Ettore Stella
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ettore Stella has a total of 88 co-authors. Here are the top co-authors by number of shared publications:
A. Distante
ISSIA-CNR, Via Amendola 122/D, 70126, Bari, Italy
35 shared publicationsArcangelo Distante
CNR-ISSIA
20 shared publications- Massimiliano Nitti
Institute of Intelligent Systems for Automation (ISSIA-CNR) via Amendola 122/DO, 70126, Bari, Italy
17 shared publications - Giovanni Attolico
Institute of Intelligent Systems for Automation
15 shared publications - Nicola Ancona
CNR─Institute of Intelligent Industrial Technologies and Systems for Advanced Manufacturing, Via Amendola 122/o, 70126 Bari, Italy
15 shared publications A. Branca
13 shared publications
Latest Publications
- Open Access
- 8 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 93911-93923
A Review of Deep Learning-Based Anomaly Detection Strategies in Industry 4.0 Focused on Application Fields, Sensing Equipment, and Algorithms
Anomaly detection is a topic of interest in several areas, ranging from Industry 4.0 to Energy Management, Smart Agriculture, Cybersecurity, and Bioinformatics. In a wide sense, detecting anomalies implies finding samples generated within a process that differs from its standard data generation mechanisms. Identifying these samples is extremely important for a variety of reasons, depending on the specific application and scenario, ranging from the minimization of production costs to maintaining the required safety standards. As such, the increasing availability of wide networks of sensors that yield large amounts of data characterizing the processes under observation allowed the large adoption of deep learning techniques, which proved worthy of attention due to their capability of identifying anomalies with large precision, accuracy and reproducibility. Consequently, there is an extensive need to consolidate research results to provide a common framework to understand the topic and ensure a common foundation to establish future research trends. To respond to this need, this work systematically reviews the state of the art of anomaly detection in Industry 4.0, evaluating gaps in the current knowledge and proposing future directions of interest. To pursue this objective, three main dimensions have been considered: the scenario where the anomaly detection methodologies were applied, the sensing equipment used to gather data characterizing the underlying process, and the algorithm employed to properly interpret the phenomena. The study was conducted following the PRISMA protocol, which allowed the identification of a relevant selection of papers by extracting a meaningful dataset of 78 papers of interest. The analysis highlighted the diffusion of autoencoders in several configurations and application scenarios, highlighting their effectiveness and flexibility for anomaly detection.
- 8 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 93911-93923
Open AccessA Review of Deep Learning-Based Anomaly Detection Strategies in Industry 4.0 Focused on Application Fields, Sensing Equipment, and Algorithms
Anomaly detection is a topic of interest in several areas, ranging from Industry 4.0 to Energy Management, Smart Agriculture, Cybersecurity, and Bioinformatics. In a wide sense, detecting anomalies implies finding samples generated within a process that differs from its standard data generation mechanisms. Identifying these samples is extremely important for a variety of reasons, depending on the specific application and scenario, ranging from the minimization of production costs to maintaining the required safety standards. As such, the increasing availability of wide networks of sensors that yield large amounts of data characterizing the processes under observation allowed the large adoption of deep learning techniques, which proved worthy of attention due to their capability of identifying anomalies with large precision, accuracy and reproducibility. Consequently, there is an extensive need to consolidate research results to provide a common framework to understand the topic and ensure a common foundation to establish future research trends. To respond to this need, this work systematically reviews the state of the art of anomaly detection in Industry 4.0, evaluating gaps in the current knowledge and proposing future directions of interest. To pursue this objective, three main dimensions have been considered: the scenario where the anomaly detection methodologies were applied, the sensing equipment used to gather data characterizing the underlying process, and the algorithm employed to properly interpret the phenomena. The study was conducted following the PRISMA protocol, which allowed the identification of a relevant selection of papers by extracting a meaningful dataset of 78 papers of interest. The analysis highlighted the diffusion of autoencoders in several configurations and application scenarios, highlighting their effectiveness and flexibility for anomaly detection.
- Open Access
- 29 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 114638-114661
A Review on Deep Learning Techniques for Railway Infrastructure Monitoring
In the last decade, thanks to a widespread diffusion of powerful computing machines, artificial intelligence has been attracting the attention of the academic and industrial worlds on itself. This review aims to understand how the scientific community is approaching the use of deep-learning techniques in a particular industrial sector, the railway. This work is an in-depth analysis related to the last years of the way this new technology can try to provide answers even in a field where the primary requirement is to improve the already very high levels of safety. A strategic and constantly evolving field such as the railway sector could not remain extraneous to the use of this new and promising technology. The railway sector offers many aspects which can be investigated with these techniques. This work aims to expose the possible applications of deep learning in the railway sector established on the type of recovered information and the type of algorithms to be used accordingly.
- 29 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 114638-114661
Open AccessA Review on Deep Learning Techniques for Railway Infrastructure Monitoring
In the last decade, thanks to a widespread diffusion of powerful computing machines, artificial intelligence has been attracting the attention of the academic and industrial worlds on itself. This review aims to understand how the scientific community is approaching the use of deep-learning techniques in a particular industrial sector, the railway. This work is an in-depth analysis related to the last years of the way this new technology can try to provide answers even in a field where the primary requirement is to improve the already very high levels of safety. A strategic and constantly evolving field such as the railway sector could not remain extraneous to the use of this new and promising technology. The railway sector offers many aspects which can be investigated with these techniques. This work aims to expose the possible applications of deep learning in the railway sector established on the type of recovered information and the type of algorithms to be used accordingly.
- 25 September 2022
- Published by Springer Nature
- p. 851-861
A Digital Twin Approach for Smart Assembly of Aircraft Skin Panels with Mechanical Fasteners
- 25 September 2022
- Published by Springer Nature
- p. 851-861
A Digital Twin Approach for Smart Assembly of Aircraft Skin Panels with Mechanical Fasteners
- Open Access
- 20 June 2021
- Published by SPIE-Intl Soc Optical Eng
- Vol. 11785, 30
Post assembly quality inspection using multimodal sensing in aircraft manufacturing
Contactless, non-destructive testing has always been an important pillar in crucial tasks performed in industrial applications, including post-assembly testing oriented toward aircraft manufacturing. This work will examine the topic from the point of view of the quality check for the lining of aircraft interiors, such as sidewalls and hatracks, with the aim of improving safety of operation and comfort during flights, using an automatic approach guided by the usage of computer vision system. In particular, it will present a multimodal approach using a 3d snapshot sensor and a color camera, for identifying defects and anomalies that belong to two distinct categories, such as geometrical and surface defects, where, in the aircraft manufacturing sectors, due to the low-volume production, when compared with the automotive industry, such quality check operation tasks are still done manually, with a low level of automation. The proposed approach is showing potential and has been demonstrated on a proof-of-concept system prototype funded through a European Commission Horizon 2020 research project under the Clean Sky 2 umbrella aimed at the growth of the aviation sector.
- 20 June 2021
- Published by SPIE-Intl Soc Optical Eng
- Vol. 11785, 30
Open AccessPost assembly quality inspection using multimodal sensing in aircraft manufacturing
Contactless, non-destructive testing has always been an important pillar in crucial tasks performed in industrial applications, including post-assembly testing oriented toward aircraft manufacturing. This work will examine the topic from the point of view of the quality check for the lining of aircraft interiors, such as sidewalls and hatracks, with the aim of improving safety of operation and comfort during flights, using an automatic approach guided by the usage of computer vision system. In particular, it will present a multimodal approach using a 3d snapshot sensor and a color camera, for identifying defects and anomalies that belong to two distinct categories, such as geometrical and surface defects, where, in the aircraft manufacturing sectors, due to the low-volume production, when compared with the automotive industry, such quality check operation tasks are still done manually, with a low level of automation. The proposed approach is showing potential and has been demonstrated on a proof-of-concept system prototype funded through a European Commission Horizon 2020 research project under the Clean Sky 2 umbrella aimed at the growth of the aviation sector.
