Research

Geospatial Analysis

We can deal with data mining techniques, spatial data analysis, point clouds, statistical data… These are inputs for our understanding of the world around us.

LBS & Augmented Reality

Location-based services are key to effortless access to information connected with particular location. We argue, that the augmented reality is just a natural extension of the LBS. It has to be just improved a bit.

Natural Language Processing

To provide natural interaction with data, we use text data as a source of useful knowledge and experiment intensively with conversational interfaces.

Social Impacts of Climate Change

The world around us is undoubtedly changing. Our research focuses also on identifying the impacts of climate change on society, also on related migration and resilience strategies.

Research topic

Understanding the 3D World

Laser scanning technology creates a completely new research area. So far, the researchers were developing algorithms for the identification of the objects in 2D images. Now, we can use the 3D scans which enable a completely new level of understanding the world.

There are many applications: Nature, villages, cities – all of them are constantly changing, and we need to monitor these changes efficiently. Cities need to monitor the status of traffic signs, lighting, traffic signs, and other infrastructure. Companies need to monitor the state of tangible and intangible assets. It costs considerable time and money. We are therefore looking for ways to effectively monitor and manage the environment and property.

In the field of Remote Sensing, we deal with point cloud processing. We try to process the point clouds and find the objects they contain in an automated manner. So far we have focused on finding road markings and traffic signs. Now we are focusing on the detection of complex objects. This research aims to map out very quickly and precisely large areas and save time and resources.

In the field of mechanical engineering, we are using the same techniques to reconstruct the shapes of scanned objects and provide precise models with sharp edges, concave shapes and other challenging features.

Some recent papers...

Sharp Feature Detection as a Useful Tool in Smart Manufacturing

Industry 4.0 comprises a wide spectrum of developmental processes within the management of manufacturing and chain production. Presently, there is a huge effort to automate manufacturing and have automatic control of the production. This intention leads to the increased need for high-quality methods for digitization and object reconstruction, especially in the area of reverse engineering. Commonly used scanning software based on well-known algorithms can correctly process smooth objects. Nevertheless, they are usually not applicable for complex-shaped models with sharp features. The number of the points on the edges is extremely limited due to the principle of laser scanning and sometimes also low scanning resolution. Therefore, a correct edge reconstruction problem occurs. The same problem appears in many other laser scanning applications, i.e., in the representation of the buildings from airborne laser scans for 3D city models. We focus on a method for preservation and reconstruction of sharp features. We provide a detailed description of all three key steps: point cloud segmentation, edge detection, and correct B-spline edge representation. The feature detection algorithm is based on the conventional region-growing method and we derive the optimal input value of curvature threshold using logarithmic least square regression. Subsequent edge representation stands on the iterative algorithm of B-spline approximation where we compute the weighted asymmetric error using the golden ratio. The series of examples indicates that our method gives better or comparable results to other methods.

Procházková, Jana — Procházka, David — Landa, Jaromír
Sharp Feature Detection as a Useful Tool in Smart Manufacturing ISPRS International Journal of Geo-Information. 2020. v. 9, no. 7, ISSN 2220-9964.

Automatic lane marking extraction from point cloud into polygon map layer

Optimization of road networks is a common concern worldwide, primarily for safety purposes. Because the extent of these networks is substantial, automation of their inventory is highly desirable. This paper concentrates on the road inventory process that is necessary for regular maintenance. The key part of our road marking detection and reconstruction is based on spanning tree usage. The spanning trees are obtained from alpha shapes of the detected road markings. The spanning trees application enables the reliable identification of the road markings and precise reconstruction of their contours even with noisy data. Our method processes the point cloud data obtained from LiDAR measurements, and provides a common vector layer with road lane polygons. Such a vector layer is stored in a common file format supported by the majority of geographical information systems, thus producing an output that can be conveniently used for decision-making based on the road inventory process.

Procházka, David — Procházková, Jana — Landa, Jaromír
Automatic lane marking extraction from point cloud into polygon map layer. European Journal of Remote Sensing. 2019. v. 52, no. S1, p. 26–39. ISSN 2279-7254.

