Proceedings of ICSIPNN '94. International Conference on Speech, Image Processing and Neural Networks
2. The Basis Of The Method In this paper we present a texture analysis and classification method ... more 2. The Basis Of The Method In this paper we present a texture analysis and classification method based on the computation of highorder statistics of gray-levels or selected features. The computation of these high-order statistics can be performed in parallel in non-overlapping windows that cover the full image. Classification is performed by neural networks. In this extended summary results are presented for back-propagation networks only, but several other types of neural nets were also tested.
Proceedings of IEEE International Conference on Industrial Technology 2000 (IEEE Cat. No.00TH8482)
This article addresses the problem of recovering a tridimensional scene from only one uncalibrate... more This article addresses the problem of recovering a tridimensional scene from only one uncalibrated static camera and images from planar mirrors. We present a linear solution for 3D Euclidean reconstruction based on multiocular geometry, epipolar geometry and projective geometric properties. From the recovered points of the scene we can obtain information related with distances, areas, curvatures, dimensions and even volumes of its objects. A system based on this technique could be applied on the industry, in tasks of great importance, such as the quality tests and metrology inspection. The system is simple, low cost and could achieve good performance. A paradigm for model fitting with applications to image analysis and automated cartography", Communications of the ACM,
Detecção de Mudança e Recuperação de Forma em Mapas 3D Baseados em Nuvens de Pontos
There are several applications for which it is important to both detect and modelling changes. In... more There are several applications for which it is important to both detect and modelling changes. In the context of 3D point cloud, detecting changes constitutes a challenging task due to the large amounts of data that must be compared, as well as shape retrieval needs to deal with large kind of shape and with noise in the data. Thus, this paper proposes a framework to efficiently detect and represent changes through a compact model. Initially, the point cloud is simplified in order to preserve the geometric characteristics. Moreover, a combined approach using Gaussian Mixture Models (GMM) and the Earth Mover's Distance (EMD) is proposed, together with a greedy technique. It allows detect and segment changes, through an previous knowledge about the environment map. The 3D shape retrieval is achieved using two different approaches. The first approach is a new method that we developed which directly retrieves basic shapes the detected shape in the Gaussian space (planes, spheres and ...
perception sys- tems related with the robotic manipulation strategies used to dexterously interac... more perception sys- tems related with the robotic manipulation strategies used to dexterously interact with deformable objects in the envi- ronment. In this context, the robotic dexterous manipulation of ob- jects require that the framework used to represent the char- acteristics of the deformable manipulated objects should be suitable to receive inputs from multiple exploratory elements (multi-ngered robotic hands) and to progressively update
Representation of 3D Space and Sensor Modelling Within a Probabilistic Framework
Springer Tracts in Advanced Robotics, 2014
For living organisms, perception can be defined as a set of cognitive processes, in the sense tha... more For living organisms, perception can be defined as a set of cognitive processes, in the sense that it consists in the processing of sensorial data in order to generate essential information with the purpose of building a coherent and useful representation of the surrounding world. Perception has been paramount for living beings, its importance having propagated from supporting the original primal objective of survival up to the more recent evolutionary purpose of promoting social interaction.
This paper presents a platform being developed in a large scale national project that aims to cre... more This paper presents a platform being developed in a large scale national project that aims to create an ecosystem of services and applications where patients, relatives and healthcare professionals can cooperate in day-today activities. It will implement functionalities for managing medical, social and context information, for integrating mobile devices, remote control and sensors, with insurance of information security.
The human ability of unconsciously attending to social signals, together with other even more pri... more The human ability of unconsciously attending to social signals, together with other even more primitive automatic attentional processes, has been argued in the literature to play an important part in social interaction. In this paper, we will argue that the evaluation of the influence of these unconscious perceptual processes in social interaction with robots has been addressed in previous research in many cases in an ad hoc fashion, while, on the contrary, it should be tackled systematically, bridging more conventional measures from robotics with criteria stemming from ideas used in human studies in psychology, neuroscience and social sciences. We will start by establishing an experimental canvas that will limit complexity to a sustainable level, while still fostering adaptive behaviour and variability in interaction. We will then present a brief assessment of the criteria used in the HRI literature to study this particular type of experiments in order to evaluate success, followed by a suggestion of adaptation of other criteria used in human studies, which has only been sporadically and non-systematically performed in HRI research-in most cases, more as expression of future intents. We will conclude by proposing a methodology for this evaluation, to be applied in the project "Coordinated Attention for Social Interaction with Robots" sponsored by the Portuguese Foundation for Science and Technology (FCT).
Proceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots, 2005
This article describes a method to track 3D articulated structures from a monocular perspective i... more This article describes a method to track 3D articulated structures from a monocular perspective image sequence using a particle filter. This structure is composed of a set of linked degenerated quadrics (cones) which are truncated by pairs of planes also modelled as degenerated quadrics. This set of truncated cones is connected by joints containing one or more degrees of freedom. The method is based upon the estimation of the contours of the structure's silhouette projected on the image plane, to validate each of the particles which correspond to proposed configurations. This validation is performed using a criterion that combines a measure based on the contours, a measure of similarity between the colour distribution around a point on the structure and a reference distribution, and other criteria that reinforce the overall cost function. The results show the feasibility of the approach when using a single camera to track a 3D model containing eight degrees of freedom.
Case-Study: Bayesian Hierarchy for Active Perception
Springer Tracts in Advanced Robotics, 2014
Consider the following scenario (Fig. 8.1) - a moving observer is presented with a non-static 3D ... more Consider the following scenario (Fig. 8.1) - a moving observer is presented with a non-static 3D scene containing several moving entities, probably generating some kind of sound: how does this observer perceive the 3D structure, motion trajectory and velocity of all entities in the scene, while taking into account the ambiguities and conflicts inherent to the perceptual process?
Perception is naturally surpassed toward action; better yet, it can be revealed only in and throu... more Perception is naturally surpassed toward action; better yet, it can be revealed only in and through projects of action.
Lecture Notes in Control and Information Sciences, 1998
In this paper we discuss the use of active vision for the development of autonomous systems. Acti... more In this paper we discuss the use of active vision for the development of autonomous systems. Active vision systems are essentially based on biological motivations. Two systems with potential application to surveillance are described. Both systems behave as watchrobots. One of them involves the integration of an active vision system in a mobile platform. The second system can track non-rigid
<title>Grid-based framework for sensorial data integration in mobile robots</title>
Sensor Fusion and Decentralized Control in Autonomous Robotic Systems, 1997
ABSTRACT This article presents a method to combine data from two sensorial modalities, a stereosc... more ABSTRACT This article presents a method to combine data from two sensorial modalities, a stereoscopic vision based sensor and a ring of ultrasonic sensors, in a grid based framework for obstacle detection and avoidance with mobile robots. The sensors&#39; data is combined using Dempster-Shafer theory. This theory allows the combination of multiple sensorial data sources in a way that they are mutually enhanced and validated. A connectionist grid is used to support these operations and the environment modeling. Each grid node maps a configuration in a discrete subset of the robot&#39;s configuration space. The process used to obtain obstacle presence information from the stereoscopic setup and ultrasonic sensors is explained in detail. Detected obstacles result in sets of restricted configurations. The grid dynamic behavior allows the iterative computation of a repulsive potential field, which rises in the vicinity of the restricted configurations. As new information is collected by the sensors during the robot&#39;s motion so new configurations are marked as restrict and the potential field changes accordingly. Since this process occurs in real time, the computed potential field can be used to navigate the robot avoiding the detected obstacles. Experimental results are presented to support the used sensor models, the integration procedure and the control strategy.
Three-dimensional planar profile sampling of surfaces is a very common method of structural recov... more Three-dimensional planar profile sampling of surfaces is a very common method of structural recovery in 3D scanning. In handheld 3D scanners, this has scarcely ever been taken into account resulting in poor precision ratings. Therefore, in this text we will describe a novel use of the profiling geometrical context to derive an intuitive and physically meaningful approach on solving the 3D profile registration problem. We will finish by describing the global optimisation algorithm and by showing experimental results achieved with a 3D scanner prototype comprising a camera, a laser-plane projector and a pose sensor.