- Open Access
- 2 July 2020
- Published by MDPI AG in Journal of Imaging
- Vol. 6 (7) , 62
MH-MetroNet—A Multi-Head CNN for Passenger-Crowd Attendance Estimation
Knowing an accurate passengers attendance estimation on each metro car contributes to the safely coordination and sorting the crowd-passenger in each metro station. In this work we propose a multi-head Convolutional Neural Network (CNN) architecture trained to infer an estimation of passenger attendance in a metro car. The proposed network architecture consists of two main parts: a convolutional backbone, which extracts features over the whole input image, and a multi-head layers able to estimate a density map, needed to predict the number of people within the crowd image. The network performance is first evaluated on publicly available crowd counting datasets, including the ShanghaiTech part_A, ShanghaiTech part_B and UCF_CC_50, and then trained and tested on our dataset acquired in subway cars in Italy. In both cases a comparison is made against the most relevant and latest state of the art crowd counting architectures, showing that our proposed MH-MetroNet architecture outperforms in terms of Mean Absolute Error (MAE) and Mean Square Error (MSE) and passenger-crowd people number prediction.
- 2 July 2020
- Published by MDPI AG in Journal of Imaging
- Vol. 6 (7) , 62
Open AccessMH-MetroNet—A Multi-Head CNN for Passenger-Crowd Attendance Estimation
Knowing an accurate passengers attendance estimation on each metro car contributes to the safely coordination and sorting the crowd-passenger in each metro station. In this work we propose a multi-head Convolutional Neural Network (CNN) architecture trained to infer an estimation of passenger attendance in a metro car. The proposed network architecture consists of two main parts: a convolutional backbone, which extracts features over the whole input image, and a multi-head layers able to estimate a density map, needed to predict the number of people within the crowd image. The network performance is first evaluated on publicly available crowd counting datasets, including the ShanghaiTech part_A, ShanghaiTech part_B and UCF_CC_50, and then trained and tested on our dataset acquired in subway cars in Italy. In both cases a comparison is made against the most relevant and latest state of the art crowd counting architectures, showing that our proposed MH-MetroNet architecture outperforms in terms of Mean Absolute Error (MAE) and Mean Square Error (MSE) and passenger-crowd people number prediction.
- Open Access
- 5 May 2020
- Published by MDPI AG in Electronics
- Vol. 9 (5) , 758
Combined Color Semantics and Deep Learning for the Automatic Detection of Dolphin Dorsal Fins
Photo-identification is a widely used non-invasive technique in biological studies for understanding if a specimen has been seen multiple times only relying on specific unique visual characteristics. This information is essential to infer knowledge about the spatial distribution, site fidelity, abundance or habitat use of a species. Today there is a large demand for algorithms that can help domain experts in the analysis of large image datasets. For this reason, it is straightforward that the problem of identify and crop the relevant portion of an image is not negligible in any photo-identification pipeline. This paper approaches the problem of automatically cropping cetaceans images with a hybrid technique based on domain analysis and deep learning. Domain knowledge is applied for proposing relevant regions with the aim of highlighting the dorsal fins, then a binary classification of fin vs. no-fin is performed by a convolutional neural network. Results obtained on real images demonstrate the feasibility of the proposed approach in the automated process of large datasets of Risso’s dolphins photos, enabling its use on more complex large scale studies. Moreover, the results of this study suggest to extend this methodology to biological investigations of different species.
- 5 May 2020
- Published by MDPI AG in Electronics
- Vol. 9 (5) , 758
Open AccessCombined Color Semantics and Deep Learning for the Automatic Detection of Dolphin Dorsal Fins
Photo-identification is a widely used non-invasive technique in biological studies for understanding if a specimen has been seen multiple times only relying on specific unique visual characteristics. This information is essential to infer knowledge about the spatial distribution, site fidelity, abundance or habitat use of a species. Today there is a large demand for algorithms that can help domain experts in the analysis of large image datasets. For this reason, it is straightforward that the problem of identify and crop the relevant portion of an image is not negligible in any photo-identification pipeline. This paper approaches the problem of automatically cropping cetaceans images with a hybrid technique based on domain analysis and deep learning. Domain knowledge is applied for proposing relevant regions with the aim of highlighting the dorsal fins, then a binary classification of fin vs. no-fin is performed by a convolutional neural network. Results obtained on real images demonstrate the feasibility of the proposed approach in the automated process of large datasets of Risso’s dolphins photos, enabling its use on more complex large scale studies. Moreover, the results of this study suggest to extend this methodology to biological investigations of different species.
