Research Article
A Vision Based System Design for Over-Sized Vessel Detecting and Warning Using Convolutional Neural Network
@INPROCEEDINGS{10.1007/978-3-030-77424-0_34, author={Xuan-Kien Dang and Viet-Chinh Nguyen and Trieu-Phong Nguyen and Thi-Duyen-Anh Pham and Cong-Phuong Vo}, title={A Vision Based System Design for Over-Sized Vessel Detecting and Warning Using Convolutional Neural Network}, proceedings={Industrial Networks and Intelligent Systems. 7th EAI International Conference, INISCOM 2021, Hanoi, Vietnam, April 22-23, 2021, Proceedings}, proceedings_a={INISCOM}, year={2021}, month={5}, keywords={Water lock Flood-protecting system Oversized vessel detection Convolutional neural network}, doi={10.1007/978-3-030-77424-0_34} }- Xuan-Kien Dang
Viet-Chinh Nguyen
Trieu-Phong Nguyen
Thi-Duyen-Anh Pham
Cong-Phuong Vo
Year: 2021
A Vision Based System Design for Over-Sized Vessel Detecting and Warning Using Convolutional Neural Network
INISCOM
Springer
DOI: 10.1007/978-3-030-77424-0_34
Abstract
In this work, we aim to investigate the problem of automatically detecting, and warning of an oversize vessel traveling through the Water lock of the flood-holding system. First, the image processing technique based on camera vision using Convolutional Neural Network (CNN), which has the potential to detect the oversize included the length and width of the vessel, is used to help the sailors to prevent this vessel crashed into the Water lock. Second, a model named Oversized Vessel Detector (OVD) was built to detect the vessel in the streaming video and to calculate the size relatively accurately of the vessels based on the proposed math function. Then, the system automatically compares the estimated sizes of the detected vessel and allowable sizes of the flood-protecting system (FPs) to determine the oversize condition, and the result will be displayed on the monitor and warning with alarm devices when decided that the vessel is oversized. Finally, to show the effectiveness and implementation performance of the proposed approach, an experiment is carried out based on Raspberry Pi 4 hardware for coding all the mentioned algorithms.
