English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

To perform advanced surveillance, Unmanned Aerial Vehicles (UAVs) require theexecution of edge-assisted computer vision (CV) tasks. In multi-hop UAVnetworks, the successful transmission of these tasks to the edge is severelychallenged due to severe bandwidth constraints. For this reason, we propose anovel A$^2$-UAV framework to optimize the number of correctly executed tasks atthe edge. In stark contrast with existing art, we take an application-awareapproach and formulate a novel pplication-Aware Task Planning Problem(A$^2$-TPP) that takes into account (i) the relationship between deep neuralnetwork (DNN) accuracy and image compression for the classes of interest basedon the available dataset, (ii) the target positions, (iii) the currentenergy/position of the UAVs to optimize routing, data pre-processing and targetassignment for each UAV. We demonstrate A$^2$-TPP is NP-Hard and propose apolynomial-time algorithm to solve it efficiently. We extensively evaluateA$^2$-UAV through real-world experiments with a testbed composed by four DJIMavic Air 2 UAVs. We consider state-of-the-art image classification tasks withfour different DNN models (i.e., DenseNet, ResNet152, ResNet50 andMobileNet-V2) and object detection tasks using YoloV4 trained on the ImageNetdataset. Results show that A$^2$-UAV attains on average around 38% moreaccomplished tasks than the state-of-the-art, with 400% more accomplished taskswhen the number of targets increases significantly. To allow fullreproducibility, we pledge to share datasets and code with the researchcommunity.

A$^2$-UAV: Application-Aware Content and Network Optimization of Edge-Assisted UAV Systems