| 汪恩良,吴晨宇,姜海强,刘兴超,韩红卫,周腾飞.人工智能算法在黑龙江流凌分布密度分析中的应用[J].水利学报,2025,56(10):1338-1348 |
| 人工智能算法在黑龙江流凌分布密度分析中的应用 |
| Application of artificial intelligence algorithm in analysis of flowing ice distribution density in Heilong River |
| 投稿时间:2024-05-30 修订日期:2025-09-17 |
| DOI:10.13243/j.cnki.slxb.20240322 |
| 中文关键词: 流凌分布密度 OTSU算法 校正算法 灰度阈值 顶帽变换算法 |
| 英文关键词: ice distribution density OTSU algorithm correction algorithm gray threshold top-hat transformation algorithm |
| 基金项目:水利部重大科技项目(SKS-2022017);黑龙江省自然科学基金联合引导项目(LH2023D001) |
| 作者 | 单位 | E-mail | | 汪恩良 | 东北农业大学 水利与土木工程学院, 黑龙江 哈尔滨 150030 黑龙江省寒区水资源与水利工程重点实验室, 黑龙江 哈尔滨 150030 | | | 吴晨宇 | 东北农业大学 水利与土木工程学院, 黑龙江 哈尔滨 150030 | | | 姜海强 | 东北农业大学 水利与土木工程学院, 黑龙江 哈尔滨 150030 黑龙江省寒区水资源与水利工程重点实验室, 黑龙江 哈尔滨 150030 | hqjiang@neau.edu.cn | | 刘兴超 | 东北农业大学 水利与土木工程学院, 黑龙江 哈尔滨 150030 黑龙江省寒区水资源与水利工程重点实验室, 黑龙江 哈尔滨 150030 | | | 韩红卫 | 东北农业大学 水利与土木工程学院, 黑龙江 哈尔滨 150030 黑龙江省寒区水资源与水利工程重点实验室, 黑龙江 哈尔滨 150030 | | | 周腾飞 | 东北农业大学 水利与土木工程学院, 黑龙江 哈尔滨 150030 | |
|
| 摘要点击次数: 45 |
| 全文下载次数: 42 |
| 中文摘要: |
| 春季北方江河的解冻期易发生流凌灾害。为了从河面监测图像中获得精确、连续的流凌分布密度信息,基于无人机所获流凌图像,对畸变较大的岸基倾斜摄影数据进行校正,然后对图像进行灰度化处理,并通过顶帽算法与维纳滤波使图像亮度均衡化,再选用最优的OTSU阈值分割算法实现了图片的二值化,最后提取出流凌分布密度信息,通过分析流凌分布密度随时间变化的折线图来验证图像校正后的效果。结果表明,通过校正后流凌图像计算得到的流凌分布密度要比通过原倾斜摄像所得结果更准确,精度最高提升10倍,证明了OTSU算法具有准确、高效的特点,可为流凌分布密度的连续监测分析提供新途径。 |
| 英文摘要: |
| In spring,the northern rivers are prone to flood disasters during the thawing period. To obtain accurate and continuous information on ice distribution density from river flow monitoring images,the highly distorted images taken at an oblique angle from the riverbank are corrected based on ice flow images obtained by Unmanned Aerial Vehicles. The image is then processed in grayscale,and its brightness is equalized using the Top-hat algorithm and Wiener filter,and the optimal OTSU threshold segmentation algorithm is applied to achieve the image binarization. Finally,the information on ice distribution density is extracted,and the effect of image correction is verified by analyzing the changes in process of ice distribution density over time. The results indicate that the ice distribution density calculated using the corrected ice images is more accurate than that of the original oblique image,with an accuracy improvement of up to 10 times. It also proves that the OTSU algorithm possesses the characteristics of accuracy and efficiency,providing a new approach for the continuous monitoring method of ice distribution density. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |