Posted at 04.10.2018
Nowadays, individuals are facing problem to find an available auto parking space in auto parking lot because of the incredible increase of occupancy of vehicles. When driver enters a certain auto parking lot, the drivers takes a quite a while just to find an available parking space. A Keeping track of Available Car parking Space using Image Processing (CAPSuIP) will develop to solve the challenge that driver confronted with low cost. CAPSuIP use image control to discover of lifetime of the automobile and also provide information such as variety of available auto parking space and the location of that auto parking. The machine will take image using webcam and process the image to keeping track of available parking space. The machine use a revised Software Development Life Routine (SDLC) to plan, review, design, development and tests. The development of the system will use techniques of image handling that will put into action in each stage of methodology. This technique will give information about the location of available auto parking space and the number of available auto parking space. It'll be benefit to all drivers when enter into a parking lot.
Nowadays, car is vital to everyone specifically for who are works. Folks are happy to make installment to get an own car. When talking about metropolitan, then traffic jam always take place because of numbers of vehicles are so high. Thus we can not deny the existing of the autos in our way of life. Whenever we go out by car, our company is facing problem to find an available car parking space due to the incredible increase of occupancy of vehicles.
The analogy is when driver gets into a certain car parking lot, the essential thing that the drivers do is excited of some signal to revealing that the parking lot is completely occupied, partly occupied or vacant. The driver also have no idea how many is there and where to find a parking department for his/her car. A few of parking divisions may stay unoccupied even the total occupancy is high. This will causing ineffective use of car parking divisions as well as traffics jams about the entrance of auto parking great deal. Therefore, by offering individuals with relevant home elevators the parking great deal during stepping into a parking great deal becomes an important issue.
The proposed system called as Counting Available Car parking Space using Image Handling (CAPSuIP). This system proposes a method of discovering the lifetime of parked vehicles by producing the image of the parking lot taken by a monitoring camera and then keeping track of the available auto parking space which is screen before entrance of car parking lot.
The system make use of images, since all area in the car parking lot can be viewed with relatively few camera. Other than that, the system is compact and the price is not is not expensive. The image of a parking lot is used by a security camera placed at some level in the car parking lot.
There are some reasons why Counting Available Auto parking Space using Image Control (CAPSuIP) is developed. The problems that have been identified are stated below:
Driver needs some relevant information before joining the parking lot such as the current available auto parking places in the parking lot.
There are current system used in parking lot however the method used is based on the detection by putting in a certain sensor on each department; the other is to identify vehicles through images of the car parking lot considered by surveillance surveillance cameras. In the method with the sensor, the cost rises as the amount of parking divisions just because a lot of sensors are required equivalent to each car parking divisions.
Objectives of the Keeping track of Available Auto parking Space using Image Processing (CAPSuIP) to be developed are to:
Capture and identify lifetime of vehicle at parking great deal using image control technique.
Count, screen of the available auto parking spaces in parking lot.
There are a few scopes that contain been identified in order to develop the machine. The scopes of the systems are:
This system is just a prototype system using image processing techniques.
Using image that captured from webcam.
The position of the parked vehicle is right.
The location of case study of the system is at Universiti Malaysia Pahang (UMP) auto parking lot stop Z. Each location contains five space of auto parking block.
The system can be utilized in daytime only without have a solid shadow.
A Car-Park Occupancy Information System (COINS)  is developed to be a viable solution to lessen the quantity of time needed to visit a vacant car-park lot especially in an enormous auto parking area. With this technique, images captured by way of a monitoring camera were processed in real-time to identify the occupancies of the auto parking plenty. This occupancy information is further prepared by a central control product and distributed to show sections located at tactical locations at the parking area. The drivers can easily find a vacant parking lot predicated on the information displayed on the sections. Motivation for producing this system originated from the fact that lowest cost is included because image processing technique is utilized somewhat than sensor-based techniques. As surveillance cameras are plentiful generally in most car parks, this technique is much cost effective than setting up sensor on each car parking lot.
