Development of an efficient method for object detection and localization in 3D space using RGBD cameras for autonomous systems

The work presents an efficient algorithm for object detection, orientation estimation, and isometric positioning in 3D space using RGBD camera data. The goal of the study is to improve the accuracy and processing speed of autonomous navigation and manipulation systems under conditions of limited com...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International journal of cognitive computing in engineering Ročník 6; s. 537 - 551
Hlavní autor: Boyko, Nataliya
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.12.2025
KeAi Communications Co., Ltd
Témata:
Algorithmic precision
Autonomous systems
Computational efficiency
Heuristic algorithm
Hyperparameter tuning
Isometry estimation
Object detection
Planar backgrounds
RGBD camera data
Robotic navigation
Autonomous systems
Heuristic algorithm
Object detection
Robotic navigation
Planar backgrounds
Computational efficiency
RGBD camera data
Isometry estimation
Algorithmic precision
Hyperparameter tuning
ISSN:2666-3074, 2666-3074
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The work presents an efficient algorithm for object detection, orientation estimation, and isometric positioning in 3D space using RGBD camera data. The goal of the study is to improve the accuracy and processing speed of autonomous navigation and manipulation systems under conditions of limited computational resources. The proposed approach combines heuristic isometry estimation with segmentation methods (DBSCAN), plane estimation (RANSAC), and orientation analysis, enabling effective processing of scenes with planar backgrounds. The main advantage of the algorithm lies in its ability to operate in real time: the processing time for a single frame is only 20 ms, achieving object positioning accuracy up to 5.48 cm. The results of experimental research confirm a high level of accuracy and stability even under challenging conditions. The algorithm outperforms existing models in terms of processing speed while demonstrating comparable or superior positioning accuracy. The practical significance of the proposed method lies in its potential application in mobile robotics, automated warehouse systems, and machine vision systems where high autonomy and precision are required. The algorithm can also be adapted to a broader range of tasks due to its flexible hyperparameter tuning. A key limitation remains the requirement for object placement on a planar surface and the use of a depth camera, which necessitates a specific environmental setup. The proposed method makes a significant contribution to the advancement of computer vision and autonomous robotics technologies, opening prospects for its implementation in next-generation systems.
ISSN:2666-3074
2666-3074
DOI:10.1016/j.ijcce.2025.04.005