@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{Agrafiotis2018,

title = {Underwater photogrammetry in very shallow waters: Main challenges and caustics effect removal},

author = {P Agrafiotis and D Skarlatos and T Forbes and C Poullis and M Skamantzari and A Georgopoulos},

url = {https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2/15/2018/},

doi = {10.5194/isprs-archives-XLII-2-15-2018},

issn = {16821750},

year  = {2018},

date = {2018-05-01},

journal = {Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. - ISPRS Arch.},

volume = {42},

number = {2},

pages = {15--22},

publisher = {International Society for Photogrammetry and Remote Sensing},

abstract = {In this paper, main challenges of underwater photogrammetry in shallow waters are described and analysed. The very short camera to object distance in such cases, as well as buoyancy issues, wave effects and turbidity of the waters are challenges to be resolved. Additionally, the major challenge of all, caustics, is addressed by a new approach for caustics removal (Forbes et al., 2018) which is applied in order to investigate its performance in terms of SfM-MVS and 3D reconstruction results. In the proposed approach the complex problem of removing caustics effects is addressed by classifying and then removing them from the images. We propose and test a novel solution based on two small and easily trainable Convolutional Neural Networks (CNNs). Real ground truth for caustics is not easily available. We show how a small set of synthetic data can be used to train the network and later transfer the le arning to real data with robustness to intra-class variation. The proposed solution results in caustic-free images which can be further used for other tasks as may be needed.},

keywords = {Caustics, CNN, SfM MVS, Underwater 3D reconstruction},

pubstate = {published},

tppubtype = {article}

}