Sustav aktivne zaštite od kolizije temeljen na više kamera

master's thesis

• Title (english): A multi-camera-based active collision protection system
• Author: Antonio Piršić
• Mentor: Tomislav Stipančić (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2025-02-06, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering

Abstract

Ovaj diplomski rad opisuje razvoj sustava aktivne zaštite od kolizije temeljenog na više kamera, s ciljem povećanja sigurnosti u zajedničkim radnim prostorima robota i ljudi. Sustav koristi dvije kamere za praćenje položaja i izračun minimalne udaljenosti između čovjeka i robota u stvarnom vremenu. Implementiran je algoritam fuzije podataka pomoću biblioteka OpenCV i MediaPipe, omogućujući visoku preciznost u detekciji objekata i generiranju upozorenja. Sustav je dodatno osiguran korištenjem TCP komunikacije za sinkronizaciju podataka između kamera i robota. Ako izmjerena udaljenost padne ispod sigurnosne granice, sustav automatski zaustavlja robota kako bi spriječio potencijalne nesreće. Ključni dijelovi uključuju kalibraciju kamera, detekciju ArUco markera i praćenje ruku pomoću MediaPipe-a. Rezultati pokazuju kako je sustav uspješno prilagođen za rad u stvarnom vremenu te ima široku primjenu u industrijskim i istraživačkim okruženjima.

Abstract (english)

This thesis describes the development of a multi-camera-based active collision protection system aimed at enhancing safety in shared workspaces between robots and humans. The system utilizes two cameras to monitor positions and calculate the minimum distance between a human and a robot in real time. A data fusion algorithm implemented using the OpenCV and MediaPipe libraries ensures high precision in object detection and alert generation. The system is further secured through the use of TCP communication for data synchronization between cameras and the robot. If the measured distance falls below the safety threshold, the system automatically stops the robot to prevent potential accidents. Key components include camera calibration, ArUco marker detection, and hand tracking using MediaPipe. The results demonstrate that the system is successfully adapted for real-time operation and has broad applications in industrial and research environments.

• Keywords: aktivna zaštita od kolizije; kamere; OpenCV; MediaPipe; UR5 robot; detekcija ArUco markera; detekcija ruke; triangulacija; sigurnost u industriji
• Keywords (english): active collision protection; cameras; OpenCV; MediaPipe; UR5 robot; ArUco marker detection; hand detection; triangulation; industrial safety
• Language: croatian
• URN:NBN: urn:nbn:hr:235:529115
• Study programme: Title: Mechanical Engineering; specializations in: Design, Process and Energy Engineering, Production Engineering, Engineering Modelling and Computer Simulation, Marine Engineering, Industrial Engineering and Management, Materials Engineering, Mechanics and Robotics, Autonomous Systems, Mechatronics and Robotics; Course: Autonomous Systems; Study programme type: university; Study level: graduate; Academic / professional title: sveučilišni/a magistar/magistra inženjer/inženjerka strojarstva (sveučilišni/a magistar/magistra inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2025-02-05 10:47:12