Page 101 - 2025年第56卷第10期

51-53.
［ 22］ JIANG H Q，LIU C Q，WANG E L，et al. Numerical modelling of thermal stability for a water retaining wall in per⁃
.
mafrost regions［J］ Thermal Science and Engineering Progress，2022 （36）：101494.
.
［ 23］ 查安秦 . 基于图像处理的车牌识别系统设计［J］ 时代汽车，2023（23）：115-117.
［ 24］ 沈同平，王元茂，方芳，等 . 基于灰度形态学的图像边缘特征提取算法研究［J］ 兰州文理学院学报 （自然科
.
学版），2018，32（2）：58-61.
［ 25］ 周威，刘辉，曾伟高 . 基于顶帽变换的指节纹和掌纹识别改进算法［J］ 传感器与微系统，2019，38（3）：
.
127-130.
［ 26］ YAGAN A C， ÖZGEN M T. Spectral graph based vertex-frequency wiener filtering for image and graph signal
.
denoising ［J］ IEEE Transactions on Signal and Information Processing Over Networks，2020（6）：226-240.
.
［ 27］ 李东洁，郭帅，杨柳 . 基于改进图像阈值分割算法的纱线疵点检测［J］ 纺织学报，2021，42（3）：82-88
［ 28］ XIAO L Y，OUYANG H L，FAN C D. Otsu’ Thresholding method based on plane intercept histogram and geomet⁃
s
.
ric analysis ［J］ The International Arab Journal of Information Technology，2020（17）：692-701.
［ 29］ 罗钧，刘建强，庞亚男 . 基于邻域搜索 JADE 的二维 Otsu 多阈值图像分割［J］ 系统工程与电子技术，2020，
.
42（10）：2164-2171.
［ 30］ BHANDARI A K， CHOSH A， KUMAR I V. A local contrast fusion based 3D Otsu algorithm for multilevel image
.
segmentation［J］ IEEE/CAA Journal of Automatica Sinica，2020，7（1）：200-213.
［ 31］ 王睿，漆泰岳，胡棠，等 . 隧道衬砌裂缝检测中的背景处理和断点连接算法［J］ 应用基础与工程科学学报，
.
2017，25（4）：742-750.

Application of artificial intelligence algorithm in analysis of flowing ice
distribution density in Heilong River

1，2
1
1，2
1，2
1，2

WANG Enliang ，WU Chenyu ，JIANG Haiqiang ，LIU Xingchao ，HAN Hongwei ，ZHOU Tengfei 1

（1. School of Water Conservancy and Civil Engineering，Northeast Agricultural University，Harbin 150030，China；

2. Heilongjiang Provincial Key Laboratory of Water Resource and Water Conservancy Engineering in Cold Region，Harbin 150030，China）

Abstract：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 ana⁃

lyzing 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.

Keywords：ice distribution density；OTSU algorithm；correction algorithm；gray threshold；top-hat transformation

algorithm
（责任编辑：韩 昆）
— 1348 —