Research on multi-stream variable resolution compression and transmission technology based on scene elements in Internet of things environment

Shangwu XIAO; Ruimin HU; Yu CHEN; Jing XIAO

doi:10.11959/j.issn.2096-3750.2018.00075

您当前的位置：

首页 >

文章列表页 >

Research on multi-stream variable resolution compression and transmission technology based on scene elements in Internet of things environment

Theory and Technology | 更新时间：2024-06-05

- Research on multi-stream variable resolution compression and transmission technology based on scene elements in Internet of things environment
- Chinese Journal on Internet of Things Vol. 2, Issue 4, Pages: 31-39(2018)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.2096-3750.2018.00075
  CLC： TP37
- Published：30 December 2018，
  
  Published Online：2018-12，
- 稿件说明：
移动端阅览
SHANGWU XIAO, RUIMIN HU, YU CHEN, et al. Research on multi-stream variable resolution compression and transmission technology based on scene elements in Internet of things environment. [J]. Chinese journal on internet of things, 2018, 2(4): 31-39.
DOI：

SHANGWU XIAO, RUIMIN HU, YU CHEN, et al. Research on multi-stream variable resolution compression and transmission technology based on scene elements in Internet of things environment. [J]. Chinese journal on internet of things, 2018, 2(4): 31-39. DOI： 10.11959/j.issn.2096-3750.2018.00075.

摘要

针对城市监控覆盖面广、海量接入的需求，实现低带宽和低功耗性能是解决这一问题的重要研究方向。在智慧城市、安防监控等应用领域，基于场景要素，如人脸关键区域的视频监控尤为重要。实现场景要素的提取，以极低带宽传输关键信息，通过多码流区别编码策略，在物联网环境下实现视频技术的应用，是目前值得研究的可行方向。通过设计面向人脸的变分辨率混合编码算法，可大幅度节省带宽、降低功耗，满足窄带物联网的接入要求。通过基于深度学习Caffe框架的人脸检测算法，在关键帧获取人脸感兴趣区域，并以高分辨率编码人脸图像；通过设计码率自适应分配算法，合理利用带宽，区别编码人脸信息和全图背景内容；通过窄带传输编码后的混合码流信息，在接收端采用基于关键帧的人脸增强解码算法，得到人脸局部的高清监控画面。实验表明，采用所提方法在120~160 kbit/s窄带传输时，人脸画面可以保持与原始高清监控采集端同等清晰度，具有很强的实用性。

Abstract

In response to the demand of wide coverage and massive access

low bandwidth and low power consumption is an important research direction to solve this problem.In smart cities

security monitoring and other application areas

video surveillance based on the region of interest of the face are particularly important.It is a feasible direction to realize the extraction of scene elements

transmission of key information with very low bandwidth and the application of video technology in the Internet of things environment through the strategy of multi-stream differential coding.By designing a face-oriented variable resolution hybrid coding algorithm

the bandwidth could be saved and the power consumption could be reduced greatly

the access requirements of narrowband Internet of things could be met.Through the face detection algorithm based on the deep learning Caffe framework

the face region of interest was acquired in key frames

and the face image was encoded with high resolution.By designing the code rate adaptive allocation algorithm

the bandwidth was utilized rationally

and the encoded face information and the full background content were distinguished.The encoded mixed code stream information was transmitted through the narrowband; the key frame-based face enhancement decoding algorithm was adopted at the receiving end to obtain a partial HD high-definition monitoring picture.Experiments show that when the video encoded by the proposed method is transmitted in a narrow band whose transmission rate is 120~160 kbit/s

the face image can maintain the same definition as the original HD monitoring acquisition end

which has strong practicability.

关键词

NB-IoT监控视频变分辨率视频编码人脸检测

Keywords

NB-IoTsurveillance videovariable resolutionvideo codingface detection

references

LIU Y, LI Z G, SOH Y C . Region-of-interest based resource allocation for conversational video communication of H.264/AVC[J]. IEEE Transactions on Circuits ＆ Systems for Video Technology, 2008,18(1): 134-139.

XU M, DENG X, LI S ,et al. Region-of-interest based conversational HEVC coding with hierarchical perception model of face[J]. IEEE Journal of Selected Topics in Signal Processing, 2014,8(3): 475-489.

ZHANG X, HUANG T, TIAN Y ,et al. Background-modeling-based adaptive prediction for surveillance video coding[J]. IEEE Transactions on Image Processing, 2014,23(2): 769-784.

TSAI T H, LIN C Y . Exploring contextual redundancy in improvingobject-based video coding for video sensor networks surveillance[J]. IEEE Transactions on Multimedia, 2012,14(3): 669-682.

NG K, WU Q, CHAN S ,et al. Object-based coding for plenoptic videos[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2010,20(4): 548-562.

LIAO L, HU R, XIAO J ,et al. An analysis-oriented ROI based coding approach on surveillance video data[C]// Pacific Rim Conference on Multimedia,September 15-16,2016,Xi’an,China. Berlin:Springer, 2016: 428-438.

RANJAN R, CASTILLO C D, CHELLAPPA R . L2-constrained softmax loss for discriminative face verification[J]. ArXiv Preprint, 2017

ZHENG H, JI M, WANG H ,et al. CrossNet:an end-to-end reference-based super resolution network using cross-scale warping[C]// European Conference on Computer Vision. Berlin:Springer, 2018: 87-104.

ZHANG Z, WANG Z, LIN Z ,et al. Reference-conditioned super-resolution by neural texture transfer[J]. ArXiv Preprint, 2018

Views

916

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A NB-IoT access scheme based on Beta distribution

The evolution of NB-IoT standard system and development of Internet of things industry

Analysis of NB-IoT technology character and networking

Related Author

Mengya LI

Zhengquan LI

Yunzhou XIE

Guang-hui ZHANG

Zhen-qiang SUN

Na LU

Related Institution

No data

⁰