Development of models for forest variable estimation from airborne laser scanning data using an area-based approach at a plot level

Airborne laser scanning (ALS) is increasingly used in the forestry over time, especially in a forest inventory process. A great potential of ALS lies in providing quick high precision data acquisition for purposes such as measurements of stand attributes over large forested areas. Models were developed using an area-based approach to predict forest variables such as wood volume and basal area. The solution was performed through developing an object-oriented script using Python programming language, Python Data Analysis Library (Pandas), which represents a very flexible and powerful data analysis tool in conjunction with interactive computational environment the IPython Notebook. Several regression models for estimation of forest inventory attributes were developed at a plot level.

Sabol, Jan — Procházka, David — Patočka, Zdeněk
Development of models for forest variable estimation from airborne laser scanning data using an area-based approach at a plot level. Journal of forest science. 2016. v. 62, no. 3, p. 137–142. ISSN 1212-4834.

User Friendly Interaction with Natural Objects in Web Map Applications Based on Object Recognition

The maps become a common tool for many users. We can nd a wide range of solutions from simple search applications to advanced location intelligence tools. In most cases, aerial or satellite images are used as a background. Above this background, other map layers are presented and used for the actual interaction. Our approach is focused on the mentioned background. Aerial and satellite images comprise a huge amount of objects, but it is virtually impossible to interact with them. This paper proposes a new kind of user interface that allows to interact with these natural objects.

Procházka, David — Chodúr, Martin
User friendly interaction with natural objects in web map applications based on object recognition. Acta Universitatis agriculturae et silviculturae Mendelianae Brunensis. 2016. v. 64, no. 6, p. 2109–2116. ISSN 1211-8516.

Research Topic

Augmented Reality, LBS, Conversational Interfaces

Location-based services (LBS) are a key technology of the contemporary mobile world. We receive location-related information about weather, traffic jams, tasks and dozens of others. However, it is quite complicated to create and deploy an LBS that actually helps the users. Missing the target audience requirements is one of the common mistakes in e.g. many smart city projects.

As a testing platform, we developed the My MENDELU application that provides information to students and employees of Mendel University in Brno. Our goal is to provide users with the right information at the right time and in the right place. Currently, we provide modules like schedule & tasks, canteen information (with filters based on allergens), indoor map with searching, FAQ module and emergency messaging system for occasions like COVID-19 pandemic. We have about 4000 active users.

However, we are not focused solely on LBS. We believe that the near future of communication with computers is augmented reality and natural conversation either by speech or by text chatting.

Further examples of our work are on the Contracted R&D page.

Some recent papers...

Preprocessing of Normative Documents for Interactive Question Answering

Every larger organisation must establish a set of normative documents to control its processes and describe solutions to common problems. These documents are usually formally written and hard to read. This leads to the necessity of different customer services. Nowadays, a lot of companies are developing chatbots to automate first-line customer support. If a company does not have a large question-answer dataset to build a chatbot, the answers can be automatically answered directly from the documents. However, we found that the automatic answering usually does not work well on the normative documents. In this paper, we describe a novel method for preprocessing of normative documents in order to use them for such automatic question answering. Our method efficiently exploits the strict document structure that is typical for normative documents. We increased the recall from 35% to 84% (for paragraph-size answers) on selected normative documents from university and bank domains.

Pisařovic, Ivo — Dařena, František — Procházka, David — Janiš, Vít
Preprocessing of Normative Documents for Interactive Question Answering. Expert Systems with Applications. 2022. v. 191, no. 1 April, ISSN 0957-4174. URL: https://doi.org/10.1016/j.eswa.2021.116314

Conversational interfaces for unconventional access to business relational data structures

Current possibilities of accessing business data by regular users usually involve complicated user interfaces or require technical expertise. This results in situations when business owners are separated from their data. The aim of this research is to apply an innovative approach leveraging conversational interfaces to tackle this problem.

