| 引用本文: | 曾广淼,俞万能,王荣杰,林安辉.船舶目标重叠下马赛克图像数据增强方法研究[J].控制理论与应用,2022,39(6):1139~1148.[点击复制] |
| ZENG Guang-miao,YU Wan-neng,WANG Rong-jie,LIN An-hui.Research on mosaic image data enhancement and detection method for overlapping ship targets[J].Control Theory and Technology,2022,39(6):1139~1148.[点击复制] |
|
| 船舶目标重叠下马赛克图像数据增强方法研究 |
| Research on mosaic image data enhancement and detection method for overlapping ship targets |
| 摘要点击 1544 全文点击 435 投稿时间：2021-04-21 修订日期：2022-03-26 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/CTA.2021.10329 |
| 2022,39(6):1139-1148 |
| 中文关键词 船舶识别 目标重叠 图像数据增强 Yolov4算法 深度学习 |
| 英文关键词 ship recognition target overlap image data enhancement Yolov4 algorithm deep learning |
| 基金项目 国家自然科学基金项目(51879118, 52171308), 福建省自然科学基金项目(2020J01688), 福建省科技重点项目(2021H0021), 福建省科技拥军项目 (B19101), 交通运输行业高层次技术人才培养项目(2019–014), 集美大学青年拔尖人才项目(ZR2019006)资助. |
|
| 中文摘要 |
| 目标识别中的重叠遮挡问题一直以来是研究的难点, 船舶目标在狭窄水域发生相互遮挡的情况依然存在.
本文提出了一种改进的马赛克数据增强方法, 将训练图片拼接变换成3种不同的尺度, 并按照不同比例输入网络进
行训练, 强化了检测算法对局部特征的学习能力, 在保持测试速度不变的情况下, 提高了对重叠目标的识别准确率,
降低了不同分辨率下识别能力的衰弱速度, 加强了算法的鲁棒性. 基于小型移动测试平台的实测实验证明, 相对于
原始算法, 经过改进后的算法在重叠目标的识别准确率上提高了2.5%, 目标丢失时间减少了17%, 在不同视频分辨
率下的识别稳定性上提高了27.01%. |
| 英文摘要 |
| The problem of overlapping occlusion in target recognition has been a difficult research problem, and the
situation of mutual occlusion of ship targets in narrow waters still exists. In this paper, we proposed an improved mosaic
data enhancement method, which transforms the training image stitching into three different scales and inputs them into
the network for training at different scales to strengthen the learning ability of the detection algorithm for local features.
While keeping the test speed constant, the recognition accuracy of overlapping targets is improved, the rate of decay of
recognition ability at different resolutions is reduced, and the robustness of the algorithm is enhanced. The experiments
based on a small mobile testbed proved that, compared to the original algorithm, the improved algorithm improved the
recognition accuracy of overlapping targets by 2.5%, reduced the target loss time by 17%, and improved the recognition
stability at different video resolutions by 27.01%. |
|
|
|
|
|