraction with nearest feature learning classification. Due to the wide variety of detection ships, the NFLC can obtain a better experimental result than conventional detection methods. The detection accuracy is enhanced by the feature training in large databases and the performance of the system can be continuously improved through the target learning. In addition, compared to convolutional neural network algorithm, it can save the computation time by using the nearest feature matching. The result shows that almost all of the offshore ships can be detected, and the total detection rate is 89.3% with 1000 experimental optical remote sensing images from Google Earth data.
AB - Satellite remote sensing data is becoming more and more abundant, In order to realize automatic detection of ships on the sea surface, this paper presents an adaptive intelligent ship detection method, a novel nearest feature learning classifier (NFLC), which combines the scale invariant feature transform (SIFT) feature extraction with nearest feature learning classification. Due to the wide variety of detection ships, the NFLC can obtain a better experimental result than conventional detection methods. The detection accuracy is enhanced by the feature training in large databases and the performance of the system can be continuously improved through the target learning. In addition, compared to convolutional neural network algorithm, it can save the computation time by using the nearest feature matching. The result shows that almost all of the offshore ships can be detected, and the total detection rate is 89.3% with 1000 experimental optical remote sensing images from Google Earth data.
KW - Nearest feature learning
KW - Optical remote sensing images
KW - Ship detection
KW - The NFLC
UR - http://www.scopus.com/inward/record.url?scp=85048683052&partnerID=8YFLogxK
U2 - 10.1007/978-981-10-6571-2_73
DO - 10.1007/978-981-10-6571-2_73
M3 - Conference contribution
AN - SCOPUS:85048683052
SN - 9789811065705
T3 - Lecture Notes in Electrical Engineering
SP - 600
EP - 606
BT - Communications, Signal Processing, and Systems - Proceedings of the 2017 International Conference on Communications, Signal Processing, and Systems
A2 - Liang, Qilian
A2 - Jia, Min
A2 - Mu, Jiasong
A2 - Wang, Wei
A2 - Feng, Xuhong
A2 - Zhang, Baoju
PB - Springer Verlag
T2 - 6th International Conference on Communications, Signal Processing, and Systems, CSPS 2017
Y2 - 14 July 2017 through 16 July 2017
ER -