Real-time Marine Animal Images Classification by Embedded System Based on Mobilenet and Transfer Learning

In marine aquaculture, the classification and identification of marine animals image is one of the important research, which can help monitor the growth and fishing of marine animals, as well as water conditions. Generally, the video and image information of marine animals transmitted by underwater cameras are identified by a human or a computer, which is hardly to do real-time processing. To classify the marine animal images efficiently and in real time, a method combining an embedded system and deep learning based on MobileNetV2 and transfer learning is proposed in this paper. Firstly, the marine animal images are colleced by an underwater robot equipped with an embedded device. Next, a MobileNetV2 model based on convolutional neural network (CNN) is constructed according to the marine animal images, which can ensure the real-time requirement. Thirdly, transfer learning is used to further improve the classification. Then, the model can be trained by the collected marine animal images. Finally, the trained model could be downloaded to the embedded device and real-time classify the marine animal images under water. To evaluate the performance of the proposed method, InceptionV3 and MobilenetV1 models are used for the comparison in the experiments, and the identification accuracy rate and average classification time are calculated. The results show that the MobilenetV2 model plus transfer learning could be a better choice for the real-time classification of the marine animal images than the other two considered models. Furthermore, the size of the MobilenetV2 model is only about 40M and suitable for the embedded device.

[1]  Zongxu Pan,et al.  Transfer Learning with Deep Convolutional Neural Network for SAR Target Classification with Limited Labeled Data , 2017, Remote. Sens..

[2]  Yi-Chao Wu,et al.  Improving handwritten Chinese text recognition using neural network language models and convolutional neural network shape models , 2017, Pattern Recognit..

[3]  A. I. Kukharenko,et al.  Simultaneous classification of several features of a person’s appearance using a deep convolutional neural network , 2015, Pattern Recognition and Image Analysis.

[4]  Lianwen Jin,et al.  A New CNN-Based Method for Multi-Directional Car License Plate Detection , 2018, IEEE Transactions on Intelligent Transportation Systems.

[5]  Haifeng Hu,et al.  Facial expression recognition with FRR-CNN , 2017 .

[6]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[8]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Jie Tian,et al.  Underwater object Images Classification Based on Convolutional Neural Network , 2018, 2018 IEEE 3rd International Conference on Signal and Image Processing (ICSIP).

[10]  Changshui Zhang,et al.  DeepFish: Accurate underwater live fish recognition with a deep architecture , 2016, Neurocomputing.

[11]  Ling Shao,et al.  Transfer Learning for Visual Categorization: A Survey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[12]  Chaur-Chin Chen,et al.  Real-world underwater fish recognition and identification, using sparse representation , 2014, Ecol. Informatics.

[13]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[14]  Nima Tajbakhsh,et al.  Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? , 2016, IEEE Transactions on Medical Imaging.

[15]  Junyu Dong,et al.  Transferring deep knowledge for object recognition in Low-quality underwater videos , 2018, Neurocomputing.

[16]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.