Locating Vehicle in a Auto parking Great deal by Image Handling is more concern to propose a method of detecting the existence of parked vehicles by finalizing the image of a parking lot taken by monitoring camera. Whenever drivers would like to park an automobile at a auto parking lot, where to find a proper car parking division there triggers a serious problem. The objective of the present article is within providing individuals with such information as the lot is totally occupied or relatively vacant, where unoccupied parking divisions are found, and so on. The images hired, since every area in the car parking lot can be observed with relatively few surveillance cameras, the machine is small, and the cost is not expensive. The image of any parking lot is used by a security camera establish at some elevation in the car parking lot.
The relevant issues are how to handle both temporal and spatial changes in illumination, how to discriminate shadows from vehicles, how to cope with occlusion, and exactly how to cope with various surface reflectances of vehicles and so forth. To cope with these issues, the source images changed to the gray levels with log-transform, extracts edges and counts the number in each car parking department, and then determines if each department is occupied or not. The acknowledgement rates for a couple of images taken at various moments of any day were well above 95 %.
Parking Assistance System using RFID and Image Processing Techniques in WSN Environment  describes a novel method of developing a Parking Direction System within the car park in a radio Sensor Network (WSN) environment to be able to help reduce the aggravation and problem in finding vacant car parking space. The machine utilizes the existing CCTVs installed in the car park coupled with FPGA device in detecting the vacant places which will subsequently be designated to the patron using the shortest journey algorithm based on both the point of access to the automobile park and building. The patron is then guided to the specified location by referring to the map paper on the parking ticket. Besides that, an RFID label is also attached to the parking ticket to uniquely identify the allocated car parking space of the customers and you will be used to remind patrons of the parking location during payment.
Whereas, Car parking Space Vacancy Monitoring is propose a stereo-vision structured system that package with occasions with severe vehicular occlusion. In this technique, multiple cameras are being used to keep an eye on the vacancy status of the P502 parking spaces on University or college of California, NORTH PARK (UCSD) campus.
In this technique, a way for monitoring vacancies in car parking lots using a stereo system camera system provided to create a 3D reconstruction of the arena, which permits us to look for the vacancy position of a particular car parking space under vehicular occlusion. Also, results for 3D reconstruction using uncalibrated versus calibrated cameras are likened.
This system is able to identify vacancies while differentiating between spots for different permit holders (faculty versus students). Essentially, the system also in a position to offer an exact count number of the number of available places, but it must have to charm to a statistical notion of vacancy, as certain areas may be too intensely occluded by trees and shrubs, other vehicles, etc. to be monitored with high accuracy. This information will finally be included with a position dissemination tool, where motorists will be able to query the parking lot position via cellular phone.
The amount 3. 1 shows the flow of the Software Development Life Routine (SDLC) methodology that has been modified in expanding Counting Available Car parking Space using Image Handling techniques.
Figure 3. 1: Software Development Life Circuit.
Requirements and past system information examination defined in the books review chapter that use in chapter 2 of the thesis. It really is include existing system information to investigate the strategy used and the execution of the system.
Data are accumulate from the image acquisition process where there are a lot of images had been captured.
This phase will describe about the procedure flow involved with developing the system. There eight step which is the image acquisition, initiation control, image feature extraction, grayscale subtraction, image edge recognition, RGB color subtraction etc. Shape 3. 2 shows the image handling flow for keeping track of available car parking space.
Figure 3. 2: Process circulation in CAPSuIP.
Image acquisition is a first level of any vision in image processing. Following the image has been obtained, various method of preprocessing can be employed to perform the many different vision tasks. The locations of image to fully capture are in the UMP car parking area. The scopes of the system are just five (5) space of auto parking stop in the UMP car parking area stop Z. Besides that, the machine using model simulation to analyze the image.
These images will capture by the writer using the webcam 5megapixels. Image that will used is 480 x 640 pixel using JPEG format. JPEG format is use because JPEG images are best used for the representation of natural field.
In this phase, image will extracted to identify the positioning of every auto parking great deal in the image. You will discover two types of images are used which is image without a car and image with a car.
An image with out a car will refined to identify the coordinate of auto parking lot. The height and width of the auto parking whole lot will be discovering predicated on the series in parking whole lot. After the level identified, it'll be split into five (5) to separate the each location of auto parking lot. Physique 3. 3 shows of the illustration of the car parking lot which is separate into five blocks.
Figure 3. 3 Illustration of block of the auto parking lot
An image with a car processed to identify the prevailing of the car in the parking lot.
