Augmented reality (AR) and Artificial Intelligence (AI) are technologies pioneers in innovation and alteration in several domains. AR allows the creation of an entirely new and interactive experience for users. However, there are several drawbacks in developing AR applications, such as the marker identification process and the creation of content itself. These are very time-consuming procedures and require ad -hoc development. The advantages of using AI to solve AR limitations have recently been explored in literature. Motivated by these findings, in this paper it is proposed DeepReality, a software toolkit plug-in for Unity 3D. It is conceived for allowing developers to integrate any Deep Learning (DL) models into Unity, through AR Foundation and Barracuda inference engine. DeepReality is aimed at simplifying and streamlining the usage of DL models in conjunction with AR. As such, users skilled in Unity and DL can easily create mobile applications (iOS and Android) to: extract visual features of real-world objects (framed with the device camera) via DL; Show on-screen content on top of those real-world objects, via AR. DeepReality performs object semantic processing within the scene, and extended semantic effects for incongruent objects, overcoming the environmental tracking, which is feature-based. In order to test DeepReality usability, experiments have been performed on the execution time and memory usage data, demonstrating the feasibility and possibility of integrating and using DNNs models in mobile applications for AR. The complexity analysis confirms that DeepReality can be completely executed on mobile devices. DeepReality is also open -source and it is freely available in the Unity asset store. By fostering accessible AI -AR integration, DeepReality addresses key shortcomings in existing approaches, encapsulating contributions such as versatile DL integration, open -source accessibility, operational validation, and comprehensive metrics analysis. DeepReality empowers developers to transcend boundaries, enriching AR applications with AI's transformative potential. Our proposed framework fosters benchmarking, comparison, and a future harmonised by AR -AI synergy.

DeepReality: An open source framework to develop AI-based augmented reality applications / Pierdicca, Roberto; Tonetto, Flavio; Paolanti, Marina; Mameli, Marco; Rosati, Riccardo; Zingaretti, Primo. - In: EXPERT SYSTEMS WITH APPLICATIONS. - ISSN 0957-4174. - 249:(2024). [10.1016/j.eswa.2024.123530]

DeepReality: An open source framework to develop AI-based augmented reality applications

Pierdicca, Roberto
;
Paolanti, Marina;Mameli, Marco;Rosati, Riccardo;Zingaretti, Primo
2024-01-01

Abstract

Augmented reality (AR) and Artificial Intelligence (AI) are technologies pioneers in innovation and alteration in several domains. AR allows the creation of an entirely new and interactive experience for users. However, there are several drawbacks in developing AR applications, such as the marker identification process and the creation of content itself. These are very time-consuming procedures and require ad -hoc development. The advantages of using AI to solve AR limitations have recently been explored in literature. Motivated by these findings, in this paper it is proposed DeepReality, a software toolkit plug-in for Unity 3D. It is conceived for allowing developers to integrate any Deep Learning (DL) models into Unity, through AR Foundation and Barracuda inference engine. DeepReality is aimed at simplifying and streamlining the usage of DL models in conjunction with AR. As such, users skilled in Unity and DL can easily create mobile applications (iOS and Android) to: extract visual features of real-world objects (framed with the device camera) via DL; Show on-screen content on top of those real-world objects, via AR. DeepReality performs object semantic processing within the scene, and extended semantic effects for incongruent objects, overcoming the environmental tracking, which is feature-based. In order to test DeepReality usability, experiments have been performed on the execution time and memory usage data, demonstrating the feasibility and possibility of integrating and using DNNs models in mobile applications for AR. The complexity analysis confirms that DeepReality can be completely executed on mobile devices. DeepReality is also open -source and it is freely available in the Unity asset store. By fostering accessible AI -AR integration, DeepReality addresses key shortcomings in existing approaches, encapsulating contributions such as versatile DL integration, open -source accessibility, operational validation, and comprehensive metrics analysis. DeepReality empowers developers to transcend boundaries, enriching AR applications with AI's transformative potential. Our proposed framework fosters benchmarking, comparison, and a future harmonised by AR -AI synergy.
2024
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S0957417424003956-main.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza d'uso: Creative commons
Dimensione 1.93 MB
Formato Adobe PDF
1.93 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11566/335935
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 1
social impact