摘要
提出了一种低参数量实时图像语义分割网络模型Atrous-squeezeseg。模型在最低参数量为2.1×107时的运算帧率为45.3frame/s,像素点准确度与均交并比分别可达到59.5%与62.9%。同时,嵌入式设备NVIDIA TX2的运算帧率可达8.3frame/s。实验结果表明,相比于其他分割算法,所提模型的速度和参数量均得到了提升。
We propose a real-time image semantic segmentation network model, which is named as Atrous-squeezeseg. Under the condition that the minimum parameter of the model is 2.1×107, the operation frame rate is 45.3 frame/s, and the pixel point accuracy and mean intersection over union can reach 59.5% and 62.9%, respectively. At the same time, in the embedded device NVIDIA TX2, the operate frame rate is up to 8.3 frame/s. The experimental results show that, compared with other segmentation algorithms, the speed and parameter quantity of the proposed model are increased.
作者
谭光鸿
侯进
韩雁鹏
罗朔
Tan Guanghong;Hou Jin;Han Yanpeng;Luo Shuo(School of Information Science and Technology, South west Jiaotong University f Chengdu, Sichuan 611756, China)
出处
《激光与光电子学进展》
CSCD
北大核心
2019年第9期92-100,共9页
Laser & Optoelectronics Progress
基金
浙江大学CAD&CG国家重点实验室开放课题(A1923)
成都市科技项目(2015-HM01-00050-SF)
关键词
图像处理
图像分割
实时图像
低参数量
卷积模块
多尺度特征
image processing
image segmentation
real-time image
low number of parameters
convolution module
multiscale feature