Computer Intelligence in Recognition and Support of Human Activities

group leader

prof. dr. sc. Vladan Papić

associates

izv. prof. dr. sc. Josip Musić
izv. prof. dr. sc. Ivan Zoraja
doc. dr. sc. Tea Marasović
Stanko Kružić, assistant

Active alumni

prof. dr. sc. Jadranka Marasović

PhD Students

Mirela Kundid, PhD student

Nediljko Bugarin, PhD student

Research Topics

  1. Object detection and tracking
  2. Robotics
  3. Human – machine interaction
  4. Control and optimization
  5. Machine learning
  6. Biomechanics
  7. Sports Analysis
  8. GPGPU accelerated image processing

Description of the Laboratory and equipment

Research group uses 3 laboratories: Laboratory for biomechanics, automatics and systems,  Laboratory for expert systems, machine learning and image processing and Laboratory for distributed systems and software engineering. Labs are equipped with various devices for measurements in biomechanics (force plate, EMG, inertial sensors XSens) and image acquisition (camcorders, 3D cameras, high-speed cameras, …), as well as other devices for signal acquisition (sensor glove, accelerometers, Kinect). Also, labs are equipped with several UAVs, mobile robotic platforms (BlueROV2,  Leo Rover, Mover6) , robotics sets (Arduino, NXT Mindstorm, Turtlebot) and several types of embedded computers.

project title

Computer intelligence for recognition and support of human activities (CIRESA)

Project research activities

Research activities are including development of system for border control and search for humans based on aerial image analysis as well as development of computer vision algorithms for robust tracking/detection of humans and objects. These algorithms can be applied in various applications of outdoor and indoor space surveillance and analysis of sports events.

Realisation of described system is conducted as extension of research conducted within EU project iSPIS (in collaboration with company Statim d.o.o.), that started on 01.11.2017. Also, a bilateral project SmartBots (Croatia and Germany – main researcher Vladan Papić) is ongoing. Research is focused on autonomous control of mobile robots based on implementation of computer vision and deep neural networks.

For improvement of medical procedures (operations and diagnosis), research of multiple visual contents fusion based on rendering of processed data and alignment with real world objects in augmented reality is planned. (I. Zoraja).

For successful implementation of planned tasks within this projects research focus is within following areas: digital image processing, robotics, machine learning (recognition and classification), design of knowledge based systems. Special attention is also on development and implementation of new, intelligent systems that are using deep neural networks for object detection, recognition and classification and producing correct decisions in unknown environments. More intensive research using underwater drones as well as multi robot collaboration is expected in the future.

Bibliography

Selected papers

(2021)

  • Burger, A., Foretić, N., Spasić, M., Rogulj, N., Papić, V. Handball jump shoot kinematics – difference between Croatian elite and professional players, 9th International scientific conference of kinesiology Opatija, pp. 102-106, 2021.
  • Papić, V., Bugarin, N., Gugić, J. On Olive Groves Analysis using UAVs, International Conference on Software, Telecommunications and Computer Networks SoftCOM 2021, September 2021.
  • Papić, V., Šolić, P., Milan, A., Gotovac, S., Polić, M. High-Resolution Image Transmission from UAV to Ground Station for Search and Rescue Mission Planning, Applied Sciences-Basel, 11 (2021), 5; 1058145.

(2020)

  • Vasić, M.K., Papić, V. Multimodel deep learning for person detection in aerial images, Electronics, Volume 9, Issue 9, September 2020, Article number 1459, Pages 1-15, 2020.
  • Pleština, V, Papić, V, Turić, H. Swimming Pool Segmentation in Pre-processing for Tracking Water Polo Players, 2nd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2020, June 2020, Article number 9179299, 2020.
  • Musić, J., Bonković, M., Kružić, S., Marasović, T., Papić, V., Kostova, S., Dimitrova, M., Saeva, S., Zamfirov, M., Kaburlasos, V., Vrochidou, E., Papakostas, G., Pachidis, T., Robotics and information technologies in education: four countries from Alpe-Adria-Danube Region survey, International Journal of Technology and Design Education, 2020.
  • Kružić, S., Musić, J., Bonković, M., Duchon, F., Crash course learning: An automated approach to simulation-driven LiDAR-based training of neural networks for obstacle avoidance in mobile robotics, Turkish Journal of Electrical Engineering and Computer Sciences, Volume 28, Issue 2, 2020, Pages 1107-1120.
  • Vasić, M.K., A. Drak, N. Bugarin, S. Kružić, J. Musić, C. Pomrehn, M. Schöbel, M. Johenneken, I. Stančić, V. Papić, R. Herpers, Deep Semantic Image Segmentation for UAV-UGV Cooperative Path Planning: A Car Park Use Case, The 28th International Conference on Software, Telecommunications and Computer Networks (SoftCOM 2020), 2020.
  • S. Kružić, J. Musić, R. Kamnik, V. Papić, Estimating Robot Manipulator End-effector Forces using Deep Learning, MIPRO 2020 43rd International Convention – Proceedings, 2020, 1411-1416.
  • J. Musić, S. Kružić, I. Stančić, F. Alexandrou, Detecting Underwater Sea Litter Using Deep Neural Networks: An Initial Study, Proceedings of 5th International Conference on Smart and Sustainable Technologies (SpliTech 2020), 2020.
  • S. Gotovac, V. Papić, On detection of small objects from aerial images, Thesis of reports, 2nd Scientific-practical conference of Russian and Croatian scientist in Dubrovnik / Н.А. Коротченко, А.П. Кутовская – Moskva : Misis, 2020, 104-104.

(…)