References of "Cazzato, Dario 50030451"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailA case study on the impact of masking moving objects on the camera pose regression with CNNs
Cimarelli, Claudio UL; Cazzato, Dario UL; Olivares Mendez, Miguel Angel UL et al

in 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) (2019, November 25)

Robot self-localization is essential for operating autonomously in open environments. When cameras are the main source of information for retrieving the pose, numerous challenges are posed by the presence ... [more ▼]

Robot self-localization is essential for operating autonomously in open environments. When cameras are the main source of information for retrieving the pose, numerous challenges are posed by the presence of dynamic objects, due to occlusion and continuous changes in the appearance. Recent research on global localization methods focused on using a single (or multiple) Convolutional Neural Network (CNN) to estimate the 6 Degrees of Freedom (6-DoF) pose directly from a monocular camera image. In contrast with the classical approaches using engineered feature detector, CNNs are usually more robust to environmental changes in light and to occlusions in outdoor scenarios. This paper contains an attempt to empirically demonstrate the ability of CNNs to ignore dynamic elements, such as pedestrians or cars, through learning. For this purpose, we pre-process a dataset for pose localization with an object segmentation network, masking potentially moving objects. Hence, we compare the pose regression CNN trained and/or tested on the set of masked images and the original one. Experimental results show that the performances of the two training approaches are similar, with a slight reduction of the error when hiding occluding objects from the views. [less ▲]

Detailed reference viewed: 40 (8 UL)
Full Text
Peer Reviewed
See detailFaster Visual-Based Localization with Mobile-PoseNet
Cimarelli, Claudio UL; Cazzato, Dario UL; Olivares Mendez, Miguel Angel UL et al

in International Conference on Computer Analysis of Images and Patterns (2019, August 22)

Precise and robust localization is of fundamental importance for robots required to carry out autonomous tasks. Above all, in the case of Unmanned Aerial Vehicles (UAVs), efficiency and reliability are ... [more ▼]

Precise and robust localization is of fundamental importance for robots required to carry out autonomous tasks. Above all, in the case of Unmanned Aerial Vehicles (UAVs), efficiency and reliability are critical aspects in developing solutions for localization due to the limited computational capabilities, payload and power constraints. In this work, we leverage novel research in efficient deep neural architectures for the problem of 6 Degrees of Freedom (6-DoF) pose estimation from single RGB camera images. In particular, we introduce an efficient neural network to jointly regress the position and orientation of the camera with respect to the navigation environment. Experimental results show that the proposed network is capable of retaining similar results with respect to the most popular state of the art methods while being smaller and with lower latency, which are fundamental aspects for real-time robotics applications. [less ▲]

Detailed reference viewed: 71 (4 UL)
Full Text
Peer Reviewed
See detailDeep learning based semantic situation awareness system for multirotor aerial robots using LIDAR
Sanchez Lopez, Jose Luis UL; Sampedro, Carlos; Cazzato, Dario UL et al

in 2019 International Conference on Unmanned Aircraft Systems (ICUAS) (2019, June)

In this work, we present a semantic situation awareness system for multirotor aerial robots, based on 2D LIDAR measurements, targeting the understanding of the environment and assuming to have a precise ... [more ▼]

In this work, we present a semantic situation awareness system for multirotor aerial robots, based on 2D LIDAR measurements, targeting the understanding of the environment and assuming to have a precise robot localization as an input of our algorithm. Our proposed situation awareness system calculates a semantic map of the objects of the environment as a list of circles represented by their radius, and the position and the velocity of their center in world coordinates. Our proposed algorithm includes three main parts. First, the LIDAR measurements are preprocessed and an object segmentation clusters the candidate objects present in the environment. Secondly, a Convolutional Neural Network (CNN) that has been designed and trained using an artificially generated dataset, computes the radius and the position of the center of individual circles in sensor coordinates. Finally, an indirect-EKF provides the estimate of the semantic map in world coordinates, including the velocity of the center of the circles in world coordinates.We have quantitative and qualitative evaluated the performance of our proposed situation awareness system by means of Software-In-The-Loop simulations using VRep with one and multiple static and moving cylindrical objects in the scene, obtaining results that support our proposed algorithm. In addition, we have demonstrated that our proposed algorithm is capable of handling real environments thanks to real laboratory experiments with non-cylindrical static (i.e. a barrel) and moving (i.e. a person) objects. [less ▲]

Detailed reference viewed: 67 (1 UL)
Full Text
Peer Reviewed
See detailFlexible body scanning without template models
Munoz-Salinas, Rafael; Sarmadi, Hamid; Cazzato, Dario UL et al

in Signal Processing (2019), 154

The apparition of low-cost depth cameras has lead to the development of several reconstruction methods that work well with rigid objects, but tend to fail when used to manually scan a standing person ... [more ▼]

The apparition of low-cost depth cameras has lead to the development of several reconstruction methods that work well with rigid objects, but tend to fail when used to manually scan a standing person. Specific methods for body scanning have been proposed, but they have some ad-hoc requirements that make them unsuitable in a wide range of applications: they either require rotation platforms, multiple sensors and a priori template model. Scanning a person with a hand-held low-cost depth camera is still a challenging unsolved problem. This work proposes a novel solution to easily scan standing persons by combining depth information with fiducial markers without using a template model. In our approach, a set of markers placed in the ground are used to improve camera tracking by a novel algorithm that fuses depth information with the known location of the markers. The proposed method analyzes the video sequence and automatically divides it into fragments that are employed to build partial overlapping scans of the subject. Then, a registration step (both rigid and non-rigid) is applied to create a final mesh of the scanned subject. The proposed method has been compared with the state-of-the-art KinectFusion [1], ElasticFusion [2], ORB-SLAM [3, 4], and BundleFusion [5] methods, exhibiting superior performance. [less ▲]