Proceedings of ICSIPNN '94. International Conference on Speech, Image Processing and Neural Networks
2. The Basis Of The Method In this paper we present a texture analysis and classification method ... more 2. The Basis Of The Method In this paper we present a texture analysis and classification method based on the computation of highorder statistics of gray-levels or selected features. The computation of these high-order statistics can be performed in parallel in non-overlapping windows that cover the full image. Classification is performed by neural networks. In this extended summary results are presented for back-propagation networks only, but several other types of neural nets were also tested.
Proceedings of IEEE International Conference on Industrial Technology 2000 (IEEE Cat. No.00TH8482)
This article addresses the problem of recovering a tridimensional scene from only one uncalibrate... more This article addresses the problem of recovering a tridimensional scene from only one uncalibrated static camera and images from planar mirrors. We present a linear solution for 3D Euclidean reconstruction based on multiocular geometry, epipolar geometry and projective geometric properties. From the recovered points of the scene we can obtain information related with distances, areas, curvatures, dimensions and even volumes of its objects. A system based on this technique could be applied on the industry, in tasks of great importance, such as the quality tests and metrology inspection. The system is simple, low cost and could achieve good performance. A paradigm for model fitting with applications to image analysis and automated cartography", Communications of the ACM,
Detecção de Mudança e Recuperação de Forma em Mapas 3D Baseados em Nuvens de Pontos
There are several applications for which it is important to both detect and modelling changes. In... more There are several applications for which it is important to both detect and modelling changes. In the context of 3D point cloud, detecting changes constitutes a challenging task due to the large amounts of data that must be compared, as well as shape retrieval needs to deal with large kind of shape and with noise in the data. Thus, this paper proposes a framework to efficiently detect and represent changes through a compact model. Initially, the point cloud is simplified in order to preserve the geometric characteristics. Moreover, a combined approach using Gaussian Mixture Models (GMM) and the Earth Mover's Distance (EMD) is proposed, together with a greedy technique. It allows detect and segment changes, through an previous knowledge about the environment map. The 3D shape retrieval is achieved using two different approaches. The first approach is a new method that we developed which directly retrieves basic shapes the detected shape in the Gaussian space (planes, spheres and ...
perception sys- tems related with the robotic manipulation strategies used to dexterously interac... more perception sys- tems related with the robotic manipulation strategies used to dexterously interact with deformable objects in the envi- ronment. In this context, the robotic dexterous manipulation of ob- jects require that the framework used to represent the char- acteristics of the deformable manipulated objects should be suitable to receive inputs from multiple exploratory elements (multi-ngered robotic hands) and to progressively update
Representation of 3D Space and Sensor Modelling Within a Probabilistic Framework
Springer Tracts in Advanced Robotics, 2014
For living organisms, perception can be defined as a set of cognitive processes, in the sense tha... more For living organisms, perception can be defined as a set of cognitive processes, in the sense that it consists in the processing of sensorial data in order to generate essential information with the purpose of building a coherent and useful representation of the surrounding world. Perception has been paramount for living beings, its importance having propagated from supporting the original primal objective of survival up to the more recent evolutionary purpose of promoting social interaction.
This paper presents a platform being developed in a large scale national project that aims to cre... more This paper presents a platform being developed in a large scale national project that aims to create an ecosystem of services and applications where patients, relatives and healthcare professionals can cooperate in day-today activities. It will implement functionalities for managing medical, social and context information, for integrating mobile devices, remote control and sensors, with insurance of information security.
The human ability of unconsciously attending to social signals, together with other even more pri... more The human ability of unconsciously attending to social signals, together with other even more primitive automatic attentional processes, has been argued in the literature to play an important part in social interaction. In this paper, we will argue that the evaluation of the influence of these unconscious perceptual processes in social interaction with robots has been addressed in previous research in many cases in an ad hoc fashion, while, on the contrary, it should be tackled systematically, bridging more conventional measures from robotics with criteria stemming from ideas used in human studies in psychology, neuroscience and social sciences. We will start by establishing an experimental canvas that will limit complexity to a sustainable level, while still fostering adaptive behaviour and variability in interaction. We will then present a brief assessment of the criteria used in the HRI literature to study this particular type of experiments in order to evaluate success, followed by a suggestion of adaptation of other criteria used in human studies, which has only been sporadically and non-systematically performed in HRI research-in most cases, more as expression of future intents. We will conclude by proposing a methodology for this evaluation, to be applied in the project "Coordinated Attention for Social Interaction with Robots" sponsored by the Portuguese Foundation for Science and Technology (FCT).
