Image Target Detection Based on Deep Convolutional Neural Network

2019 International Conference on Communications, Information System and Computer Engineering (CISCE)（2019）

引用 3|浏览0

暂无评分

摘要

Aiming at the problem of poor foreground extraction in dynamic background images, an image foreground target detection method based on deep convolutional neural network is proposed. The VGG16-NET-based network model is used to extract the feature map. Using the deconvolution method and the pyramid pooling method ameliorates the defect that VGG16-Net can only classify the entire image, and the model can only receive fixed-size images.

查看译文

关键词

component,foreground detection,convolutional neural network,deconvolution,Pyramid pooling

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要