计算机工程与应用 ›› 2019, Vol. 55 ›› Issue (24): 91-95.DOI: 10.3778/j.issn.1002-8331.1904-0155

• 模式识别与人工智能 • 上一篇    下一篇

空洞卷积的多尺度语义分割网络

曲长波,姜思瑶,吴德阳   

  1. 1.辽宁工程技术大学,辽宁 葫芦岛 125105
    2.燕山大学,河北 秦皇岛 066004
  • 出版日期:2019-12-15 发布日期:2019-12-11

Multiscale Semantic Segmentation Network Based on Cavity Convolution

QU Changbo, JIANG Siyao, WU Deyang   

  1. 1.Liaoning Technical University, Huludao, Liaoning 125105, China
    2.Yanshan University, Qinhuangdao, Hebei 066004, China
  • Online:2019-12-15 Published:2019-12-11

摘要: 计算机硬件的发展极大程度地促进了计算机视觉的发展,卷积神经网络在语义分割中取得了令人瞩目的成就,但多卷积层叠加难免造成图像中目标边界信息的丢失。为了尽可能保留边界信息,提高图像分割精度,提出一种多尺度空洞卷积神经网络模型。该模型利用多尺度池化适应图像中不同尺度目标,并利用空洞卷积学习目标特征,在更加准确识别目标的同时,提高目标边界的识别精度,在ISPRS Vaihingen数据集上的实验结果表明,提出的多尺度空洞卷积神经网络对于目标边界的拟合结果较为理想。

关键词: 深度学习, 语义分割, 空洞卷积, 多尺度

Abstract: The development of computer hardware has greatly promoted the development of computer vision. Convolution neural network has made remarkable achievements in semantic segmentation. However, the stacking  of multiple convolutional layers inevitably result in the loss of detailed information in the boundary of objects. In order to preserve boundary information as far as possible and improve the accuracy of image segmentation, a multiscale atrous convolution neural network model is proposed. The proposed model utilizes multiscale pooling to adapt to different scale targets in images. Besides, atrous convolution layer is used to learn target features, thus the accuracy of detailed information is improved, better segmentation results are obtained. Experimental results on the ISPRS Vaihingen dataset show that the proposed multiscale atrous convolution neural network is effective for target boundary fitting.

Key words: deep learning, semantic segmentation, cavity convolution, multiscale