基于视频时空特征学习的近岸海浪周期检测

Nearshore Wave Period Detection Based on Video Spatiotemporal Feature Learning

近岸海浪周期检测对于近岸精细化海洋预报至关重要。为此,提出一种新的基于视频时空特征学习的近岸海浪周期自动化检测方法。所提方法以连续海浪视频帧为输入,首先利用二维卷积神经网络(2D-CNN)提取视频帧的空间特征,将空间特征在时间维度上拼接成序列,再通过一维卷积神经网络(1D-CNN)提取时间维度特征,这种复合卷积神经网络(CNN-2D1D)能够实现海浪时空信息的有效融合,最后采用注意力机制对融合后的特征进行权重调整,并将所得结果线性映射为海浪周期。将所提方法与基于VGG16网络的单纯空间特征的检测方法和基于ConvLSTM和三维卷积(C3D)网络的时空特征融合的检测方法进行对比。实验结果表明,C3D和CNN-2D1D的检测精度最高,平均绝对误差分别为0.47 s和0.48 s,但CNN-2D1D比C3D的检测结果更稳定,均方根误差分别为0.66和0.81,且CNN-2D1D需要的训练参数更少,这表明所提方法在波浪周期检测中更有效。

The detection of nearshore wave period is crucial for fine nearshore wave forecast. Thus, we propose a novel method to realize automatic detection of nearshore wave period by learning spatiotemporal features from nearshore wave surveillance videos. The method takes continuous ocean wave video frames as inputs. First, a two-dimensional convolutional neural network(2 D-CNN) is used to extract spatial features of the video frame images, and the extracted spatial features are spliced into sequences in the time dimension. Then a one-dimensional convolutional neural network(1 D-CNN) is used to extract temporal features. The composite convolutional neural network(CNN-2 D1 D) can realize the effective fusion of wave space-time information. Finally, the attention mechanism is used to adjust the weight of the fusion features and linearly maps the fusion features to wave period. The method in this paper is compared with the detection method only extracting spatial features based on VGG16 network and the detection method for spatiotemporal feature fusion based on the ConvLSTM and three-dimensional convolutional(C3 D) network. The results of experiments show that C3 D and CNN-2 D1 D achieve the best detection results, with an average absolute error of 0.47 s and 0.48 s, respectively, but CNN-2 D1 D is more stable than C3 D, with a lower root-mean-square error(0.66) than C3 D(0.81). And CNN-2 D1 D requires fewer training parameters. These results show that the proposed method is more effective in wave period detection.