The authors examine the current possibilities of accessing business data by business, users with an emphasis on conversational interfaces employing a chatbot as an alternative to traditional approaches. The authors propose a new concept relying on a guided conversation, and through experiments with a real chatbot and database, the authors demonstrate the benefits of the proposed approach.

The authors found out that the key to the success of our approach is a decomposition of complex database queries and their incremental construction in conversations. This also enables natural discovery of the domain model through constantly provided feedback. Based on the experiments with a real chatbot, the authors demonstrate that defining conversation flows and maintaining the conversation context is a crucial aspect contributing to the overall accuracy, together with keeping the conversation within the defined limits in its certain parts.

The authors present a novel approach using natural language interfaces for accessing data by business users. In contrast to existing approaches, the authors emphasize incremental construction of queries, predefined conversation flows and constraining the conversations, when necessary.

Kostelník, Pavel — Dařena, František Conversational interfaces for unconventional access to business relational data structures, Data Technologies and Applications. 2021. ISSN 2514-9288. URL: https://doi.org/10.1108/DTA-03-2021-0062.

Chatbots for Enterprises: Outlook

Chatbots are going to be the main tool for automated conversations with customers. Still, there is no consistent methodology for choosing a suitable chatbot platform for a particular business. This paper proposes a new method for chatbot platform evaluation. To describe the current state of chatbot platforms, two high-level approaches to chatbot platform design are discussed and compared. WYSIWYG platforms aim to simplicity but may lack some advanced features. All-purpose chatbot platforms require extensive technical skills and are more expensive but give their users more freedom in chatbot design. We provide an evaluation of six major chatbot solutions. The proposed method for the chatbot selection is demonstrated on two sample businesses – a large bank and a small taxi service.

Kostelník, Pavel — Pisařovic, Ivo — Muroň, Mikuláš — Procházka, David — Dařena, František: Chatbots for Enterprises: Outlook. In Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis. 2019. 67(6):1541-1550. ISSN 1211-8516.

Smart displays: Personalisation of information panels

Information panels are a common part of university or administrative buildings. We can see large panels with news or social media feeds as well as small displays on conference rooms with information about their occupancy. All these panels usually present general information without any relation to a present audience. Presentation of personalised information for a particular user can be very helpful; however, for such personalisation we must take into account many aspects: identification of users in the display vicinity, sharing of the screen among multiple users etc. This paper is focused on the architecture of such system that allows presenting customised information on information panels for users within university buildings. Our solution allows detection of a user via Bluetooth beacons. The selected close display then presents information related to the user. In case there are multiple users in the display vicinity, the system evaluates their requirements and decides how to share the display.

Pisařovic, Ivo — Koubek, Tomáš — Ondroušek, Vít — Procházka, David
Smart displays: Personalisation of information panels. In Acta Universitatis agriculturae et silviculturae Mendelianae Brunensis. 2018. v. 66, no. 5, p. 1307–1314. ISSN 1211-8516.

Providing Customised Information Panel Content Based on User Behavioral Patterns

Although mobile applications are commonly using user location and behavior to provide relevant content, public information panels usually lack the ability to adjust the content for a particular user or a group of users. Therefore, we focused on the development of information panels that are able, in combination with a mobile application, to collect anonymous location data about the users, identify key behavioral patterns and provide content that is relevant for the users in the panel vicinity. The key property of our solution is the anonymity of the collected information and privacy in general. The proposed algorithm consists of the data clustering and subsequent analysis. Described solution can be used in any public building or campus that the users visit regularly.

Pisařovic, Ivo — Procházka, David — Vybíral, Dan — Procházková, Jana
Providing customised information panel content based on user behavioral patterns. In Mendel. Brno: Brno University of Technology. 2018, p. 173–180. ISSN 1803-3814.

