An Intelligent Smart Parking System Using Convolutional Neural Network

Algorithm 1

Smart parking and management system.

Input: Real-time images.

Output: Number of parked cars, number of vacant spaces, and directions to these spaces.

1. Scan the parking lot every time a vehicle enters or leaves.

2. If no vacant spaces are available, then

3. Display a message to inform drivers and keep gate closed.

4. Else

5. Open the gate.

6. Remove noise from captured image.

7. Transform the resultant image into a gray image.

8. Determine the dimensions of the parking area.

9. End of preprocessing phase.

10. Assign a number of vacant spaces to a threshold variable.

11. Subtract captured image of current parking area from the parking map structure.

12. Apply AlexNet for deep learning objective.

13. For i =1: length of parking area

14. For j =1: width of parking area

15. Do the following:

16.  Find resultant image from subtraction process and compare it with the threshold.

17.  If result > threshold, then:

18.   Place 1 in the current index,

19.  Else

20.   Place 0.

21. End

22. End

23. End

24. Check which lanes have vacant spaces to direct drivers to the nearest one.

25. Display instructions for drivers or motorists to park their vehicles in the detected lane.

26. End of algorithm.