An Object Detection Model based on Augmented Reality for Iraqi Archaeology

Authors

DOI:

https://doi.org/10.21123/bsj.2024.9199

Keywords:

Anchor boxes, Classification, Computer Vision, Localization, Object detection.

Abstract

The culture of Iraq, which boasts a rich history, serves as evidence of the magnificence of human civilization. Nonetheless, safeguarding and highlighting this valuable cultural legacy has become a significant worry in a time characterized by technological progress. Augmented Reality (AR) offers a powerful tool for preserving and presenting historical sites. The aim of this research is to leverage AR technology as a means to ensure the continued preservation and dynamic presentation of Iraq's cultural heritage. This study explores the capabilities of CNNs as the basis of AR's development. CNN is used as an essential initial step in constructing AR systems. The proposed model utilizes a pre-trained backbone network to extract complicated spatial features from input images; additional convolutional and fully connected layers are introduced to refine these features. A new custom class called “AnchorBoxes”, dynamically generates predefined anchor boxes for each feature map. Since there is not an appropriate Iraqi archeology dataset available for training deep learning models, a dataset of 2188 color images was collected. Spanning ancient Iraqi ruins, celebrated monuments, and real-time scenes combined with various objects. This dataset is subjected to manual annotation, wherein bounding boxes and labels are assigned to objects in each image. Results from the regression analysis emphasize the model's proficiency in estimating object bounding box coordinates with good precision and regression loss equal 0.008, facilitating locate-accurate object localization. The classification outcomes illuminate the model's ability to assign class labels to detected objects with high confidence. The mAP for the trained model was 0.84 and the classification loss was 0.02

References

Ghasemi Y, Jeong H, Choi SH, Park K-B, Lee JYJCiI. Deep learning-based object detection in augmented reality: A systematic review. Comput Ind. 2022; 139: 103661. http://dx.doi.org/10.1016/j.compind.2022.103661

Khan MA, Israr SS, Almogren A, Din IU, Almogren A, Rodrigues JJ. Using augmented reality and deep learning to enhance Taxila Museum experience. J Real-Time Image Process 18 (2): 321–32. https://doi.org/10.1007/s11554-020-01038-y

Sweeney SK, Newbill P, Ogle T, Terry KJT. Using augmented reality and virtual environments in historic places to scaffold historical empathy.TechTrends 2018; 62: 114-8. https://doi.org/10.1007/s11528-017-0234-9

Blanco-Fernández Y, López-Nores M, Pazos-Arias JJ, Gil-Solla A, Ramos-Cabrer M, García-Duque J. REENACT: A step forward in immersive learning about Human History by augmented reality, role playing and social networking. Expert Syst Appl. 2014; 41(10): 4811-28. https://doi.org/10.1016/j.eswa.2014.02.018

Oleksy T, Wnuk A. Augmented places: An impact of embodied historical experience on attitudes towards places. Comput. Hum. Behav. 2016 Apr 1;57:11-6. https://doi.org/10.1016/j.chb.2015.12.014

Çakiroğlu Ü, Aydin M, Köroğlu Y, Ayvaz Kina MJILE. Looking past seeing present: teaching historical empathy skills via augmented realit.nteract. Interact Learn Environ. 2023:1-13. https://doi.org/10.1080/10494820.2023.2174142

Carmigniani J, Furht B, Anisetti M, Ceravolo P, Damiani E, Ivkovic MJMt, et al. Augmented reality technologies, systems and applications. Multimed. Tools Appl. 2011; 51: 341-77. https://doi.org/10.1007/s11042-010-0660-6

Fenais AS, Ariaratnam ST, Ayer SK, Smilovsky NJJoITiC. A review of augmented reality applied to underground construction. J Inf echnol Constr. 2020; 25: 308-24. https://doi.org/10.36680/j.itcon.2020.018

Ponnusamy V, Natarajan, Solutions, Applications. Precision agriculture using advanced technology of IoT, unmanned aerial vehicle, augmented reality, and machine learning. IIOT. 2021: 207-29. https://doi.org/10.1007/978-3-030-52624-5_14

Lalonde J-F, editor Deep learning for augmented reality. 2018 17th Workshop on Information Optics (WIO); 2018: IEEE. https://doi.org/10.1109/WIO.2018.8643463

Park K-B, Kim M, Choi SH, Lee JYJR, Manufacturing C-I. Deep learning-based smart task assistance in wearable augmented reality. Robot Comput Integr Manuf. 2020; 63: 101887. https://doi.org/10.1016/j.rcim.2019.101887

Alsaedi EM, Farhan Ak. Retrieving Encrypted Images Using Convolution Neural Network and Fully Homomorphic Encryption. Baghdad Sci J. 2023; 20(1): 0206. https://dx.doi.org/10.21123/bsj.2022.6550

He Y, Ren J, Yu G, Cai YJIToWC. Optimizing the learning performance in mobile augmented reality systems with CNN. IEEE Trans Wirel Commun. 2020; 19(8): 5333-44. https://doi.org/10.1109/TWC.2020.2992329

Ababsa F-e, Mallem M, editors. Robust camera pose estimation using 2d fiducials tracking for real-time augmented reality systems. Proceedings of the 2004 ACM SIGGRAPH international conference on Virtual Reality continuum and its applications in industry; 2004. https://doi.org/10.1145/1044588.1044682

Abdullah TH, Alizadeh F, Abdullah BH. COVID-19 Diagnosis System using SimpNet Deep Model. Baghdad Sci J. 2022; 19(5): 1078. https://doi.org/10.21123/bsj.2022.6074

Sprute D, Viertel P, Tönnies K, König M, editors. Learning virtual borders through semantic scene understanding and augmented reality. IEEE Int Conf Intell Robots Sys.; 2019: https://doi.org/10.1109/IROS40897.2019.8967576

Soroush M, Mehrtash A, Khazraee E, Ur JAJRS. Deep learning in archaeological remote sensing: Automated qanat detection in the Kurdistan region of Iraq. Remote Sens. 2020; 12(3): 500. https://doi.org/10.3390/rs12030500

Yer A, Franklin M. AI-Powered Archaeology: Determining the Origin Culture of Various Ancient Artifacts Using Machine Learning. JSR. 2022; 11(1). https://doi.org/10.47611/jsrhs.v11i1.2465

Verschoof-Van der Vaart WB, Lambers K. Learning to look at LiDAR: The use of R-CNN in the automated detection of archaeological objects in LiDAR data from the Netherlands. J Comput Appl Archaeol. 2019; 2(1). https://doi.org/10.5334/jcaa.32

. Combined detection and segmentation of archeological structures from LiDAR data using a deep learning approach. Comput Appl Archaeol. 2021; 4(1): 1. https://dx.doi.org/10.5334/jcaa.64

Rahman MA, Wang Y, editors. Optimizing intersection-over-union in deep neural networks for image segmentation. ISVC; 2016: Springer. https://doi.org/10.1007/978-3-319-50835-1_22

Lin T-Y, Goyal P, Girshick R, He K, Dollár P, editors. Focal loss for dense object detection. Proc IEEE Int Conf Comput Vis. ; 2017. https://doi.org/10.48550/arXiv.1708.02002

Downloads

Issue

Section

article

How to Cite

1.
An Object Detection Model based on Augmented Reality for Iraqi Archaeology. Baghdad Sci.J [Internet]. [cited 2024 Jun. 14];21(12). Available from: https://bsj.uobaghdad.edu.iq/index.php/BSJ/article/view/9199