Spatial Data Driven Evaluation of City Locations

Moving to a new home or setting a new bureau in a new city is always difficult. One does not have knowledge about suitable locations; therefore, people are frequently unpleasantly surprised. High traffic noise, long distance to shops or high criminal activity are just few of many possible disturbing aspects. Certainly, there are many data sources that can help to see some particular aspect of the city life. Nonetheless, it is extremely complex and time‑consuming task to browse through large data sets and com‑pare provided information. Therefore, we developed a solution that comprises many different data sets that describe the city environment and created set of straightforward indices such as environment, safety, shopping etc. The users just provide the application his/her preferences and the application finds locations that are most suitable for particular cause. The application is presented on the example of the Brno city area.

Muroň, Mikuláš — Procházka, David Spatial data driven evaluation of city locations. Acta Universitatis agriculturae et silviculturae Mendelianae Brunensis. 2018. v. 66, no. 5, p. 1301–1306. ISSN 1211-8516.

Research topic

Migration, development and environmental changes

One of the biggest challeng for “Western societies” in the last decade is the massive migration. This challenge has many dimensions.

Countries are making efforts to reduce or manage migration to their own countries, or to integrate immigrants into their civilization structures, cities and economies. We have been dealing with this problem for hundreds of years and the responses vary according to individual situations. On the other hand, some “solutions” such as “Fortress Europe concept” have been the subject of negotiations repeatedly for several decades. In order to make a meaningful attempt to give rules to immigration, the processes firstly must be understood. And to know the real causes of migration, which is not easy. In many cases, there are a number of interrelated factors dealing with development, remittances, and other economic and social factors. Therefore, research on this topic requires a multidisciplinary approach.
Our team has decided to focus on research into the causes of migration in the countries of origin and their analysis using a variety of tools that will allow us to better understand through visualization in the geographical spatial regime.

Quite special and relatively scarce factors are environmental changes. Although natural resources such as drinking water or soil may seem inexhaustible, in many cases the reality is quite the opposite. Long-term environmental changes or natural disasters can fundamentally affect the lives of the people in the area and thus take them natural resources, dwelling or subsistence away. Exhaustion of agricultural areas, floods, hurricanes and other natural or man-made changes along with economic causes lead people to migrate to cities. People in the affected areas are forced to leave their homes and seek livelihood elsewhere.

But is it always so? Why do people not move from areas often affected by floods, droughts, hurricanes or other impacts of environmental change, natural disasters or climatic extremes? Or why does only part of the affected population out-migrate while the others stay? Did the environmental factors affect the current population movement to Europe from Syria and other Middle Eastern and Sub-Saharan African countries since 2015?

And the dynamics of these processes, the behavior of the inhabitants of the affected areas, their perception of environmental changes, their degree of resilience, the decision to migrate or to stay belong to the main research topics of this research group.

Research Topic

Climate change, resilience and adaptation strategies

The impacts of climate change are here. How can we adapt?

The impacts of climate change, climatic extremes, and climate variability have become more and more known in the last decade. Increasing intensity and frequency of floods, droughts, extremely hot days in Europe or lack of precipitation, tropical storms and sea level rise in Asia, Africa and the Pacific and Indian Ocean is reflected in the growing number of media articles and reports.

We examine the perception, resilience and adaptation strategies of households (i) in rural areas and smaller municipalities in Central Europe that have been repeatedly affected by floods; (ii) between rural and coastal residents in South Asian countries, often affected by floods and hurricanes; (iii) inhabitants of small islands they are threaten by sea level rise.

To solve the above mentioned problems, their exact identification is necessary. Our research focuses primarily on identifying the impacts of climate change as people perceive these changes; as well as on interpretation of their resilience and adaptation strategies with the assistance of a variety of GIT tools and visualization in a geographic environment.

