20.500.12556/RUL-173651 Robotski vid za zaznavo in analizo stebelne zelenjave Robotic Vision for Detection and Analysis of Stem Vegetables Diplomsko delo se osredotoča na avtomatizacijo kmetijskih procesov z uporabo naprednih sistemov računalniškega vida in umetne inteligence, zlasti pri pobiranju špargljev. Zaradi naraščajoče svetovne populacije in omejenih kmetijskih površin postaja avtomatizacija ključna za zagotavljanje zadostne količine hrane. V delu je prikazana pregledna analiza sodobnih pristopov k avtomatizaciji pobiranja pridelkov, vključno z robotskimi sistemi za jabolka, paradižnike in zaznavo plevela, ki temeljijo na mobilnih platformah, globinskih kamerah in algoritmih, kot sta YOLO in PointNet. Posebna pozornost je namenjena pobiranju stebelne zelenjave, kjer sta detekcija in lokalizacija ključni. Predstavljeni so različni pristopi, od taktilnih senzorjev in laserskih skenerjev do globinskih kamer, pri čemer se kot najboljša izbira izkaže uporaba globinske RGBD kamere. Implementacija detekcije špargljev temelji na algoritmu YOLOv8, ki omogoča zaznavanje objektov v realnem času in obdelavo heterogenih scen z visoko natančnostjo. Model je bil naučen na anotiranih slikah laboratorijskih in pravih špargljev, pri čemer je dosegel zadovoljive rezultate. Dodatno je predstavljena uporaba točkovnih oblakov za analizo tridimenzionalnih lastnosti špargljev, kot so višina, lega in oblika, kar omogoča kvantitativno oceno za avtomatizirane pobiralne sisteme. Pri tem je izpostavljen pomen kakovostnih podatkov, ustrezne kalibracije in optimizacije zajema, kar zagotavlja natančnost in zanesljivost sistema. The thesis focuses on the automation of agricultural processes using advanced computer vision and artificial intelligence systems, particularly in asparagus harvesting. Due to the growing global population and limited agricultural land, automation is becoming crucial for ensuring sufficient food supply. The work provides a comprehensive analysis of modern approaches to crop harvesting automation, including robotic systems for apples, tomatoes, and weed detection, which are based on mobile platforms, depth cameras, and algorithms such as YOLO and PointNet. Special attention is given to harvesting stem vegetables, where detection and localization are key. Various approaches are presented, ranging from tactile sensors and laser scanners to depth cameras, with the RGB-D depth camera emerging as the optimal choice. The implementation of asparagus detection is based on the YOLOv8 algorithm, enabling real-time object detection and the processing of heterogeneous scenes with high accuracy. The model was trained on annotated images of asparagus models and real asparagus, achieving satisfactory results, although a larger dataset and further optimization are still required for real-world applications. Additionally, the use of point clouds is presented for analyzing the three-dimensional properties of asparagus, such as height, position, and shape, allowing for quantitative evaluation for automated harvesting systems. The importance of high-quality data, proper calibration, and optimized acquisition is emphasized, ensuring the accuracy and reliability of the system. kmetijstvo avtomatizacija v kmetijstvu računalniški vid robotski sistem za pobiranje špargljev mobilna robotska platforma detekcija in prepoznavanje špargljev segmentacija objektov globinska kamera točkovni oblaki konvolucijske nevronske mreže YOLO algoritem agriculture agricultural automation computer vision robotic asparagus harvesting system mobile robotic platform asparagus detection and recognition object segmentation depth camera point clouds convolutional neural networks YOLO algorithm true false false Slovenski jezik Angleški jezik Diplomsko delo/naloga 2025-09-19 11:25:15 2025-09-19 11:25:25 2025-11-11 03:57:38 0000-00-00 00:00:00 2025 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 63190 252541699 Kozuh_Mai_kristian_-_Robotski_vid_za_zaznavo_in_analizo_stebelne_zelenjave.pdf Kozuh_Mai_kristian_-_Robotski_vid_za_zaznavo_in_analizo_stebelne_zelenjave.pdf 1 F9C1B8D710BF8CC74CCB7A01BAC83FC5 69ad6d498ab9e7d1962a4048522ba2f8d9a35a4e81ccadfe3ae3ac70872be211 656cfc60-953a-11f0-9328-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=218270 Fakulteta za elektrotehniko 0 0 0