@article{boutsi2022pose,

title = {POSE ESTIMATION THROUGH MASK-R CNN AND VSLAM IN LARGE-SCALE OUTDOORS AUGMENTED REALITY},

author = {A-M Boutsi and N Bakalos and C Ioannidis},

url = {https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-4-2022/197/2022/},

doi = {10.5194/isprs-annals-V-4-2022-197-2022},

issn = {2194-9050},

year  = {2022},

date = {2022-05-18},

journal = {ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci.},

volume = {V-4-2022},

number = {4},

pages = {197--204},

abstract = {Abstract. Deep Learning (DL) ingrained into Mobile Augmented Reality (MAR) enables a new information-delivery paradigm. In the context of 6 DoF pose estimation, powerful DL networks could provide a direct solution for AR systems. However, their concurrent operation requires a significant number of computations per frame and yields to both misclassifications and localization errors. In this paper, a hybrid and lightweight solution on 3D tracking of arbitrary geometry for outdoor MAR scenarios is presented. The camera pose information obtained by ARCore SDK and vSLAM algorithm is combined with the semantic and geometric output of a CNN-object detector to validate and improve tracking performance in large-scale and uncontrolled outdoor environments. The methodology involves three main steps: i) training of the Mask-R CNN model to extract the class, bounding box and mask predictions, ii) real-time detection, segmentation and localization of the region of interest (ROI) in camera frames, and iii) computation of 2D-3D correspondences to enhance pose estimation of a 3D overlay. The dataset holds 30 images of the rock of St. Modestos \textendash Modi in Meteora, Greece in which the ROI is an area with characteristic geological features. The comparative evaluation between the prototype system and the original one, as well as with R-CNN and FAST-R CNN detectors demonstrates higher precision accuracy and stable visualization at half a kilometre distance, while tracking time has decreased at 42% during far-field AR session.},

keywords = {3D rendering, Augmented Reality, CNN, deep learning, image recognition, pose estimation},

pubstate = {published},

tppubtype = {article}

}

@article{app11188750,

title = {Mobile Augmented Reality for Low-End Devices Based on Planar Surface Recognition and Optimized Vertex Data Rendering},

author = {Styliani Verykokou and Argyro-Maria Boutsi and Charalabos Ioannidis},

url = {https://www.mdpi.com/2076-3417/11/18/8750},

doi = {10.3390/app11188750},

issn = {2076-3417},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {Applied Sciences},

volume = {11},

number = {18},

abstract = {Mobile Augmented Reality (MAR) is designed to keep pace with high-end mobile computing and their powerful sensors. This evolution excludes users with low-end devices and network constraints. This article presents ModAR, a hybrid Android prototype that expands the MAR experience to the aforementioned target group. It combines feature-based image matching and pose estimation with fast rendering of 3D textured models. Planar objects of the real environment are used as pattern images for overlaying users’ meshes or the app’s default ones. Since ModAR is based on the OpenCV C++ library at Android NDK and OpenGL ES 2.0 graphics API, there are no dependencies on additional software, operating system version or model-specific hardware. The developed 3D graphics engine implements optimized vertex-data rendering with a combination of data grouping, synchronization, sub-texture compression and instancing for limited CPU/GPU resources and a single-threaded approach. It achieves up to 3× speed-up compared to standard index rendering, and AR overlay of a 50 K vertices 3D model in less than 30 s. Several deployment scenarios on pose estimation demonstrate that the oriented FAST detector with an upper threshold of features per frame combined with the ORB descriptor yield best results in terms of robustness and efficiency, achieving a 90% reduction of image matching time compared to the time required by the AGAST detector and the BRISK descriptor, corresponding to pattern recognition accuracy of above 90% for a wide range of scale changes, regardless of any in-plane rotations and partial occlusions of the pattern.},

keywords = {3D rendering, BRISK, camera pose estimation, geometric instancing, mobile augmented reality, OpenCV, OpenGL ES, ORB, pattern recognition, vertex-based rendering},

pubstate = {published},

tppubtype = {article}

}