An Edge Computing-based Photo Crowdsourcing Framework for Real-time 3D Reconstruction


The process of image-based three-dimensional (3D) reconstruction takes a collection of photographs and uses them to build a 3D model. This technique has a wide range of potential applications, including augmented reality (AR) and disaster recovery, among others. The majority of the currently available strategies for 3D reconstruction call for a mobile user to walk around the target area and reconstruct objectives with a hand-held camera. This is a laborious and inefficient process. In this paper, we propose a framework for edge computing-based photo crowdsourcing (EC-PCS) in order to meet the requirements of delay-intensive and resource-hungry applications in 5G. The primary goal is to collect a set of representative photographs from pervasive mobile and Internet of Things (IoT) devices at the network edge in order to reconstruct a real-time 3D model while taking into consideration the amount of network resources and the cost in monetary terms. To be more specific, we first suggest a pricing mechanism for photos by jointly taking into consideration their level of freshness, resolution, and data size. Then, we come up with an innovative plan for selecting photos in order to dynamically choose a collection of pictures that have the necessary amount of target coverage at the lowest possible cost. We provide proof that such a problem is NP-hard and then design and implement an effective algorithm that is based on greedy behavior to obtain a solution that is nearly optimal. Additionally, an optimal network resource allocation scheme is presented in order to minimize the maximum uploading delay of the chosen photos to the edge server. This is done by using the scheme to allocate network resources in the best possible way. In the end, a real-time 3D reconstruction algorithm and a 3D model caching scheme are both carried out by the edge server. The extensive experimental results that are based on real-world datasets demonstrate that our EC-PCS system performs significantly better than the other mechanisms that are currently in place.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE :Moiré Photo Restoration Using Multiresolution Convolutional Neural Networks - 2018ABSTRACT:Digital cameras and mobile phones enable us to conveniently record precious moments. Whereas digital image quality is continually
PROJECT TITLE :Lossless Compression of JPEG Coded Photo CollectionsABSTRACT:The explosion of digital photos has posed a important challenge to photo storage and transmission for each personal devices and cloud platforms. In this
PROJECT TITLE : On the Delay Advantage of Coding in Packet Erasure Networks - 2014 ABSTRACT: We consider the delay of network coding compared to routing with retransmissions in packet erasure networks with probabilistic erasures.
PROJECT TITLE : Network Resource Allocation for Users With Multiple Connections Fairness and Stability - 2014 ABSTRACT: This paper studies network resource allocation between users that manage multiple connections, possibly
PROJECT TITLE : Multi-Core Embedded Wireless Sensor Networks Architecture and Applications - 2014 ABSTRACT: Technological advancements in the silicon industry, as predicted by Moore's law, have enabled integration of billions

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry