Mihael Presecan - Academia.edu (original) (raw)

Uploads

Papers by Mihael Presecan

Research paper thumbnail of Mapiranje i lokalizacija NAO robota u prostoru pomoću RGB-D senzora

RGB-D commercial sensors are giving strong alternative for SLAM systems. This work has presented ... more RGB-D commercial sensors are giving strong alternative for SLAM systems. This work has presented a Visual SLAM implemented with Microsoft Kinect sensor which had been added to NAO robot. Furthermore, we discussed about the influence of the sensor on stability of a robot, and also it was given small evaluation of the localisation given by rgbdlsam system. All the work was implemented on ROS platform.

Research paper thumbnail of Object Classification for Child Behavior Observation in the Context of Autism Diagnostics Using a Deep Learning-based Approach

2018 26th International Conference on Software, Telecommunications and Computer Networks (SoftCOM)

In this paper we demonstrate the effectiveness of a deep learning approach for object detection a... more In this paper we demonstrate the effectiveness of a deep learning approach for object detection and classification using a mono-vision feedback of a NAO humanoid robot for assessing the child’s behavior during a free play with standardized toys. The free play is one of the tasks contained in the standard ADOS-2 autism spectrum disorder diagnostic protocol used by clinicians. In order to make an accurate, robust and fast object detector, a new data set for learning and testing has been created to enable a reliable assessment of the child’s behavior while playing with the toys. This has also led to the development of algorithms and mechanism to assess child’s attention based on the toys that the child is playing with. This paper concludes with the discussion about the challenges encountered and their solutions, as well as about the prospective development goals focused on achieving more robust and accurate child attention analyzer.

Research paper thumbnail of Klasifikacija objekata za promatranje djetetovog ponašanja u kontekstu dijagnostike autizma putem pristupa dubinskog učenja

Ovaj rad postavlja temelje za novi zadatak u ADORE protokolu - Free-play analize. Kljucni problem... more Ovaj rad postavlja temelje za novi zadatak u ADORE protokolu - Free-play analize. Kljucni problem kojega je potrebno rijesiti je izraditi precizan,

Research paper thumbnail of Object Classification for Child Behavior Observation in the Context of Autism Diagnostics Using a Deep Learning-based Approach

2018 26th International Conference on Software, Telecommunications and Computer Networks (SoftCOM), 2018

In this paper we demonstrate the effectiveness of a deep learning approach for object detection a... more In this paper we demonstrate the effectiveness of a deep learning approach for object detection and classification using a mono-vision feedback of a NAO humanoid robot for assessing the child’s behavior during a free play with standardized toys. The free play is one of the tasks contained in the standard ADOS-2 autism spectrum disorder diagnostic protocol used by clinicians. In order to make an accurate, robust and fast object detector, a new data set for learning and testing has been created to enable a reliable assessment of the child’s behavior while playing with the toys. This has also led to the development of algorithms and mechanism to assess child’s attention based on the toys that the child is playing with. This paper concludes with the discussion about the challenges encountered and their solutions, as well as about the prospective development goals focused on achieving more robust and accurate child attention analyzer.

Research paper thumbnail of Mapiranje i lokalizacija NAO robota u prostoru pomoću RGB-D senzora

RGB-D commercial sensors are giving strong alternative for SLAM systems. This work has presented ... more RGB-D commercial sensors are giving strong alternative for SLAM systems. This work has presented a Visual SLAM implemented with Microsoft Kinect sensor which had been added to NAO robot. Furthermore, we discussed about the influence of the sensor on stability of a robot, and also it was given small evaluation of the localisation given by rgbdlsam system. All the work was implemented on ROS platform.

Research paper thumbnail of Object Classification for Child Behavior Observation in the Context of Autism Diagnostics Using a Deep Learning-based Approach

2018 26th International Conference on Software, Telecommunications and Computer Networks (SoftCOM)

In this paper we demonstrate the effectiveness of a deep learning approach for object detection a... more In this paper we demonstrate the effectiveness of a deep learning approach for object detection and classification using a mono-vision feedback of a NAO humanoid robot for assessing the child’s behavior during a free play with standardized toys. The free play is one of the tasks contained in the standard ADOS-2 autism spectrum disorder diagnostic protocol used by clinicians. In order to make an accurate, robust and fast object detector, a new data set for learning and testing has been created to enable a reliable assessment of the child’s behavior while playing with the toys. This has also led to the development of algorithms and mechanism to assess child’s attention based on the toys that the child is playing with. This paper concludes with the discussion about the challenges encountered and their solutions, as well as about the prospective development goals focused on achieving more robust and accurate child attention analyzer.

Research paper thumbnail of Klasifikacija objekata za promatranje djetetovog ponašanja u kontekstu dijagnostike autizma putem pristupa dubinskog učenja

Ovaj rad postavlja temelje za novi zadatak u ADORE protokolu - Free-play analize. Kljucni problem... more Ovaj rad postavlja temelje za novi zadatak u ADORE protokolu - Free-play analize. Kljucni problem kojega je potrebno rijesiti je izraditi precizan,

Research paper thumbnail of Object Classification for Child Behavior Observation in the Context of Autism Diagnostics Using a Deep Learning-based Approach

2018 26th International Conference on Software, Telecommunications and Computer Networks (SoftCOM), 2018

In this paper we demonstrate the effectiveness of a deep learning approach for object detection a... more In this paper we demonstrate the effectiveness of a deep learning approach for object detection and classification using a mono-vision feedback of a NAO humanoid robot for assessing the child’s behavior during a free play with standardized toys. The free play is one of the tasks contained in the standard ADOS-2 autism spectrum disorder diagnostic protocol used by clinicians. In order to make an accurate, robust and fast object detector, a new data set for learning and testing has been created to enable a reliable assessment of the child’s behavior while playing with the toys. This has also led to the development of algorithms and mechanism to assess child’s attention based on the toys that the child is playing with. This paper concludes with the discussion about the challenges encountered and their solutions, as well as about the prospective development goals focused on achieving more robust and accurate child attention analyzer.

Log In