...
首页> 外文期刊>Neurocomputing >DeepFish: Accurate underwater live fish recognition with a deep architecture
【24h】

DeepFish: Accurate underwater live fish recognition with a deep architecture

机译:DeepFish:具有深层结构的准确水下活鱼识别

获取原文
获取原文并翻译 | 示例
           

摘要

Underwater object recognition is in great demand, while the research is far from enough. The unrestricted natural environment makes it a challenging task. We propose a framework to recognize fish from videos captured by underwater cameras deployed in the ocean observation network. First, we extract the foreground via sparse and low-rank matrix decomposition. Then, a deep architecture is used to extract features of the foreground fish images. In this architecture, principal component analysis (PCA) is used in two convolutional layers, followed by binary hashing in the non-linear layer and block-wise histograms in the feature pooling layer. Then spatial pyramid pooling (SPP) is used to extract information invariant to large poses. Finally, a linear SVM classifier is used for the classification. This deep network model can be trained efficiently. On a real-world fish recognition dataset, we achieve the state-of-the-art accuracy of 98.64%. (C) 2015 Elsevier B.V. All rights reserved.
机译:水下物体识别的需求量很大,而研究还远远不够。不受限制的自然环境使其成为一项具有挑战性的任务。我们提出了一个框架,用于从海洋观测网络中部署的水下摄像机拍摄的视频中识别鱼。首先,我们通过稀疏和低秩矩阵分解提取前景。然后,使用深度架构来提取前景鱼图像的特征。在这种体系结构中,在两个卷积层中使用主成分分析(PCA),然后在非线性层中使用二进制哈希,在特征池层中使用逐块直方图。然后,使用空间金字塔池(SPP)来提取对于大姿势不变的信息。最后,将线性SVM分类器用于分类。可以有效地训练此深度网络模型。在真实的鱼类识别数据集上,我们达到了98.64%的最新准确性。 (C)2015 Elsevier B.V.保留所有权利。

著录项

  • 来源
    《Neurocomputing》 |2016年第26期|49-58|共10页
  • 作者单位

    Tsinghua Univ, Grad Sch Shenzhen, Shenzhen 518055, Peoples R China|Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China;

    Tsinghua Univ, Grad Sch Shenzhen, Shenzhen 518055, Peoples R China|Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China;

    Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China;

    Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China;

    Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Deep learning; Object recognition; Underwater; Cascaded network;

    机译:深度学习;目标识别;水下;级联网络;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号