About LAPIS projects

Scientific projects

ExQuMe - Explaining Quantum Mechanics SAFER - Smart AI- and IoT-based Fire Extinguisher CPM Smart Predictive Analytics for Reliable Turbine Assets AERONAUT - Advancing research capacities for the development of autonomous marine-aerial systems for novel Adriatic applications Nonverbal Communication-Based Adaptive Learning Model for Interactive AI Agents Virtual - transfer - Technology Transfer of an Affective Virtual Being for Immersive Interaction AMICORC Project ACRON - A New Concept of Applied Cognitive Robotics in Clinical Neuroscience Mixed reality applications

Student projects

Robotic plotter for printing photos in the vertical plane A mechanism for directing the virtual agent's gaze based on sound and visual input A robotic manipulator for printing photos Computational model for classification and counting of push-ups Data transmission between two computers using blockchain technology Artificial intelligence and virtual reality in creating interactive 3D environments Automated label quality control using computer vision and a collaborative robot Control of a robot using real-time hand gesture recognition Real-time driver state detection A vision system for controlling an industrial robot with hand movements

Computational model for classification and counting of push ups

Student: Ana Njirić

This work presents the development of a computer vision system for push-up classification and automatic repetition counting using human pose estimation.

The system is implemented in Python using the MediaPipe library, enabling real-time detection and tracking of body landmarks. Based on the extracted pose information, the model identifies push-up movements and counts repetitions, while visualizing the estimation in a 2D interface.

The work also includes an overview of the theoretical foundations of human pose estimation, along with evaluation on multiple test examples. The results are analyzed and potential improvements for increasing accuracy and robustness are discussed.

This project demonstrates the application of computer vision in fitness tracking and human activity recognition, with potential extensions toward real-time coaching and smart training systems.

Repository: https://repozitorij.fsb.unizg.hr/object/fsb:9853