计算机应用 ›› 2019, Vol. 39 ›› Issue (2): 376-381.DOI: 10.11772/j.issn.1001-9081.2018061372

• 人工智能 • 上一篇    下一篇

基于深度学习的海底观测视频中鱼类的识别方法

张俊龙1, 曾国荪1, 覃如符2,3   

  1. 1. 同济大学 电子与信息工程学院, 上海 200092;
    2. 同济大学 海洋与地球科学学院, 上海 200092;
    3. 海洋地质国家重点实验室(同济大学), 上海 200092
  • 收稿日期:2018-07-02 修回日期:2018-09-05 出版日期:2019-02-10 发布日期:2019-02-15
  • 通讯作者: 曾国荪
  • 作者简介:张俊龙(1994-),男,山东淄博人,硕士研究生,主要研究方向:可信搜索、深度学习;曾国荪(1964-),男,江西吉安人,教授,博士,主要研究方向:智能搜索、可信网络软件、并行分布计算;覃如符(1979-),男,广西柳江人,副教授,博士,主要研究方向:地理信息系统、海洋信息技术、海底观测系统。
  • 基金资助:
    国家社会科学基金资助项目(17BQT086);同济大学实验教改项目(0800104214)。

Fish recognition method for submarine observation video based on deep learning

ZHANG Junlong1, ZENG Guosun1, QIN Rufu2,3   

  1. 1. College of Electronic and Information, Tongji University, Shanghai 200092, China;
    2. School of Ocean and Earth Science, Tongji University, Shanghai 200092, China;
    3. State Key Laboratory of Marine Geology(Tongji University), Tongji University, Shanghai 200092, China
  • Received:2018-07-02 Revised:2018-09-05 Online:2019-02-10 Published:2019-02-15
  • Supported by:
    This work is partially supported by the National Social Science Fundation of China (17BQT086), the Experimental Teaching Reform Project of Tongji University (0800104214).

摘要: 针对海底环境恶劣、海底观测视频品质差导致视频中的海洋鱼类识别难的问题,提出一种基于深度学习的海洋鱼类识别方法。首先,将海底观测视频分解为图片,由于海底观测视频中存在较大比例的空白数据,使用背景差分法过滤不包含鱼类的图片,缩短处理全部数据的时间;然后,考虑到海底拍摄环境亮度低、场景模糊的实际情况,对图片基于暗通道先验算法进行预处理提高品质;最后,以卷积神经网络(CNN)为基础构建深度学习模型,并且提出了权重化特征的卷积过程,提高模型的鲁棒性。实验结果表明:面对较差品质的海底观测视频图片,在深度学习模型结构相同的条件下,与普通卷积神经网络模型相比,使用权重化卷积作为隐层并且加入预处理过程后,对海洋鱼类识别准确率的提升幅度达到23%,有助于实现对海底观测视频图片中海洋鱼类的精准识别。

关键词: 海底观测, 视频图片, 图片品质, 深度学习, 鱼类识别

Abstract: As it is hard to recognize marine fishes occurred in submarine observation videos due to the bad undersea environment and low quality of the video, a recognition method based on deep learning was proposed. Firstly, the video was split into pictures, and as this type of video contains a large proportion of useless data, a background subtraction algorithm was used to filter the pictures without fish to save the time of processing all data. Then, considering the undersea environment is blurring with low bright, based on the dark channel prior algorithm, the pictures were preprocessed to improve their quality before recognition. Finally, a recognition deep learning model based on Convolutional Neural Network (CNN) was consructed with weighted convolution process to improve the robustness of the model. The experimental results show that, facing submarine observation video frames with poor quality, compared with traditional CNN, the method with preprocessing and weighted convolution as hidden layer can increase the recognition accuracy by 23%, contributing to the recognition of marine fishes in submarine observation video.

Key words: submarine observation, video picture, picture quality, deep learning, fish recognition

中图分类号: