Edge Assisted Real-time Object Detection for Mobile Augmented Reality

Liu, Luyang; Li, Hongyu; Gruteser, Marco

doi:10.1145/3300061.3300116

Cited by 365 publications

(216 citation statements)

References 34 publications

Supporting

Mentioning

215

Contrasting

Order By: Relevance

“…An exception was clustering a subset of images on client devices (machine learning in-device) [41]. Streaming data was analysed and inferred in edge [29,32,34] and in-device [29,34] environments. Models were experimented in in-device environments [28].…”

Section: Discussionmentioning

confidence: 99%

“…One alternative is to offload model computation/inference [27][28][29] to the edge/cloud or partition neural network (NN) computation [29][30][31] to the edge/cloud. Offloading of NN inference to the edge achieved best performance in the context of image recognition in web browsers [27].…”

Section: Related Workmentioning

confidence: 99%

“…Integration of many optimisation approaches (DNN partitioning, pre-processing, offloading, distributed computing) [8] achieved high accuracy object detection with 60 FPS in edge environment [29]. The solution was to encode only interesting parts of the video [Region of Interest (RoI)], utilise parallel streaming and inference pipeling to reduce offloading latency, send only significantly changed frames (adaptive offloading) to the edge, and utilise a fast object tracking method in the mobile device.…”

Section: Related Workmentioning

confidence: 99%

“…Also, new SW processes [25] and platforms [26] have been suggested for facilitating utilisation of ML/AI techniques for the SW/service developers. The utilisation of ML/AI techniques in the edge environment has been studied by focusing mostly on either model training [29,[35][36][37][38][39]41] or inference [27, 28, 30-32, 34, 40] point of view. However, RA design of big data systems utilising ML techniques in the edge environment has not been addressed to the authors' best knowledge, which is the contribution of this paper.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Extending reference architecture of big data systems towards machine learning in edge computing environments

Pääkkönen

Pakkala

2020

J Big Data

View full text Add to dashboard Cite

IntroductionMany big data systems have been developed and realised to provide end user services (Netflix, Facebook, Twitter, LinkedIn etc.). Also, underlying architectures and technologies of the enabling systems have been published [1-3], and RAs have been designed and proposed [4][5][6]. Edge/5G computing is an emerging technological field [7], and the first products are being shipped to the markets. However, the utilisation of machine learning (ML) as part of the edge computing infrastructure is still an area for further research [8]. Particularly, it should be understood, how data is collected, and how models are Abstract Background: Augmented reality, computer vision and other (e.g. network functions, Internet-of-Things (IoT)) use cases can be realised in edge computing environments with machine learning (ML) techniques. For realisation of the use cases, it has to be understood how data is collected, stored, processed, analysed, and visualised in big data systems. In order to provide services with low latency for end users, often utilisation of ML techniques has to be optimized. Also, software/service developers have to understand, how to develop and deploy ML models in edge computing environments. Therefore, architecture design of big data systems to edge computing environments may be challenging. Findings:The contribution of this paper is reference architecture (RA) design of a big data system utilising ML techniques in edge computing environments. An earlier version of the RA has been extended based on 16 realised implementation architectures, which have been developed to edge/distributed computing environments. Also, deployment of architectural elements in different environments is described. Finally, a system view is provided of the software engineering aspects of ML model development and deployment. Conclusions:The presented RA may facilitate concrete architecture design of use cases in edge computing environments. The value of RAs is reduction of development and maintenance costs of systems, reduction of risks, and facilitation of communication between different stakeholders.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Extending reference architecture of big data systems towards machine learning in edge computing environments

Pääkkönen

Pakkala

2020

J Big Data

View full text Add to dashboard Cite

show abstract

“…On the other hand, certain applications, such as cloud gaming and augmented reality, require extremely low latency communication and processing [10]. For instance, augmented reality applications require that objects in live videos are recognized and virtual content is rendered within 100 ms [11]. Finally, automotive applications require very reliable transfer and processing of messages.…”

Section: Introductionmentioning

confidence: 99%

Efficient placement of edge computing devices for vehicular applications in smart cities

Premsankar

Ghaddar

Francesco

et al. 2018

NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium

View full text Add to dashboard Cite

The author of this dissertation contributed to the development of the heuristic algorithms, the implementation of the simulator, the evaluation through simulation, the analysis of results, and writing the article.Publication IV empirically evaluates the impact of edge computing on emerging interactive applications and services. At the time of writing, there was no clear consensus on what specifically constitutes the edge of the network in edge computing. Thus, we first survey the state of the art in edge computing architectures and determine different deployment options for edge devices. Next, we experimentally evaluate edge computing when available at different physical locations and with different virtualization technologies. Specifically, we characterize the end-to-end latency (including

show abstract

Leveraging Edge Computing for Mobile Augmented Reality

Lehman

Tan

2020

Fog/Edge Computing for Security, Privacy, and Applications

View full text Add to dashboard Cite

Edge Assisted Real-time Object Detection for Mobile Augmented Reality

Cited by 365 publications

References 34 publications

Extending reference architecture of big data systems towards machine learning in edge computing environments

Extending reference architecture of big data systems towards machine learning in edge computing environments

Efficient placement of edge computing devices for vehicular applications in smart cities

Leveraging Edge Computing for Mobile Augmented Reality

Contact Info

Product

Resources

About