Parking Lot Occupancy Detection using Deep Learning and Fisheye Camera for AIoT System

다국어 초록 (Multilingual Abstract)

The combination of Artificial Intelligence and the Internet of Things (AIoT) has gained significant popularity. Deep neural networks (DNNs) have demonstrated remarkable success in various applications. However, deploying complex AI models on embedded boards can pose challenges due to computational limitations and model complexity. This paper presents an AIoT-based system for smart parking lots using edge devices. Our approach involves developing a detection model and a decision tree for occupancy status classification. Specifically, we utilize YOLOv5 for car license plate (LP) detection by verifying the position of the license plate within the parking space.

참고문헌 (Reference)

1 A. Bochkovskiy, "Yolov4 : Optimal speed and accuracy of object detection"

2 WongKinYiu, "Yolov4"

3 J. Redmon, "Yolov3 : An incremental improvement"

4 J. Redmon, "Yolov3 : An incremental improvement"

5 G. Jocher, "YOLOv5 by ultralytics"

6 Joseph, J., "Wireless sensor network based smart parking system" 162 (162): 5-, 2014

7 E. Sifuentes, "Wireless Magnetic Sensor Node for Vehicle Detection With Optical Wake-Up" 11 (11): 1669-1676, 2011

8 D. Wu, "Using channel pruning-based yolo v4 deep learning algorithm for the real-time and accurate detection of apple flowers in natural environments" 178 : 105742-, 2020

9 S. Albawi, "Understanding of a convolutional neural network" 1-6, 2017

10 N. Wojke, "Simple online and realtime tracking with a deep association metric" 3645-3649, 2017

11 Cho, W., "Robust parking occupancy monitoring system using random forests" 1-4, 2018

12 X. Wu, "Recent advances in deep learning for object detection" 396 : 39-64, 2020

13 V. Mazzia, "Realtime apple detection system using embedded systems with hardware accelerators : An edge ai application" 8 : 9102-9114, 2020

14 Alam, M., "Real-time smart parking systems integration in distributed ITS for smart cities" 2018

15 "Post-training quantization"

16 Z. -Q. Zhao, "Object detection with deep learning : A review" 30 (30): 3212-3232, 2019

17 M. Sandler, "Mobilenetv2 : Inverted residuals and linear bottlenecks" 4510-4520, 2018

18 Y. Xiong, "Mobiledets : Searching for object detection architectures for mobile accelerators" 3825-3834, 2021

19 A. Krizhevsky, "Imagenet classification with deep convolutional neural networks" 60 (60): 84-90, 2017

20 Z. Li, "Fssd : feature fusion single shot multibox detector"

21 Z. -C. Xue, "Fisheye distortion rectification from deep straight lines"

22 M. Tan, "Efficientdet : Scalable and efficient object detection" 10781-10790, 2020

23 M. Tan, "Efficientdet : Scalable and efficient object detection" 10781-10790, 2020

24 Cai, B. Y., "Deep learning-based video system for accurate and real-time parking measurement" 6 (6): 7693-7701, 2019

25 C. -Y. Wang, "Cspnet : A new backbone that can enhance learning capability of cnn" 390-391, 2020

26 A. Ghosh, "Assistive technology for visually impaired using tensor flow object detection in raspberry pi and coral usb accelerator" 186-189, 2020

27 A. Yazdanbakhsh, "An evaluation of edge tpu accelerators for convolutional neural networks"

28 D. Biswas, "An automatic traffic density estimation using single shot detection(ssd)and mobilenet-ssd" 110 : 176-184, 2019

29 B. Jiang, "Acquisition of localization confidence for accurate object detection" 784-799, 2018

30 L. Jiao, "A survey of deep learning-based object detection" 7 : 128837-128868, 2019

31 Mingkai Chen, "A parking guidance and information system based on wireless sensor network" 601-605, 2011

32 Z. Zhang, "A Parking Occupancy Detection Algorithm Based on AMR Sensor" 15 (15): 1261-1269, 2015