Publisher

SAINTISPUBSAINTISPUB

Journal Electronic Journal of Education, Social Economics and TechnologyElectronic Journal of Education, Social Economics and Technology Abstract

Object detection is a fundamental task in computer vision systems used in robotics, automation, and real-time tracking applications. However, implementing accurate and responsive detection on low-cost embedded hardware presents significant challenges due to limited processing power and environmental variability. This study aims to evaluate the performance of an object detection system utilizing ArUco markers on a Raspberry Pi-based platform. The research investigates the systems ability to detect and identify three types of physical objects – a plastic bottle, a flower pot, and a glass cup – as well as the performance when all three objects are present simultaneously. The system was tested under controlled static conditions using a camera to capture real-time video streams. Detection time, computation time, and accuracy were measured across five consecutive frames for each scenario. Results show that the system achieved consistent detection and processing times below 0.14 seconds per frame, meeting real-time performance criteria. Detection accuracy across all individual object scenarios exceeded 91%, with the highest accuracy recorded in the multi-object scenario at 93.44%. No detection failures occurred during the experiments, and frame-by-frame analysis confirmed temporal stability. These findings indicate that marker-based detection is a reliable and efficient approach for real-time applications in structured environments. The study provides a foundation for extending the system to more dynamic conditions in future research.

Conclusion

The ArUco marker-based object detection system demonstrated efficient real-time performance with detection and computation times consistently below 0.The system achieved high detection accuracy, exceeding 91% across all tested scenarios, with the multi-object condition yielding the highest accuracy at 93.Frame-by-frame analysis confirmed the systems temporal stability, indicating reliable and consistent object detection over time.

Future Research

Future research should investigate the systems performance under dynamic conditions, such as varying lighting and object motion, to assess its robustness in real-world scenarios. Exploring the integration of depth information or sensor fusion techniques could enhance the systems ability to handle partial occlusions and improve object localization accuracy. Further studies could also focus on developing adaptive algorithms that dynamically adjust detection parameters based on environmental conditions, optimizing performance and minimizing false positives in challenging environments. These advancements would broaden the applicability of the system to a wider range of practical applications, including robotics, automation, and assistive technologies, while maintaining its low-cost and resource-efficient characteristics.

References

1. Real-time Object Detection Performance Analysis Using YOLOv7 on Edge Devices | IEEE Journals & Magazine... doi.org/10.1109/TLA.2024.10705971Real time Object Detection Performance Analysis Using YOLOv7 on Edge Devices IEEE Journals Magazine doi 10 1109 TLA 2024 10705971
2. SSD Framework in Raspberry Pi for Real-Time Object Detection in Autonomous Vehicles | IEEE Conference... ieeexplore.ieee.org/document/10677229SSD Framework in Raspberry Pi for Real Time Object Detection in Autonomous Vehicles IEEE Conference ieeexplore ieee document 10677229
3. Real-Time Tracking and Distance Measurement of Opencv Aruco Marker Using Webcam | International Journal... doi.org/10.51583/ijltemas.2025.1401034Real Time Tracking and Distance Measurement of Opencv Aruco Marker Using Webcam International Journal doi 10 51583 ijltemas 2025 1401034
4. Real-Time Object Size Dimensioning in Raspberry Pi | IEEE Conference Publication | IEEE Xplore. real... doi.org/10.1109/icces54183.2022.9836005Real Time Object Size Dimensioning in Raspberry Pi IEEE Conference Publication IEEE Xplore real doi 10 1109 icces54183 2022 9836005
5. One moment, please.... one moment please wait request verified ejeset.saintispub.com/ejeset/article/view/309One moment please one moment please wait request verified ejeset saintispub ejeset article view 309

Metadata

File size	619.08 KB
Pages	11
DMCA	Report