ANALYSIS OF EFFECTIVE IMAGE PROCESSING METRICS ON RASPBERRY PI AND NVIDIA JETSON NANO

Roman Mysiuk

Abstract


Image processing and object recognition technologies for detecting defects on the surfaces of a variety of materials is critical to ensuring the safety and durability of infrastructure. That is why this topic and problems of the field of defect detection were chosen in the study. Therefore, the development of effective image processing methods for defect identification, especially in low-light conditions and hard-to-reach places, is of great relevance. The research is a comparison of classical image processing methods with modern deep learning algorithms such as CNN (Convolutional Neural Networks) and YOLO (You Only Look Once). The study analyzes the effectiveness of these methods under specific defect inspection conditions, including diffuse lighting and device mobility. An important aspect is the use of microcomputers such as Raspberry Pi and Nvidia Jetson Nano, which ensures the mobility and autonomy of the system. The practical value of the research lies in the implementation of effective image processing methods for detecting defects on the surfaces of engineering structures. This makes it possible to significantly improve the accuracy of surface defect identification, which is confirmed by the IoU (Intersection over Union) and Dice metrics. In particular, using CNNs for surface defect identification showed 35% better results compared to existing implementations of similar networks and 12% more efficient compared to YOLO. On the other hand, YOLO proved to be more productive in terms of processing frames per second on microcomputers, which is important for real-time monitoring.

Keywords: computer vision, deep learning, image processing, surface defect detection, Raspberry PI, Nvidia Jetson Nano, performance metrics.


Full Text:

PDF

References


  1. S. Vani, H. Singh. The Performance Analysis of Edge Detection Algorithms for Image Processing Based on Improved Canny Operator. International Journal of Computer Trends & Technology. 2020. Vol. 68, No. 10. P. 29–34. https://doi.org/10.14445/22312803/IJCTT-V68I10P106
  2. A. Saberironaghi, J. Ren, M. El-Gindy. Defect Detection Methods for Industrial Products Using Deep Learning Techniques: A Review. Algorithms. 2023. Vol.16. P. 95. https://doi.org/10.3390/a16020095
  3. Z. Ren et al. State of the Art in Defect Detection Based on Machine Vision. International Journal of Precision Engineering and Manufacturing-Green Technology. 2022. Vol. 9, P. 661–691. https://doi.org/10.1007/s40684-021-00343-6
  4. J. Lu, S.-H. Lee. Real-Time Defect Detection Model in Industrial Environment Based on Lightweight Deep Learning Network. Electronics. 2023. Vol. 12. No. 21. P.4388. https://doi.org/10.3390/electronics12214388
  5. Zhen Yu. YOLO V5s-based Deep Learning Approach for Concrete Cracks Detection. SHS Web Conf. 2022. Vol. 144. P. 03015. https://doi.org/10.1051/shsconf/202214403015.
  6. Riya Kumari et al. A Review of Image Detection, Recognition and Classification with the Help of Machine Learning and Artificial Intelligence. SSRN Electronic Journal. 2020. https://doi.org/10.2139/ssrn.3611339
  7. R. Mysiuk et al. Detection of Surface Defects Inside Concrete Pipelines Using Trained Model on JetRacer Kit. 2023 IEEE 13th International Conference on Electronics and Information Technologies, 2023. P. 21–24. DOI: 10.1109/ELIT61488.2023.10310691
  8. R. Mysiuk et al. Video-based Concrete Road Damage Assessment Using JetRacer Kit. 2023 17th International Conference on the Experience of Designing and Application of CAD Systems. 2023, P. 1–4, doi: http://doi.org/10.1109/CADSM58174.2023.10076528.
  9. R. Mysiuk, V. Yuzevych. IoT-based solution for detection defects in infrastructure objects using Raspberry PI. Electronics and Information Technologies. 2023. No. 21. P. 45–56. http://doi.org/10.30970/eli.21.5
  10. GitHub - khanhha/crack_segmentation: This repository contains code and dataset for the task crack segmentation using two architectures UNet_VGG16, UNet_Resnet and DenseNet-Tiramusu. GitHub. URL: https://github.com/khanhha/crack_segmentation
  11. Roboflow: Give your software the power to see objects in images and video. Roboflow: Give your software the power to see objects in images and video. URL: https://roboflow.com/
  12. ONNX Runtime. Inference. ONNX Runtime. Home. URL: https://onnxruntime.ai/inference
  13. Ultralytics. Home. Home – Ultralytics YOLOv8 Docs. URL: https://docs.ultralytics.com/
  14. PyTorch v2.1.0. Previous PyTorch Versions. URL: https://pytorch.org/get-started/previous-versions/#v210
  15. A Guide to using TensorRT on the Nvidia Jetson Nano. Donkey Car. URL: https://docs.donkeycar.com/guide/robot_sbc/tensorrt_jetson_nano/
  16. D. Adami, M. O. Ojo and S. Giordano. Design, Development and Evaluation of an Intelligent Animal Repelling System for Crop Protection Based on Embedded Edge-AI. in IEEE Access. 2021. Vol. 9, P. 132125–132139. DOI: 10.1109/ACCESS.2021.3114503




DOI: http://dx.doi.org/10.30970/eli.28.2

Refbacks

  • There are currently no refbacks.