• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of visual communication & image representation >Novel shrinking residual convolutional neural network for efficient accurate stereo matching
【24h】

Novel shrinking residual convolutional neural network for efficient accurate stereo matching

机译：新型缩小残余卷积神经网络，以实现高效准确立体声匹配

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

For stereo matching based on patch comparing using convolutional neural networks (CNNs), the matching cost estimation is highly dependent on the network structure, and the patch comparing is time consuming for traditional CNNs. Accordingly, we propose a stereo matching method based on a novel shrinking residual CNN, which consists of convolutional layers and skip-connection layers, and the size of the fully connected layers decreases progressively. Firstly, a layer-by-layer shrinking size model is adopted for the full-connection layers to greatly increase the running speed. Secondly, the convolutional layer and the residual structure are fused to improve patch comparing. Finally, the Loss function is re-designed to give higher weights to hard-classified examples compared with the standard cross entropy loss. Experimental results on KITTI2012 and KITTI2015 demonstrate that the proposed method can improve the operation speed while maintaining high accuracy.
机译：对于基于补丁使用卷积神经网络（CNNS）进行比较的立体声匹配，匹配成本估计高度依赖于网络结构，并且贴片比较是传统CNN的耗时。因此，我们提出了一种基于新型收缩残余CNN的立体声匹配方法，该方法由卷积层和跳过连接层组成，并且完全连接层的尺寸逐渐减小。首先，采用了逐层收缩尺寸模型，用于全连接层，从而大大增加运行速度。其次，卷积层和残余结构融合以改善贴片比较。最后，与标准交叉熵损耗相比，重新设计损耗函数以使更高的重量分类为硬分类示例。 Kitti2012和Kitti2015上的实验结果表明，该方法可以在保持高精度的同时提高操作速度。

著录项

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