标题:Real-time Semantic Segmentation for Road Scene
作者:Zhang, Xuetao; Chen, Zhenxue; Lu, Dan; Li, Xianming
通讯作者:Chen, ZX;Chen, ZX
作者机构:[Zhang, Xuetao; Chen, Zhenxue; Lu, Dan; Li, Xianming] Shandong Univ, Sch Control Sci & Engn, Jinan, Shandong, Peoples R China.; [Chen, Zhenxue] Shan 更多
会议名称:3rd IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)
会议日期:JUL 18-20, 2018
来源:2018 3RD IEEE INTERNATIONAL CONFERENCE ON ADVANCED ROBOTICS AND MECHATRONICS (IEEE ICARM)
出版年:2018
页码:19-23
关键词:Image segmentation; Residual Network; CNN; Real-time
摘要:Semantic segmentation is challenging for diverse scenes. In this paper, we propose a new model for road complex scene. Our model use encoder-decoder structure with auxiliary loss. Based on ResNet bottleneck block, we proposed dilated bottleneck block and tiny block. These block applied in the encoder and decoder. The dilated bottleneck block enlarges the field-of-view and the tiny block maintains the model as small as possible. We train our model end-to-end from scartch, and the image and segmentation map in network is pixel-to-pixel. With the help of auxiliary loss, our model yields 56.9% mean IoU on CamVid dataset, it is smaller and faster than ENet and SegNet.
收录类别:CPCI-S
资源类型:会议论文
TOP