摘要
针对水下视频质量不高、视频模糊不清甚至很难辨认的问题,利用计算机视觉技术对水下鱼类目标进行快速目标检测,提出了一种基于背景去除的水下视频目标检测方法。设计适合水下环境的鱼类目标检测框架,使用偏最小二乘(PLS)分类器进行目标检测。利用水下拍摄的鱼类数据集收集输入的视频序列,并提取单独的帧。将帧的RGB格式转换为HSI格式并进行中值滤波器去噪的预处理,利用GMG背景去除过程,提取了基于局部二值模式(LBP)纹理和灰度系数的重要特征,最后将所提取的特征,利用PLS分类器,实现了分别对白天及夜晚环境中的水下鱼类目标检测。结果表明,该方法在水下拍摄的鱼类视频数据集目标检测精度可达96.89%,提高了检测效率,降低了人工成本。为水下鱼类等生物资源的监测、保护和可持续开发等工程应用提供了一定的参考价值。
In order to overcome the problems of underwater videos,such as low quality,blurring and even unrecognizability,using the computer vision technology for fast detection of underwater fish targets,an underwater video object detection method was proposed based on background removal methods.An object detection framework for underwater fish was designed,using the partial least squares(PLS)classifier for object detection.Input video sequences were collected from underwater fish data sets,and individual frames were extracted.After the format conversion of RGB to HSI and median filter denoising pretreatment,using the GMG background removal process,the texture and the characteristic of the gray scale coefficient were extracted based on local binary(LBP)pattern.At last,with the above extracted characteristics,the object detection of underwater fish in the daytime and night was realized using the PLS classifier.The results show that the method can achieve the object detection accuracy of 96.89%using the underwater fish video datasets,which improves the detection efficiency of underwater fish and reduces the labor cost.It can also provide some guidance for the monitoring,protection and sustainable development of underwater fish and other biological resources.
作者
张明华
龙腾
宋巍
黄冬梅
梅海彬
覃学标
ZHANG Ming-hua;LONG Teng;SONG Wei;HUANG Dong-mei;MEI Hai-bin;QIN Xue-biao(College of Information Technology,Shanghai Ocean University,Shanghai 201306,China;Shanghai University of Electric Power,Shanghai 200090,China)
出处
《图学学报》
CSCD
北大核心
2021年第1期52-58,共7页
Journal of Graphics
基金
国家自然科学基金面上项目(61972240)
上海市科委能力建设项目(17050501900)
大洋渔业资源可持续开发教育部重点实验室开放基金项目(A1-2006-00-301104)。
关键词
偏最小二乘
背景去除
鱼类
目标检测
动态视觉序列
partial least squares
background removal
fish
object detection
dynamic video sequence
