Christos Stentoumis

Monocular camera fall detection system exploiting 3d measures: a semi-supervised learning approach

Falls have been reported as the leading cause of injury-related visits to emergency departments and the primary etiology of accidental deaths in elderly. The system presented in this article addresses the fall detection problem through visual cues. The proposed methodology utilize a fast, real-time background subtraction algorithm based on motion information in the scene and capable to operate properly in dynamically changing visual conditions, in order to detect the foreground object and, at the same time, it exploits 3D spaces measures, through automatic camera calibration, to increase the robustness of fall detection algorithm which is based on semi-supervised learning. The above system uses a single monocular camera and is characterized by minimal computational cost and memory requirements that make it suitable for real-time large scale implementations.

Census-Based Cost on Gradients for Matching under Illumination Differences

Stereo-matching is an indispensable process of dense 3D information extraction for a wide range of applications. Relevant methods rely on cost functions and optimization algorithms for estimating accurate disparities. This work analyses a novel cost for stereo matching under radiometric differences in the stereo-pair, which is based on a modification of the widely used census transformation. It is proposed to define the census on image x and y gradients. The modified census (MC) on gradients is evaluated as an independent matching cost in the presence of severe radiometric differences. For this, the original and the modified census transformation (CT) are implemented in three different aggregation schemes, namely fixed rectangular windows, adaptive cross-based support regions and semi-global matching. It is shown that the MC can provide better results in the cases of local radiometric differences, such as different illumination conditions. Thus, this approach can extend the inherent capability of the original CT to address global monotonic radiometric differences.

Autonomous robotic system for tunnel structural inspection and assessment

This paper presents a robotic platform, capable of autonomous tunnel inspection, developed under ROBO-SPECT European union funded research project. The robotic vehicle consists of a robotized production boom lift, a high precision robotic arm, advanced computer vision systems, a 3D laser scanner and an ultrasonic sensor. The autonomous inspection of tunnels requires advanced capabilities of the robotic vehicle and the computer vision sub-system. The robot localization in underground spaces and on long linear paths is a challenging task, as well as the mm accurate positioning of a robotic tip installed on a five-ton crane vehicle. Moreover, the 2D and 3D vision tasks, which support the inspection process, should tackle with poor and variable lighting conditions, low textured lining surfaces and the need for high accuracy. This contribution describes the final robotic vehicle and the developments as designed for concrete lining tunnel inspection. Results from the validation and benchmarking of the system are also included following the final tests at the operating Egnatia Motorway tunnels in northern Greece.

A hybrid algorithm for dense stereo correspondences in challenging indoor scenes

The algorithms for dense correspondences in stereo images are an extensively researched topic, since it is an essential step in a large number of applications. Despite the fact that the first stereo matching algorithms were proposed some decades ago, novel approaches regarding typical, but also cutting-edge applications, are always in demand. Stereo matching is an inverse, ill-posed problem, which usually depends on the application and the scenario. In this contribution, a hybrid approach for stereo matching is proposed, which is based on graph-cuts optimization (global) and cross-based aggregation (local) under a hierarchical scheme. It is shown that the combined effect of a global method in a coarse layer and a local method in finer layers improves the matching results. This hybrid approach exploits the strengths and ameliorates the weaknesses of the individual global and local algorithms. The resulted disparity map is robust without outliers even in untextured areas and at the same time high fidelity details are accurately represented. This hybrid scheme is evaluated on challenging indoor datasets. It is also computationally efficient for applying it on low-processing power applications.

A review and evaluation of penalty functions for Semi-Global Matching

Multi-view matching presents significant advantages regarding accuracy, radiometric fidelity or occlusion handling; however, the limitation of having only two available views remains common in many real-life scenarios. The Semi-Global Matching (SGM) approach has been proved to be robust against complex scenes (from aerial images to those from autonomous systems) and radiometrically challenging images, providing accurate disparity maps (compared to global and local methods) and computational efficiency. Recently, an entire class of methods has appeared relying on SGM. In the present study, a review of methods which define an adaptive function for the P2 cost penalty for disparity discontinuities is presented. The evaluation methodology includes use of absolute intensity differences and the distance on Census transformed images as cost functions, and extensive parameter tuning with comparisons under the demanding Middlebury College 2006 stereo dataset, which involves radiometric changes in illumination/exposure. Results are reported and evaluated as regards the performance of such variations of SGM.

Precise 3D Reconstruction of Cultural Objects Using Combined Multi-component Image Matching and Active Contours Segmentation

Cultural and creative industries constitute a large range of economic activities. Towards this expansion we need to state the inclusion of ICT technologies, as such of 3D reconstruction methods. However, precise 3D reconstruction under a computationally affordable manner is a research challenge. One way to precisely reconstruct a cultural object is through the use of photogrammetry with the main goal of finding the correspondences between two or more images to reconstruct 3D surfaces. A cultural object is often surrounded by visual background data that should be excluded to improve 3D reconstruction accuracy. Background conditions dynamically change, especially if the object is captured under outdoor conditions, where many occlusions occur and the shadows effects are not negligible. In this paper, we propose a combine image segmentation and matching method to yield an affordable 3D reconstruction of cultural objects. Image segmentation is performed on the use of active contours while image matching through novel multi-cost criteria optimization functions. Experimental results on real-life ancient column capitals indicate the efficiency of the proposed scheme both in terms of performance efficiency and cost.

An interactive story map for the Methana volcanic peninsula

The purpose of this research is the identification, recording, mapping and photographic imaging of the special volcanic geoforms as well as the cultural monuments of the volcanic Methana Peninsula. With the use of novel methods the aim is to reveal and study the impressive topographic features of the Methana geotope and discover its unique geodiversity. The proposed hiking trails along with the Methana’s archaeology and history, will be highlighted through the creation of an ‘intelligent’ interactive map (Story Map). Two field trips have been conducted for the collection of further information and the digital mapping of the younger volcanic flows of Kammeni Chora with drones. Through the compiled data, thematic maps were created depicting the lava flows and the most important points of the individual hiking paths. The thematic maps were created using a Geographic Information System (GIS). Finally, those maps were the basis for the creation of the main Story Map. The decision to use Story Maps was based on the numerous advantages on offer such as user-friendly mapping, ease of use and interaction and user customized displays.

Human tracking driven activity recognition in video streams

In this paper we describe a method to visually recognize activities from video streams driven by a robust tracking algorithm. The tracking algorithm uses object flow as a motion model that estimates the displacement and the direction of objects in imagery streams; as observation model, object flow is complemented by a generative prior based on the Gaussian Process Latent Variable Model for increased robustness to visual alterations of the tracked object (human). We then use tracking results as input to drive the recognition of activities by hidden Markov models-based classifiers. We evaluate the performance of the examined approach under real-life activity recognition scenarios in visually complex environments characterized by lighting changes, occlusions and outliers.