###
计算机系统应用:2019,28(1):239-244
本文二维码信息
码上扫一扫!
基于NVIDIA Jetson TX2的道路场景分割
(四川大学 电子信息学院, 成都 610065)
Road Scene Segmentation Based on NVIDIA Jetson TX2
(College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 164次   下载 105
投稿时间:2018-07-17    修订日期:2018-08-09
中文摘要: 图像语义分割是计算机视觉领域重要研究方向之一,其中基于深度学习的语义分割相较于传统分割算法更为高效可靠,可应用于交通监控、自动驾驶等领域的场景理解阶段.但复杂的分割网络在嵌入式平台上的推理速度较低,难以进行实际应用.因此针对交通监控、无人驾驶等应用背景,在嵌入式平台NVIDIA Jetson TX2上,采用基于深度卷积编解码器结构的图像分割网络,对道路场景进行语义分割,并基于NVIDIA的推理加速器TensorRT2,完成网络模型简化、网络自定义层添加与CUDA并行优化,实现了对网络推理阶段的加速.实验结果表明,加速引擎在TX2上的推理速度约为原模型的10倍,为复杂分割网络在嵌入式平台上的应用提供了支持.
Abstract:Image semantic segmentation is one of the most important research directions of computer vision. Compared with traditional algorithms, image segmentation based on deep-learning performs better, and can be applied to the scene understanding stage of traffic monitoring and automatic drive. However, the speed of complex segmentation network on embedded platform is too low to be practically applied. Therefore, in view of the application of traffic monitoring and automatic drive, the image segmentation network based on deep convolutional encoder-decoder architecture was used to complete the road scene segmentation on the embedded platform NVIDIA Jetson TX2. Meanwhile, in order to accelerate the network, the model was simplified and transformed to engine based on TensorRT2 provided by NVIDIA, which including plugin layers adding and CUDA parallel optimization. The experimental results show that the speed-up ratio can reach ten, which provides support for the application of the complex structure segmentation network on the embedded platform.
文章编号:     中图分类号:    文献标志码:
基金项目:成都市科技项目(2016-XT00-00015-GX);四川省教育厅科研项目(18ZB0355)
引用文本:
李诗菁,卿粼波,何小海,韩杰.基于NVIDIA Jetson TX2的道路场景分割.计算机系统应用,2019,28(1):239-244
LI Shi-Jing,QING Lin-Bo,HE Xiao-Hai,HAN Jie.Road Scene Segmentation Based on NVIDIA Jetson TX2.COMPUTER SYSTEMS APPLICATIONS,2019,28(1):239-244

用微信扫一扫

用微信扫一扫