The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Semasa pengesanan sasaran maritim, kegelisahan kamera bawaan kapal biasanya menyebabkan ketidakstabilan video dan pengesanan sasaran yang salah atau terlepas. Bertujuan untuk menangani masalah ini, satu algoritma baru untuk pengesanan sasaran maritim berdasarkan teknologi penstabilan imej elektronik dicadangkan dalam kajian ini. Algoritma terutamanya merangkumi tiga model, iaitu model garis titik (PLM), model klasifikasi titik (PCM), dan model klasifikasi imej (ICM). Titik ciri (FP) mula-mula dikelaskan oleh PLM, dan video stabil serta kontur sasaran diperoleh oleh PCM. Kemudian segi empat tepat sempadan terkecil bagi kontur sasaran yang dihasilkan sebagai kotak sempadan calon (bboxes) dihantar ke ICM untuk pengelasan. Dalam eksperimen, ICM, yang dibina berdasarkan rangkaian neural convolutional (CNN), dilatih dan keberkesanannya disahkan. Keputusan eksperimen kami menunjukkan bahawa algoritma yang dicadangkan mengatasi model penanda aras dalam semua metrik biasa termasuk ralat min kuasa dua (MSE), nisbah isyarat puncak kepada hingar (PSNR), indeks kesamaan struktur (SSIM), dan purata ketepatan purata (mAP) dengan sekurang-kurangnya -47.87%, 8.66%, 6.94%, dan 5.75%, masing-masing. Algoritma yang dicadangkan adalah lebih baik daripada teknik terkini dalam kedua-dua penstabilan imej dan pengesanan kapal sasaran, yang menyediakan sokongan teknikal yang boleh dipercayai untuk pembangunan visual kapal tanpa pemandu.
Xiongfei SHAN
Dalian Maritime University
Mingyang PAN
Dalian Maritime University
Depeng ZHAO
Dalian Maritime University
Deqiang WANG
Dalian Maritime University
Feng-Jang HWANG
Transport Research Centre, University of Technology Sydney
Chi-Hua CHEN
Fuzhou University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Xiongfei SHAN, Mingyang PAN, Depeng ZHAO, Deqiang WANG, Feng-Jang HWANG, Chi-Hua CHEN, "Maritime Target Detection Based on Electronic Image Stabilization Technology of Shipborne Camera" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 7, pp. 948-960, July 2021, doi: 10.1587/transinf.2020EDP7192.
Abstract: During the detection of maritime targets, the jitter of the shipborne camera usually causes the video instability and the false or missed detection of targets. Aimed at tackling this problem, a novel algorithm for maritime target detection based on the electronic image stabilization technology is proposed in this study. The algorithm mainly includes three models, namely the points line model (PLM), the points classification model (PCM), and the image classification model (ICM). The feature points (FPs) are firstly classified by the PLM, and stable videos as well as target contours are obtained by the PCM. Then the smallest bounding rectangles of the target contours generated as the candidate bounding boxes (bboxes) are sent to the ICM for classification. In the experiments, the ICM, which is constructed based on the convolutional neural network (CNN), is trained and its effectiveness is verified. Our experimental results demonstrate that the proposed algorithm outperformed the benchmark models in all the common metrics including the mean square error (MSE), peak signal to noise ratio (PSNR), structural similarity index (SSIM), and mean average precision (mAP) by at least -47.87%, 8.66%, 6.94%, and 5.75%, respectively. The proposed algorithm is superior to the state-of-the-art techniques in both the image stabilization and target ship detection, which provides reliable technical support for the visual development of unmanned ships.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDP7192/_p
Salinan
@ARTICLE{e104-d_7_948,
author={Xiongfei SHAN, Mingyang PAN, Depeng ZHAO, Deqiang WANG, Feng-Jang HWANG, Chi-Hua CHEN, },
journal={IEICE TRANSACTIONS on Information},
title={Maritime Target Detection Based on Electronic Image Stabilization Technology of Shipborne Camera},
year={2021},
volume={E104-D},
number={7},
pages={948-960},
abstract={During the detection of maritime targets, the jitter of the shipborne camera usually causes the video instability and the false or missed detection of targets. Aimed at tackling this problem, a novel algorithm for maritime target detection based on the electronic image stabilization technology is proposed in this study. The algorithm mainly includes three models, namely the points line model (PLM), the points classification model (PCM), and the image classification model (ICM). The feature points (FPs) are firstly classified by the PLM, and stable videos as well as target contours are obtained by the PCM. Then the smallest bounding rectangles of the target contours generated as the candidate bounding boxes (bboxes) are sent to the ICM for classification. In the experiments, the ICM, which is constructed based on the convolutional neural network (CNN), is trained and its effectiveness is verified. Our experimental results demonstrate that the proposed algorithm outperformed the benchmark models in all the common metrics including the mean square error (MSE), peak signal to noise ratio (PSNR), structural similarity index (SSIM), and mean average precision (mAP) by at least -47.87%, 8.66%, 6.94%, and 5.75%, respectively. The proposed algorithm is superior to the state-of-the-art techniques in both the image stabilization and target ship detection, which provides reliable technical support for the visual development of unmanned ships.},
keywords={},
doi={10.1587/transinf.2020EDP7192},
ISSN={1745-1361},
month={July},}
Salinan
TY - JOUR
TI - Maritime Target Detection Based on Electronic Image Stabilization Technology of Shipborne Camera
T2 - IEICE TRANSACTIONS on Information
SP - 948
EP - 960
AU - Xiongfei SHAN
AU - Mingyang PAN
AU - Depeng ZHAO
AU - Deqiang WANG
AU - Feng-Jang HWANG
AU - Chi-Hua CHEN
PY - 2021
DO - 10.1587/transinf.2020EDP7192
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2021
AB - During the detection of maritime targets, the jitter of the shipborne camera usually causes the video instability and the false or missed detection of targets. Aimed at tackling this problem, a novel algorithm for maritime target detection based on the electronic image stabilization technology is proposed in this study. The algorithm mainly includes three models, namely the points line model (PLM), the points classification model (PCM), and the image classification model (ICM). The feature points (FPs) are firstly classified by the PLM, and stable videos as well as target contours are obtained by the PCM. Then the smallest bounding rectangles of the target contours generated as the candidate bounding boxes (bboxes) are sent to the ICM for classification. In the experiments, the ICM, which is constructed based on the convolutional neural network (CNN), is trained and its effectiveness is verified. Our experimental results demonstrate that the proposed algorithm outperformed the benchmark models in all the common metrics including the mean square error (MSE), peak signal to noise ratio (PSNR), structural similarity index (SSIM), and mean average precision (mAP) by at least -47.87%, 8.66%, 6.94%, and 5.75%, respectively. The proposed algorithm is superior to the state-of-the-art techniques in both the image stabilization and target ship detection, which provides reliable technical support for the visual development of unmanned ships.
ER -