Container Damage Identification Based on RP-FCN

In this paper, a new upsampling algorithm is proposed to Fusion Upsampling, and a new RP-FCN network is presented based on ResNeXt50, Pyramid Pooling, Fusion Upsampling and FCN framework. The information perception system, operation control system and dispatching command system of the fully automated wharf are gradually perfected, but the automatic inspection module of the container has not been built yet. In this paper, the RP-FCN network is applied to the identification of container damage in port, in order to add a luster to the increasingly perfect fully automated terminal system. The experiment shows that the effect of the Fusion Upsampling is better than the traditional bilinear interpolation and deconvolution, and the effect of RP-FCN is better than that of FCN.

[1]  Kwang-Baek Kim,et al.  An Intelligent System for Container Image Recognition Using ART2-Based Self-organizing Supervised Learning Algorithm , 2006, SEAL.

[2]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  P. S. Rao,et al.  Vibration Based Damage Identification Method for Cantilever Beam Using Artificial Neural Network , 2017 .

[4]  Nikhil Ketkar,et al.  Convolutional Neural Networks , 2021, Deep Learning with Python.

[5]  Dong Liu,et al.  Improving triplet-wise training of convolutional neural network for vehicle re-identification , 2017, 2017 IEEE International Conference on Multimedia and Expo (ICME).

[6]  Jianming Guo,et al.  MSER and Connected Domain Analysis Based Algorithm for Container Code Locating Process , 2017, 2017 International Conference on Industrial Informatics - Computing Technology, Intelligent Technology, Industrial Information Integration (ICIICII).

[7]  Graham W. Taylor,et al.  Adaptive deconvolutional networks for mid and high level feature learning , 2011, 2011 International Conference on Computer Vision.

[8]  Zhuowen Tu,et al.  Aggregated Residual Transformations for Deep Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Verma Ankit,et al.  Automatic Container Code Recognition via Spatial Transformer Networks and Connected Component Region Proposals , 2016 .

[10]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Shih-Fu Chang,et al.  CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Gyogwon Koo,et al.  End-to-end recognition of slab identification numbers using a deep convolutional neural network , 2017, Knowl. Based Syst..

[13]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.