Proceedings of 2005 5th IEEE-RAS International Conference on Humanoid Robots, 2005
This article describes a method to track 3D articulated structures from a monocular perspective i... more This article describes a method to track 3D articulated structures from a monocular perspective image sequence using a particle filter. This structure is composed of a set of linked degenerated quadrics (cones) which are truncated by pairs of planes also modelled as degenerated quadrics. This set of truncated cones is connected by joints containing one or more degrees of freedom. The method is based upon the estimation of the contours of the structure's silhouette projected on the image plane, to validate each of the particles which correspond to proposed configurations. This validation is performed using a criterion that combines a measure based on the contours, a measure of similarity between the colour distribution around a point on the structure and a reference distribution, and other criteria that reinforce the overall cost function. The results show the feasibility of the approach when using a single camera to track a 3D model containing eight degrees of freedom.
Case-Study: Bayesian Hierarchy for Active Perception
Springer Tracts in Advanced Robotics, 2014
Consider the following scenario (Fig. 8.1) - a moving observer is presented with a non-static 3D ... more Consider the following scenario (Fig. 8.1) - a moving observer is presented with a non-static 3D scene containing several moving entities, probably generating some kind of sound: how does this observer perceive the 3D structure, motion trajectory and velocity of all entities in the scene, while taking into account the ambiguities and conflicts inherent to the perceptual process?
Perception is naturally surpassed toward action; better yet, it can be revealed only in and throu... more Perception is naturally surpassed toward action; better yet, it can be revealed only in and through projects of action.
Lecture Notes in Control and Information Sciences, 1998
In this paper we discuss the use of active vision for the development of autonomous systems. Acti... more In this paper we discuss the use of active vision for the development of autonomous systems. Active vision systems are essentially based on biological motivations. Two systems with potential application to surveillance are described. Both systems behave as watchrobots. One of them involves the integration of an active vision system in a mobile platform. The second system can track non-rigid
<title>Grid-based framework for sensorial data integration in mobile robots</title>
Sensor Fusion and Decentralized Control in Autonomous Robotic Systems, 1997
ABSTRACT This article presents a method to combine data from two sensorial modalities, a stereosc... more ABSTRACT This article presents a method to combine data from two sensorial modalities, a stereoscopic vision based sensor and a ring of ultrasonic sensors, in a grid based framework for obstacle detection and avoidance with mobile robots. The sensors&#39; data is combined using Dempster-Shafer theory. This theory allows the combination of multiple sensorial data sources in a way that they are mutually enhanced and validated. A connectionist grid is used to support these operations and the environment modeling. Each grid node maps a configuration in a discrete subset of the robot&#39;s configuration space. The process used to obtain obstacle presence information from the stereoscopic setup and ultrasonic sensors is explained in detail. Detected obstacles result in sets of restricted configurations. The grid dynamic behavior allows the iterative computation of a repulsive potential field, which rises in the vicinity of the restricted configurations. As new information is collected by the sensors during the robot&#39;s motion so new configurations are marked as restrict and the potential field changes accordingly. Since this process occurs in real time, the computed potential field can be used to navigate the robot avoiding the detected obstacles. Experimental results are presented to support the used sensor models, the integration procedure and the control strategy.
Three-dimensional planar profile sampling of surfaces is a very common method of structural recov... more Three-dimensional planar profile sampling of surfaces is a very common method of structural recovery in 3D scanning. In handheld 3D scanners, this has scarcely ever been taken into account resulting in poor precision ratings. Therefore, in this text we will describe a novel use of the profiling geometrical context to derive an intuitive and physically meaningful approach on solving the 3D profile registration problem. We will finish by describing the global optimisation algorithm and by showing experimental results achieved with a 3D scanner prototype comprising a camera, a laser-plane projector and a pose sensor.
Uploads
Papers by Jorge Dias