Please wait a minute...
IET Cyber-Systems and Robotics
IET Cyber-Systems and Robotics  2020, Vol. 2 Issue (4): 190-196    
    
基于神经网络的无人驾驶视觉语义分割模型
Lu Ye; Ting Duan; Jiayi Zhu
Neural network-based semantic segmentation model for robot perception of driverless vision
Lu Ye; Ting Duan; Jiayi Zhu

Lu Ye; Ting Duan; Jiayi Zhu

 全文: PDF 
摘要： 无人驾驶视觉感知是机器人感知的重要应用之一。随着无人驾驶汽车的发展，汽车对周围环境的感知和理解能力变得越来越重要。当周围物体的类型过于复杂时，计算机识别周围环境的能力会变得很差。为了提高计算机的识别精度和分割能力，本研究使用估计的深度信息来辅助语义分割，然后引入物体的边缘特征来增强物体的轮廓。基于以上改进，本文提出了一种基于神经网络的语义分割模型，并在最后使用内在的注意力机制来增加通道间的相关性。在CamVid数据集上的实验结果表明，与其他模型相比，该模型能够获得更好的评价指标，更高的图像分割精度。
Abstract: Driverless vision is one of the important applications of robot perception. With the development of driverless vehicles, the perception and understanding of the surrounding environment are becoming more and more important. When the types of surrounding objects are too complex, the ability of the computer to recognise the environment is poor. To improve the recognition accuracy of the computer and enhance the ability of segmentation, in this study, depth estimation is used to predict depth information to assist semantic segmentation, and then edge features of objects are introduced to enhance the contour of objects. A neural network-based semantic segmentation model is proposed. Finally, the intrinsic mechanism of attention is used to increase the correlation between channels. The experimental results on the CamVid data set show that this model can obtain better evaluation results and improve the segmentation accuracy of images compared with other models.
出版日期: 2021-04-14
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
Lu Ye
Ting Duan
Jiayi Zhu

引用本文:

Lu Ye, Ting Duan, Jiayi Zhu. Neural network-based semantic segmentation model for robot perception of driverless vision. IET Cyber-Systems and Robotics, 2020, 2(4): 190-196.

链接本文:

http://www.zjujournals.com/iet-csr/CN/    或    http://www.zjujournals.com/iet-csr/CN/Y2020/V2/I4/190

No related articles found!