@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{Voulodimos2020,

title = {NOISE-TOLERANT HYPERSPECTRAL IMAGE CLASSIFICATION USING DISCRETE COSINE TRANSFORM AND CONVOLUTIONAL NEURAL NETWORKS},

author = {Athanasios Voulodimos and K Fokeas and Nikolaos Doulamis and Anastasios Doulamis and K Makantasis},

url = {https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-1281-2020 https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B2-2020/1281/2020/},

doi = {10.5194/isprs-archives-XLIII-B2-2020-1281-2020},

issn = {2194-9034},

year  = {2020},

date = {2020-08-01},

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

volume = {XLIII-B2-2},

pages = {1281--1287},

abstract = {Abstract. Hyperspectral image classification has drawn significant attention in the recent years driven by the increasing abundance of sensor-generated hyper- and multi-spectral data, combined with the rapid advancements in the field of machine learning. A vast range of techniques, especially involving deep learning models, have been proposed attaining high levels of classification accuracy. However, many of these approaches significantly deteriorate in performance in the presence of noise in the hyperspectral data. In this paper, we propose a new model that effectively addresses the challenge of noise residing in hyperspectral images. The proposed model, which will be called DCT-CNN, combines the representational power of Convolutional Neural Networks with the noise elimination capabilities introduced by frequency-domain filtering enabled through the Discrete Cosine Transform. In particular, the proposed method entails the transformation of pixel macroblocks to the frequency domain and the discarding of information that corresponds to the higher frequencies in every patch, in which pixel information of abrupt changes and noise often resides. Experiment results in Indian Pines, Salinas and Pavia University datasets indicate that the proposed DCT-CNN constitutes a promising new model for accurate hyperspectral image classification offering robustness to different types of noise, such as Gaussian and salt and pepper noise.},

keywords = {Convolutional Neural Networks, deep learning, Discrete Cosine Transform, Hyperspectral image classification, noise tolerance, robustness to noise},

pubstate = {published},

tppubtype = {article}

}

@article{Katsamenis2020,

title = {Pixel-level Corrosion Detection on Metal Constructions by Fusion of Deep Learning Semantic and Contour Segmentation},

author = {Iason Katsamenis and Eftychios Protopapadakis and Anastasios Doulamis and Nikolaos Doulamis and Athanasios Voulodimos},

url = {http://arxiv.org/abs/2008.05204},

year  = {2020},

date = {2020-08-01},

abstract = {Corrosion detection on metal constructions is a major challenge in civil engineering for quick, safe and effective inspection. Existing image analysis approaches tend to place bounding boxes around the defected region which is not adequate both for structural analysis and pre-fabrication, an innovative construction concept which reduces maintenance cost, time and improves safety. In this paper, we apply three semantic segmentation-oriented deep learning models (FCN, U-Net and Mask R-CNN) for corrosion detection, which perform better in terms of accuracy and time and require a smaller number of annotated samples compared to other deep models, e.g. CNN. However, the final images derived are still not sufficiently accurate for structural analysis and pre-fabrication. Thus, we adopt a novel data projection scheme that fuses the results of color segmentation, yielding accurate but over-segmented contours of a region, with a processed area of the deep masks, resulting in high-confidence corroded pixels.},

keywords = {boundary refinement, corrosion detection, deep learning, Index Terms-Semantic segmentation},

pubstate = {published},

tppubtype = {article}

}

@article{Antoniou2020,

title = {A deep learning method to accelerate the disaster response process},

author = {Vyron Antoniou and Chryssy Potsiou},

url = {https://www.unisdr.org/},

doi = {10.3390/rs12030544},

issn = {20724292},

year  = {2020},

date = {2020-02-01},

journal = {Remote Sens.},

volume = {12},

number = {3},

pages = {544},

publisher = {MDPI AG},

abstract = {This paper presents an end-to-end methodology that can be used in the disaster response process. The core element of the proposed method is a deep learning process which enables a helicopter landing site analysis through the identification of soccer fields. The method trains a deep learning autoencoder with the help of volunteered geographic information and satellite images. The process is mostly automated, it was developed to be applied in a time-and resource-constrained environment and keeps the human factor in the loop in order to control the final decisions. We show that through this process the cognitive load (CL) for an expert image analyst will be reduced by 70%, while the process will successfully identify 85.6% of the potential landing sites. We conclude that the suggested methodology can be used as part of a disaster response process.},

keywords = {artificial intelligence, deep learning, Deep learning autoencoder, Disaster response management, Helicopter landing site analysis, Machine Learning, Object detection, Satellite imagery, Volunteered geographic information},

pubstate = {published},

tppubtype = {article}

}