Detailed reference viewed: 95 (3 UL)
Full Text
Peer Reviewed
See detailUnderstanding and Modelling Human Attention for Soft Biometrics Purposes
Cazzato, Dario UL; Leo, Marco; Carcagnì, Pierluigi et al

in AIVR 2019: Proceedings of the 2019 3rd International Conference on Artificial Intelligence and Virtual Reality (2019)

Detailed reference viewed: 70 (10 UL)
Full Text
Peer Reviewed
See detailAn image processing pipeline to segment iris for unconstrained cow identification system
Larregui, Juan I.; Cazzato, Dario UL; Castro, Silvia M.

in Open Computer Science (2019), 9(1), 145--159

Detailed reference viewed: 30 (1 UL)
Full Text
Peer Reviewed
See detailA non-invasive tool for attention-deficit disorder analysis based on gaze tracks
Cazzato, Dario UL; Castro, Silvia M.; Agamennoni, Osvaldo et al

in Proceedings of the 2nd International Conference on Applications of Intelligent Systems (2019)

Detailed reference viewed: 27 (1 UL)
Full Text
Peer Reviewed
See detailVideo Indexing Using Face Appearance and Shot Transition Detection
Cazzato, Dario UL; Leo, Marco; Carcagni, Pierluigi et al

in Proceedings of the IEEE International Conference on Computer Vision Workshops (2019)

Detailed reference viewed: 34 (1 UL)
Full Text
Peer Reviewed
See detailReal-Time Human Head Imitation for Humanoid Robots
Cazzato, Dario UL; Cimarelli, Claudio UL; Sanchez Lopez, Jose Luis UL et al

in Proceedings of the 2019 3rd International Conference on Artificial Intelligence and Virtual Reality (2019)

Detailed reference viewed: 59 (11 UL)
Full Text
Peer Reviewed
See detailVision-Based Aircraft Pose Estimation for UAVs Autonomous Inspection without Fiducial Markers
Cazzato, Dario UL; Olivares Mendez, Miguel Angel UL; Sanchez Lopez, Jose Luis UL et al

in IECON 2019-45th Annual Conference of the IEEE Industrial Electronics Society (2019)

Detailed reference viewed: 43 (4 UL)
Full Text
Peer Reviewed
See detailReal-time gaze estimation via pupil center tracking
Cazzato, Dario UL; Dominio, Fabio; Manduchi, Roberto et al

in Paladyn. Journal of Behavioral Robotics (2018)

Automatic gaze estimation not based on commercial and expensive eye tracking hardware solutions can enable several applications in the fields of human computer interaction (HCI) and human behavior ... [more ▼]

Automatic gaze estimation not based on commercial and expensive eye tracking hardware solutions can enable several applications in the fields of human computer interaction (HCI) and human behavior analysis. It is therefore not surprising that several related techniques and methods have been investigated in recent years. However, very few camera-based systems proposed in the literature are both real-time and robust. In this work, we propose a real-time user-calibration-free gaze estimation system that does not need person-dependent calibration, can deal with illumination changes and head pose variations, and can work with a wide range of distances from the camera. Our solution is based on a 3-D appearance-based method that processes the images from a built-in laptop camera. Real-time performance is obtained by combining head pose information with geometrical eye features to train a machine learning algorithm. Our method has been validated on a data set of images of users in natural environments, and shows promising results. The possibility of a real-time implementation, combined with the good quality of gaze tracking, make this system suitable for various HCI applications. [less ▲]

Detailed reference viewed: 54 (0 UL)
Full Text
Peer Reviewed
See detailAn Ecological Visual Exploration Tool to Support the Analysis of Visual Processing Pathways in Children with Autism Spectrum Disorders
Cazzato, Dario UL; Leo, Marco; Distante, Cosimo et al

in Journal of Imaging (2018)

Recent improvements in the field of assistive technologies have led to innovative solutions aiming at increasing the capabilities of people with disability, helping them in daily activities with ... [more ▼]

Recent improvements in the field of assistive technologies have led to innovative solutions aiming at increasing the capabilities of people with disability, helping them in daily activities with applications that span from cognitive impairments to developmental disabilities. In particular, in the case of Autism Spectrum Disorder (ASD), the need to obtain active feedback in order to extract subsequently meaningful data becomes of fundamental importance. In this work, a study about the possibility of understanding the visual exploration in children with ASD is presented. In order to obtain an automatic evaluation, an algorithm for free (i.e., without constraints, nor using additional hardware, infrared (IR) light sources or other intrusive methods) gaze estimation is employed. Furthermore, no initial calibration is required. It allows the user to freely rotate the head in the field of view of the sensor, and it is insensitive to the presence of eyeglasses, hats or particular hairstyles. These relaxations of the constraints make this technique particularly suitable to be used in the critical context of autism, where the child is certainly not inclined to employ invasive devices, nor to collaborate during calibration procedures.The evaluation of children’s gaze trajectories through the proposed solution is presented for the purpose of an Early Start Denver Model (ESDM) program built on the child’s spontaneous interests and game choice delivered in a natural setting. [less ▲]

Detailed reference viewed: 63 (1 UL)