RGB-SpectralImaging 2016 Abstracts


Full Papers
Paper Nr: 1
Title:

Extracting Dynamics from Multi-dimensional Time-evolving Data using a Bag of Higher-order Linear Dynamical Systems

Authors:

Kosmas Dimitropoulos, Panagiotis Barmpoutis, Alexandors Kitsikidis and Nikos Grammalidis

Abstract: In this paper we address the problem of extracting dynamics from multi-dimensional time-evolving data. To this end, we propose a linear dynamical model (LDS), which is based on the higher order decomposition of the observation data. In this way, we are able to extract a new descriptor for analyzing data of multiple elements coming from of the same or different data sources. Each sequence of data is modeled as a collection of higher order LDS descriptors (h-LDSs), which are estimated in equally sized temporal segments of data. Finally, each sequence is represented as a term frequency histogram following a bag-of-systems approach, in which h-LDSs are used as feature descriptors. For evaluating the performance of the proposed methodology to extract dynamics from time evolving multidimensional data and using them for classification purposes in various applications, in this paper we consider two different cases: dynamic texture analysis and human motion recognition. Experimental results with two datasets for dynamic texture analysis and two datasets for human action recognition demonstrate the great potential of the proposed method.

Paper Nr: 2
Title:

RGB-D-λ: 3D Multispectral Acquisition with Stereo RGB Cameras

Authors:

Alain Trémeau, Simone Bianco and Raimondo Schettini

Abstract: In this paper we report some key questions related to the acquisition of accurate color images adressed by the Colour and Space in Cultural Heritage (COSCH) project. We summarize the main criteria defined by COSCH Working Group 1 and used by the authors to help Digital Cultural Heritage (DCH) users to have a deepen knowledge and understanding of the constraints, preconditions and practical aspects related to the use of a multi-spectral acquisition system. We also report how color data can be estimated from spectral data and discuss several issues related to the measurement of reflective surfaces by 2D imaging systems.

Paper Nr: 3
Title:

Land Cover Clustering based on Improved Dictionary Learning Method from Modis Data

Authors:

Mariem Zaouali, Sonia Bouzidi and Ezzeddine Zagrouba

Abstract: An approach based on k-means clustering algorithm combined with the concept of sparse representation is proposed in this paper. We intend to discriminate, each vegetation type, by its temporal behavior. Our method is composed of two main parts : The first part consists of designing the dictionary that we are going to use. For this reason, we propose a modification of the k-svd algorithm by switching the use of OMP algorithm by the SunSAL algorithm. Then we carry on an unsupervised clustering process using k-means algorithm on sparse vectors. As a result, we found that SunSAL algorithm outperforms the OMP algorithm and we succeed to elaborate discriminative temporal behaviors of the vegetation in our region of study. As perspectives, our approach could be considered as an attempt to overcome the shortage of high spatial resolution data since we are relying only on coarse remote sensing images like MODIS to monitor Land Cover dynamics.

Paper Nr: 4
Title:

Online Indexing Structure for Big Image Data used for 3D Reconstruction

Authors:

Konstantinos Makantasis, Yannis Katsaros, Anastasios Doulamis and Matthaios Bimpas

Abstract: One of the main characteristics of Internet era is the free and online availability of extremely large collections of images. Although the proliferation of millions of shared photos provide a unique opportunity for cultural heritage e-documentation, the main difficulty is that Internet image datasets are unstructured. For this reason, this paper aims to describe a new image indexing scheme with application in 3D reconstruction. The presented approach is capable, on the one hand to index images in a fast and accurate way and on the other to select form an image dataset the most appropriate images for 3D reconstruction, improving this way reconstruction computational time, while simultaneously keeping the same reconstruction performance.

Paper Nr: 5
Title:

3D Building Reconstruction using Stereo Camera and Edge Detection

Authors:

Konstantinos Bacharidis, Lemonia Ragia, Marios Politis, Konstantia Moirogiorgou and Michalis Zervakis

Abstract: Three dimensional geo-referenced data for buildings are very important for many applications like cadastre, urban and regional planning, environmental issues, archaeology, architecture, tourism and energy. The acquisition and update of existing databases is time consuming and involves specialized equipment and heavy post processing of the raw data. In this study we propose a system for urban area data based on stereo cameras for the reconstruction of the 3D space and subsequent matching with limited geodetic measurements. The proposed stereo system along with image processing algorithms for edge detection and characteristic point matching in the two cameras allows for the reconstruction of the 3D scene in camera coordinates. The matching with the available geodetic data allows for the mapping of the entire scene on the word coordinates and the reconstruction of real world distance and angle measurements.

Paper Nr: 6
Title:

Crack Identification Via User Feedback, Convolutional Neural Networks and Laser Scanners for Tunnel Infrastructures

Authors:

Eftychios Protopapadakis, Konstantinos Makantasis, George Kopsiaftis, Nikolaos Doulamis and Angelos Amditis

Abstract: In this paper, a deep learning approach synergetically to a laser scanning process are employed for the visual detection and accurate description of concrete defects in tunnels. Analysis is performed over raw RGB images; Convolutional Neural Network serves as the crack detector, during the inspection. In case of a positive detection, the tunnel’s cross-section morphology is assessed via 3D point clouds, created by a laser scanner, allowing the identification of deformations in the compartment. The proposed approach, in contrast to the existing ones, emphasizes on applicability (easy initialization, no preprocessing of the input data) and provides a holistic assessment of the structure; reconstructed 3D model allows the fast identification of structural divergence from the original design, alerting the engineers for possible dangers.

Paper Nr: 7
Title:

Human Detection from Ground Truth Cameras through Combined Use of Histogram of Oriented Gradients and Body Part Models

Authors:

Tian-Rui Liu, Valentine Copin and Tania Stathaki

Abstract: Vision based human detection continuously attracts research interest since it is a topic of practical significance. The well-established Histogram of Oriented Gradients (HOG) human detector, though regarded as a reference for human detection, still suffers from the typical problem of the trade-off between precision and recall, relying on the threshold of its classifiers. In this paper, we propose a human detection system which can provide both good precision and recall without the need for adjusting the classification thresholds. Our strategy is to combine the HOG detector with a body part model in order to eliminate the false detections that do not match the human silhouette (body) model. For this purpose, a probabilistic model of the human body is learned to describe the relative position between the distinctive body parts. A HOG detection would be retained if the body parts can be detected in the confidence areas provided by the learned body model. Moreover, the body parts detectors are boosted cascade classifier learned with the Haar, HOG or LBP features. The multi-modal feature representation of the different human body parts is more robust against variations in human appearances. Experiment results on the INRIA data sets show that our human detector achieves a precision of 70% at a recall of 50%, which cannot be achieved by the HOG detector under any parameter settings.