Climate Mobility and Development Cooperation

Development cooperation actors have been addressing climate change as a cross-cutting issue and investing in climate adaptation projects since the early 2000s. More recently, as concern has risen about the potential impacts of climate variability and change on human mobility, development cooperation actors have begun to design projects that intentionally address the drivers of migration, including climate impacts on livelihoods. However, to date, we know little about the development cooperation’s role and function in responding to climate related mobility and migration. As such, the main aim of this paper is to outline the policy frameworks and approaches shaping development cooperation actors’ engagement and to identify areas for further exploration and investment. First, we frame the concept of climate mobility and migration and discuss some applicable policy frameworks that govern the issue from various perspectives; secondly, we review the toolbox of approaches that development cooperation actors bring to climate mobility; and third, we discuss the implications of the current Covid-19 pandemic and identify avenues for the way forward. We conclude that ensuring safe and orderly mobility and the decent reception and long-term inclusion of migrants and displaced persons under conditions of more severe climate hazards, and in the context of rising nationalism and xenophobia, poses significant challenges. Integrated approaches across multiple policy sectors and levels of governance are needed. In addition to resources, development cooperation actors can bring data to help empower the most affected communities and regions and leverage their convening power to foster more coordinated approaches within and across countries.

STOJANOV, R.; ROSENGAERTNER, S.; DE SHERBININ, A.; NAWROTZKI, R. (2021): Climate Mobility and Development Cooperation. Population and Environment.

Islander migrations and the oceans: From hopes to fears?

This paper explores islanders’ hopes and fears for migration and non-migration, highlighting the role of the ocean. Migration, non-migration, hope, and fear are human conditions. To examine these conditions for islanders and oceans, this paper uses a qualitative evidence synthesis for collating and interpreting themes on the topic. Some types of hopes and fears, and a few reasons why they might emerge, are covered for islanders and ocean- related migration. Then, different ocean representations which islander migration and non- migration produces and portrays are presented. The conclusions question dichotomies and norms in the context of islander fears and hopes, as well as threats and opportunities, regarding ocean migrations.

KELMAN, I.; STOJANOV, R. (2021): Islander migrations and the oceans: From hopes to fears? Island Studies Journal, 16(1), 23-42.

Strengths and Weaknesses of Canadian Express Entry System: Experts’ Perceptions

This article offers an analysis of the first four years of functioning of Express Entry, a new on-line application management system to select skilled entrants for Canada’s key economic immigration programs leading to permanent residence. Based on interviews with 20 experts on Canadian immigration policies, we identified a number of strengths and weaknesses of the Canadian Express Entry system related to four areas: immigration policy making, processing of applications, selection of immigrants, and retention of immigrants. Since these areas are integral parts of immigration policies in all countries and Canada is a long-term leader in the design of points-based systems for selection of skilled immigrants, we also specify several lessons from the Canadian experience with the Express Entry system for other countries seeking to attract skilled immigrants.

BUREŠ, O.; KLVAŇOVÁ, R.; STOJANOV, R. (2020): Strengths and Challenges of Canadian Express Entry System: Experts’ Perceptions. Population and Development Review, 46(4): 787-812

European policies and legislation targeting ocean acidification in european waters - Current state

Ocean acidification (OA) is a global problem with profoundly negative environmental, social and economic consequences. From a governance perspective, there is a need to ensure a coordinated effort to directly address it. This study reviews 90 legislative documents from 17 countries from the European Economic Area (EEA) and the UK that primarily border the sea. The primary finding from this study is that the European national policies and legislation addressing OA is at best uncoordinated. Although OA is acknowledged at the higher levels of governance, its status as an environmental challenge is greatly diluted at the European Union Member State level. As a notable exception within the EEA, Norway seems to have a proactive approach towards legislative frameworks and research aimed towards further understanding OA. On the other hand, there was a complete lack of, or inadequate reporting in the Marine Strategy Framework Directive by the majority of the EU Member States, with the exception of Italy and the Netherlands. We argue that the problems associated with OA and the solutions needed to address it are unique and cannot be bundled together with traditional climate change responses and measures. Therefore, European OA-related policy and legislation must reflect this and tailor their actions to mitigate OA to safeguard marine ecosystems and societies. A stronger and more coordinated approach is needed to build environmental, economic and social resilience of the observed and anticipated changes to the coastal marine systems.