- Open Access
- 23 March 2020
- Published by Copernicus GmbH
3d stereo reconstruction of train paths for supporting maintenance operations
Railway infrastructure maintenance is a critical activity for ensuring safe train operations, due to the constant mechanical stress and wear and tear that crucial parts of the infrastructure such as rail and catenary undergo under use. Several methodologies and systems have been devised for diagnosing and prevent anomalies and minimize safety risks, that measure geometrical parameters and assess the way the infrastructure interacts with the train. While those techniques help at identifying anomalies when they occur, sometimes they are not able to provide enough evidence on the reasons behind the failure. A visual inspection can surely help in assessing the causes of failure, especially when they happen during train operations, without introducing any disruption to the service to schedule a specific check with a visit to the site. This work investigates the design of a stereo vision system that can be mounted on diagnostic trains so that a virtual visit to the site can be done when needed, by providing a 3d reconstruction of the surrounding of a train path. To achieve this, in the proposed system two color cameras can be mounted on the head or tail locomotive in a stereo configuration. They are triggered by an axle encoder mounted on the train at a fixed distance of 2 mt. This way the acquired point clouds can be registered together to achieve a full 3d reconstruction of the train path so that an offline, remote inspection of parts of the rails and catenaries can support in detecting, and possibly prevent, future anomalies. Moreover, since the reconstruction extends beyond train paths for a few meters, the 3d reconstruction of the railway can be exploited in different ways too, for example by preventing that foreign objects invade and jeopardize the train loading gauge.
- 23 March 2020
- Published by Copernicus GmbH
Open Access3d stereo reconstruction of train paths for supporting maintenance operations
Railway infrastructure maintenance is a critical activity for ensuring safe train operations, due to the constant mechanical stress and wear and tear that crucial parts of the infrastructure such as rail and catenary undergo under use. Several methodologies and systems have been devised for diagnosing and prevent anomalies and minimize safety risks, that measure geometrical parameters and assess the way the infrastructure interacts with the train. While those techniques help at identifying anomalies when they occur, sometimes they are not able to provide enough evidence on the reasons behind the failure. A visual inspection can surely help in assessing the causes of failure, especially when they happen during train operations, without introducing any disruption to the service to schedule a specific check with a visit to the site. This work investigates the design of a stereo vision system that can be mounted on diagnostic trains so that a virtual visit to the site can be done when needed, by providing a 3d reconstruction of the surrounding of a train path. To achieve this, in the proposed system two color cameras can be mounted on the head or tail locomotive in a stereo configuration. They are triggered by an axle encoder mounted on the train at a fixed distance of 2 mt. This way the acquired point clouds can be registered together to achieve a full 3d reconstruction of the train path so that an offline, remote inspection of parts of the rails and catenaries can support in detecting, and possibly prevent, future anomalies. Moreover, since the reconstruction extends beyond train paths for a few meters, the 3d reconstruction of the railway can be exploited in different ways too, for example by preventing that foreign objects invade and jeopardize the train loading gauge.
- 26 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Improving performance of an omnidirectional range sensor for 3D modeling of environments
High resolution in distance (range) measurements can be achieved by means of accurate instrumentations and precise analytical models. This paper reports an improvement in the estimation of distance measurements performed by an omnidirectional range sensor already presented in literature. This sensor exploits the principle of laser triangulation, together with the advantages brought by catadioptric systems, which allow the reduction of the sensor size without decreasing the resolution. Starting from a known analytical model in two dimensions (2D), the paper shows the development of a fully 3D formulation where all initial constrains are removed to gain in measurement accuracy. Specifically, the ray projection problem is solved by considering that both the emitter and the receiver have general poses in a global system of coordinates. Calibration is thus made to estimate their poses and compensate for any misalignment with respect to the 2D approximation. Results prove an increase in the measurement accuracy due to the more general formulation of the problem, with a remarkable decrease of the uncertainty.
