- Artificial Intelligence, Computer Science, Computer Vision, Image Processing, OOAD, UML, Design Patterns, semantic interoperbility, ontology, serious games, e-learning, computer architectures, computer modelling and behavioural simulation, Particle filters, and 22 moreVisual tracking, Extended Kalman Filter, Sensor Fusion, Multirobot systems, Cooperative Robot Localization, Graph Optimization, Cooperative Object Tracking, Moving Landmarks, Spherical Object Detection, Database Systems, Content Analysis, Localization, Content-Based Image Retrieval, Tagging Technologies, Engineering, Information Technology, Data Mining, Computer Engineering, Software Engineering, Machine Learning, Computer Networks, and Algorithmsedit
- Emanuele Frontoni joined the Dept. of Information Engineering (DII) at the Università Politecnica delle Marche, as a ... moreEmanuele Frontoni joined the Dept. of Information Engineering (DII) at the Università Politecnica delle Marche, as a Ph.D. student in "Intelligent Artificial Systems". He obtained his PhD in 2006 discussing a thesis on Vision Based Robotics. At present he has an Assistant Professor position in the same department. His research focuses on applying artificial intelligence and computer vision techniques to mobile robots. He is a member of IEEE, MESA, GIRPR and AI*IA.edit
Automated approaches to building detection in multi-source aerial data are important in many applications, including map updating, city modeling, urban growth analysis and monitoring of informal settlements. This paper presents a... more
Automated approaches to building detection in multi-source aerial data are important in many applications, including map updating, city modeling, urban growth analysis and monitoring of informal settlements. This paper presents a comparative analysis of different methods for automated building detection in aerial images and laser data at different spatial resolutions. Five methods are tested in two study areas using features extracted at both pixel level and object level, but with the strong prerequisite of using the same training set for all methods. The evaluation of the methods is based on error measures obtained by superimposing the results on a manually generated reference map of each area. The results in both study areas show a better performance of the Dempster-Shafer and the AdaBoost methods, although these two methods also yield a number of unclassified pixels. The method of thresholding a normalized DSM performs well in terms of the detection rate and reliability in the less vegetated Mannheim study area, but also yields a high rate of false positive errors. The Bayesian methods perform better in the Memmingen study area where buildings have more or less the same heights.
Research Interests:
This paper aims to propose a novel idea of an embedded intelligent system where low cost embedded vision systems can analyze human behaviors to obtain interac-tivity and statistical data, mainly devoted to customer behavior analysis. In... more
This paper aims to propose a novel idea of an embedded intelligent system where low cost embedded vision systems can analyze human behaviors to obtain interac-tivity and statistical data, mainly devoted to customer behavior analysis. In this project we addressed the need for new services into the shop, involving consumers more directly and instigating them to increase their satisfaction and, as a consequence, their purchases. To do this, technology is very important and allows making interactions between costumers and products and between customers and the environment of the shop a rich source of marketing analysis. We construct a novel system that uses vertical RGBD sensor for people counting and shelf interaction analysis, where the depth information is used to remove the affect of the appearance variation and to evaluate customers' activities inside the store and in front of the shelf, with products. Also group interactions are monitored and analyzed with the main goal of having a better knowledge of the customers' activities, using real data in real time. Even if preliminary, results are convincing and most of all the general architecture is affordable in this specific application, robust, easy to install and maintain and low cost.
Research Interests:
The importance of finding correct correspondences between two images is the major aspect in problems such as appearance-based robot localization and content-based image retrieval. Local feature matching has become a commonly used method... more
The importance of finding correct correspondences between two images is the major aspect in problems such as appearance-based robot localization and content-based image retrieval. Local feature matching has become a commonly used method to compare images, despite being highly probable that at least some of the matchings/correspondences it detects are incorrect. In this paper we describe a novel approach to local feature matching, named Feature Group Matching (FGM), to select stable features and obtain a more reliable similarity value between two images. The proposed technique is demonstrated to be translational, rotational and scaling invariant. Experimental evaluation was performed on large and heterogeneous datasets of images using SIFT and SURF, the actual state-of-art feature extractors. Results show that FGM avoids almost 95% of incorrect matchings, reduces the visual aliasing (number of images considered similar) and increases both robotic localization and image retrieval accuracy on the average of 13%.
Research Interests:
The main goal of the SIT-REM project is the design and the development of an interoperable web-GIS environment for the information retrieval and data editing/updating of the geobotanical and wildlife map of Marche Region. The vegetation,... more
The main goal of the SIT-REM project is the design and the development of an interoperable web-GIS environment for the information retrieval and data editing/updating of the geobotanical and wildlife map of Marche Region. The vegetation, plant landscape OPEN ACCESS ISPRS Int. J. Geo-Inf. 2014, 3 2 and faunistic analysis allow the realization of a regional information system for wildlife-geobotanical data. A main characteristic of the SIT-REM is its flexibility and interoperability, in particular, its ability to be easily updated with the insertion of new types of environmental, faunal or socioeconomic data and to generate analyses at any geographical (from regional to local) or quantitative level of detail. Different query levels obtain the latter: spatial queries, hybrid query builder and WMSs usable by means of a GIS. SIT-REM has been available online for more than a year and its use over this period has produced extensive data about users' experiences.
Research Interests:
Research Interests:
New smart objects to improve the quality of life in the ambient assisted living (AAL) scenario are capturing the interest of researchers and companies. In particular, novel assistive technologies are being developed to make accessible... more
New smart objects to improve the quality of life in the ambient assisted living (AAL) scenario are capturing the interest of researchers and companies. In particular, novel assistive technologies are being developed to make accessible street navigation to impaired people. The solution that we propose in this new application domain of intelligent transportation systems is a framework for a safe point-to-point navigation, owing to high-detailed road graphs, including sidewalks, crosswalks, and generic “obstacles.” The system is based on a low-cost modular sensor box (embedded hardware) interfaced with a mobile/phone application that acts as an intelligent navigator. The main novelty is the capability to sense the surrounding area while being able to perform a fast path replanning, owing to a real-time link to a remote server, if an obstacle is detected. The sensing is performed using different sensors, such as ultrasound, lidar, and a 77-GHz mid-range automotive radar (absolutely novel in the AAL context), which are processed and fused in the well-established robot operating system (ROS). We tested the framework by analyzing its performance in two different configurations and environments by using, respectively, a sonar and a laser rangefinder in a building scenario and a radar in an urban environment. Even if in both cases results demonstrated a quite good robustness in the obstacle detection with a quasi-real-time route replanning, we were mainly interested and succeeded in demonstrating the high flexibility and extensibility of our framework.