GALDIES, C.; BELLERBY, R.; CANU, D.M.; CHEN, W.; LUQUE, E.G.; GASPAROVIC, B.; GODRIJAN, J.; LAWLOR, P.J.; MAES, F.; MALEJ, A.; PANAGIOTARAS, D.; MARTINEZ ROMERA, B.; REYMOND, C.E.; ROCHETTE, J.; SOLIDORO, C.; STOJANOV, R.; TILLER, R.; DE NORONHA, I.T.; UŚCINOWICZ, G.; VAIDIANU, N.; WALSH, C.; GUERRA, R. (2020):  European policies and legislation targeting ocean acidification in European Waters – current state. Marine Policy, 118, 103947, https://doi.org/10.1016/j.marpol.2020.103947.

Does climate change influence people’s migration decisions in Maldives?

The influence of climate change and perceptions of it on people’s migration decisions has received significant prominence, especially for people living on low-lying islands. To contribute to this literature, this paper uses Maldives as a case study for exploring the research question: How does climate change influence or not influence people’s migration decisions in Maldives? Previous work tends to start from a disciplinary climate change perspective, while this study combines migration, mobility, and island studies perspectives, within which climate change sits. As well, rather than focusing on the area around the capital, Malé, as with many previous studies, the 113 interviews here were conducted in eight islands across three atolls. The method was qualitative, semi-structured, face-to-face interviews using purposive sampling of ordinary people. Contrary to a view of islanders preparing to flee their islands as “climate change refugees”, the interviewees provided nuanced and varied responses. They rarely identified the potential of future impacts due to climate change as influencing their migration-related decisions. When migration was considered, it was chiefly internal movement seeking a better standard of living via improved services, better living conditions, and more job opportunities. If migration related to potential climate change impacts might happen, then it was assumed to be in the future for decisions then. This lack of influence of climate change-related perceptions on Maldivians’ migration decisions fits well within island mobilities studies, from which climate change perspectives could adopt wider contexts.

KELMAN, I.; ORLOWSKA, J.; UPADHYAY, U.; STOJANOV, R.; WEBERSIK, C.; SIMONELLI, A. C.; PROCHÁZKA, D.; NĚMEC, D.: (2019): Does Climate Change Influence People’s Migration Decisions in Maldives? Climatic Change. 153(1–2): 285–299.

Who cares about ocean acidification in the Plasticene?

Plastics is all the rage, and mitigating marine litter is topping the agenda for nations pushing issues such as ocean acidification, or even climate change, away from the public consciousness. We are personally directly affected by plastics and charismatic megafauna is dying from it, and it is something that appears to be doable. So, who cares about the issue of ocean acidification anymore? We all should. The challenge is dual in the fact that is both invisible to the naked eye and therefore not felt like a pressing issue to the public, thereby not reaching the top of the agenda of policy makers; but also that it is framed in the climate change narrative of fear – whereby it instills in a fight-or-flight response in the public, resulting in their avoidance of the issue because they feel they are unable to take action that have results. In this article, we argue that the effective global environmental governance of ocean acidification, though critical to address, mitigate against and adapt to, is hindered by the both this lack of perception of urgency in the general public, fueled by a lack of media coverage, as well as a fight-or-flight response resulting from fear. We compare this to the more media friendly and plastics problem that is tangible and manageable. We report on a media plots of plastics and ocean acidification coverage over time and argue that the issue needs to be detangled from climate change and framed as its own issue to reach the agenda at a global level, making it manageable to assess and even care about for policy makers and the public alike?

TILLER, R.; ARENAS, F.; GALDIES, C.; LEITAO, F.; MALEJ, A.; MARTINEZ ROMERA, B.; SOLIDORO, C.; STOJANOV, R.; TURK, V.; GUERRA, R. (2019): Who cares about ocean acidification in the Plasticene? Ocean and Coastal Management, 174: (170-180). DOI:10.1016/j.ocecoaman.2019.03.020

Further Information

Complete list of projects and publications with impact factor as well as description of our contracted research and development can be found on separate pages.