- 26 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Improving performance of an omnidirectional range sensor for 3D modeling of environments
High resolution in distance (range) measurements can be achieved by means of accurate instrumentations and precise analytical models. This paper reports an improvement in the estimation of distance measurements performed by an omnidirectional range sensor already presented in literature. This sensor exploits the principle of laser triangulation, together with the advantages brought by catadioptric systems, which allow the reduction of the sensor size without decreasing the resolution. Starting from a known analytical model in two dimensions (2D), the paper shows the development of a fully 3D formulation where all initial constrains are removed to gain in measurement accuracy. Specifically, the ray projection problem is solved by considering that both the emitter and the receiver have general poses in a global system of coordinates. Calibration is thus made to estimate their poses and compensate for any misalignment with respect to the 2D approximation. Results prove an increase in the measurement accuracy due to the more general formulation of the problem, with a remarkable decrease of the uncertainty.
- 1 June 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Monitoring of indoor environments by change detection in point clouds
This paper describes a complete method for monitoring indoor environments. Three-dimensional (3D) point clouds are first acquired from the environment under investigation by means of a laser range scanner in order to obtain several 3D models to be compared. Input datasets are thus registered each other exploiting a reliable variant of the iterative closest point algorithm (ICP) assisted by the use of deletion masks. These terms work in cooperation with the resampling of the model surfaces to reduce significantly the errors in the estimation of the registration parameters. Once datasets are registered, deformation maps are displayed to help the user to detect changes within the environment. Deletion masks are again used to filter measurement artifacts from the comparison, thus highlighting only the actual alterations of the environment. Several experiments are performed for the analysis of an indoor environment, proving the capability of the proposed method to reliably estimate the presence of alterations.
- 1 June 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Monitoring of indoor environments by change detection in point clouds
This paper describes a complete method for monitoring indoor environments. Three-dimensional (3D) point clouds are first acquired from the environment under investigation by means of a laser range scanner in order to obtain several 3D models to be compared. Input datasets are thus registered each other exploiting a reliable variant of the iterative closest point algorithm (ICP) assisted by the use of deletion masks. These terms work in cooperation with the resampling of the model surfaces to reduce significantly the errors in the estimation of the registration parameters. Once datasets are registered, deformation maps are displayed to help the user to detect changes within the environment. Deletion masks are again used to filter measurement artifacts from the comparison, thus highlighting only the actual alterations of the environment. Several experiments are performed for the analysis of an indoor environment, proving the capability of the proposed method to reliably estimate the presence of alterations.
- 1 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 718-725
Tennis Player Segmentation for Semantic Behavior Analysis
Tennis player silhouette extraction is a preliminary step fundamental for any behavior analysis processing. Automatic systems for the evaluation of player tactics, in terms of position in the court, postures during the game and types of strokes, are highly desired for coaches and training purposes. These systems require accurate segmentation of players in order to apply posture analysis and high level semantic analysis. Background subtraction algorithms have been largely used in sportive context when fixed cameras are used. In this paper an innovative background subtraction algorithm is presented, which has been adapted to the tennis context and allows high precision in player segmentation both for the completeness of the extracted silhouettes. The algorithm is able to achieve interactive frame rates with up to 30 frames per second, and is suitable for smart cameras embedding. Real experiments demonstrate that the proposed approach is suitable in tennis contexts.
- 1 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 718-725
Tennis Player Segmentation for Semantic Behavior Analysis
Tennis player silhouette extraction is a preliminary step fundamental for any behavior analysis processing. Automatic systems for the evaluation of player tactics, in terms of position in the court, postures during the game and types of strokes, are highly desired for coaches and training purposes. These systems require accurate segmentation of players in order to apply posture analysis and high level semantic analysis. Background subtraction algorithms have been largely used in sportive context when fixed cameras are used. In this paper an innovative background subtraction algorithm is presented, which has been adapted to the tennis context and allows high precision in player segmentation both for the completeness of the extracted silhouettes. The algorithm is able to achieve interactive frame rates with up to 30 frames per second, and is suitable for smart cameras embedding. Real experiments demonstrate that the proposed approach is suitable in tennis contexts.