TY - GEN
T1 - Optimization of ship target detection algorithm based on random forest and regional convolutional network
AU - Han, Zhong
AU - Ma, Long
AU - Chen, He
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - Target detection can assist in detecting the position of the target ship, which is an important part of the intelligent ship visual aid system. With the development and perfection of deep learning, the convolutional neural network technology has been continuously optimized. And it can automatically learn and extract features of objects in images, providing stronger distinguishing power and representation ability. In this paper, various optimization algorithms of convolutional neural networks are compared. Aiming at the problem of unbalanced ship targets in remote sensing images of near-port areas, a ship target detection algorithm based on random forest and Faster-RCNN is proposed. The random forest algorithm is used for model optimization due to its insensitivity to multi-collinearity. The positive effect of the optimized algorithm on accuracy is verified through experiments.
AB - Target detection can assist in detecting the position of the target ship, which is an important part of the intelligent ship visual aid system. With the development and perfection of deep learning, the convolutional neural network technology has been continuously optimized. And it can automatically learn and extract features of objects in images, providing stronger distinguishing power and representation ability. In this paper, various optimization algorithms of convolutional neural networks are compared. Aiming at the problem of unbalanced ship targets in remote sensing images of near-port areas, a ship target detection algorithm based on random forest and Faster-RCNN is proposed. The random forest algorithm is used for model optimization due to its insensitivity to multi-collinearity. The positive effect of the optimized algorithm on accuracy is verified through experiments.
KW - Deep learning
KW - Random forest
KW - Regional convolutional network
KW - Ship target detection algorithm
UR - http://www.scopus.com/inward/record.url?scp=85081169693&partnerID=8YFLogxK
U2 - 10.1109/EEI48997.2019.00088
DO - 10.1109/EEI48997.2019.00088
M3 - Conference contribution
AN - SCOPUS:85081169693
T3 - Proceedings - 2019 International Conference on Electronic Engineering and Informatics, EEI 2019
SP - 375
EP - 382
BT - Proceedings - 2019 International Conference on Electronic Engineering and Informatics, EEI 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 International Conference on Electronic Engineering and Informatics, EEI 2019
Y2 - 8 November 2019 through 10 November 2019
ER -