Preprocessing is second phase in the phase of Keeping track of Available Auto parking Space using Image Processing. Preprocessing stage is an activity of improvement of digital image without knowledge about the foundation of degradation. It can used to improve an images deal and brightness characteristics, reduce its noise content, or sharpen its details. There are two (2) steps in the image improvement to increase the quality of a graphic which is transforming image into two times and normalize RGB image.
Converting Image Into Double
The images are used in this technique will be converted to double kind of images. This process will converts the real color image RGB to double precision, rescaling the info if necessary. This conversion is important because it will make the calculation more appropriate.
Normalization RGB Image
Image that record will be refined by normalize the RGB image to eliminate the effect of any change in strength. This process is vital phase before move to next process.
To get an subject which free from darkness, three (3) steps must be done. First rung on the ladder is RGB color subtraction, second step is thresholding the image and previous step is dilating the image.
RGB Color Subtraction
Image without car and image with car will be subtracted to get the several value between images. This technique will execute following the image is normalize.
Thresholding process is to get darkness free image.
Image will be dilated to structuring component object, or array of structuring element objects. This technique will be utilized after the process of subtraction of the images.
Exact boundary of the objects and the shadows of the object are needed. To take action, below steps are applied:
Gray Level Transformation
Gray level transformation is utilized to convert RGB image to gray scale.
The grayscale image without car and with an automobile will be employed.
Thresholding process is to get darkness free image.
Image will be dilated to structuring element object, or selection of structuring element items. This process will be utilized after the procedure for subtraction of the images.
Image will be filled out the openings in a bounded part of an image.
To find the reconstructed boundary of the thing without shadow region, point smart multiplication of items which is shadow is multiplied with the dilated thing region. Body 3. 4 shows the example code of reconstruction of the thing.
finalRes(:, :, 1) = Res(:, :, 1). *re;
finalRes(:, :, 2) = Res(:, :, 2). *re;
finalRes(:, :, 3) = Res(:, :, 3). *re;
Figure 3. 4 Example of code of reconstruction
To find the region of object, code below can be used:
[B, L] = bwboundaries(final);
if N > 0
if (area>saiz1 && u1>5)
condition1 = 1;
N = quantity of label connected component
area = size of chosen label
saiz1 = size of image
u1 = variety of edge detected
condition1 is determine whether car are present or not. If condition1 is 1 then the block have a car.
To find least value of images by grayscale it and use code below:
fil = the grayscale image of 
t1 = minimum amount value of selected image
If minimum value higher than 20, then check out RGB color subtraction + grayscale.
Subtract RGB color image  and then grayscale it.
If size detected image is greater than 40% and less than 90% then car is exist for the reason that block.
In this phase, there are several process that must definitely be done before getting the result. The insight that needed are image with out a car as a track record and image with a car as a foreground. The exemplory case of insight image is shown in Table 4. 1.
Table 4. 1 Exemplory case of input
In data reduction phase, first step is the image was segment from original image into specific location of car parking using their width and level and axis X and Y. Second step is the segment image from image that segmented before into 5 stop of location of parking by dividing the width of the image. The resources code for the execution is same as above.
Conversion image into dual type format is actually converts the true color image RGB to increase precision, rescaling the data if required. This change is important since it can make the calculation more exact.
Method of converting an RGB image into normalized RGB is used to removes the result of any level variations. After aggregating R, G and B, it is checked out that if any value is 0 then it is set 0. 001 to overcome "split by zero problem. Next process is to normalizing R factor and G factor.
Subtraction method is used to get new image which considered by subtract track record image and image with car.
Thresholding method is put on get darkness free image.
Dilating image is put on structuring element thing, or selection of structuring element objects.
Gray scale transformation is a process of transformation from RGB image to the gray size image using grey scale change.
Subtraction of gray image method is also used to get new image which used by subtract history image and image with car. After that, the image will be changed into double type.
Thresholding method is applied in grey image also to get darkness free image.
Dilating is put on structuring element thing, or array of structuring element things and filling up method is used to fill out the holes in a bounded region of an image.
Reconstruction image is used to reconstructed boundary of the object without darkness region, point smart multiplication of items which is darkness is multiplied with the dilated object region.
Regrayscale is utilized to convert rgb image to gray image and closing method is employed to performs morphological final on the grayscale or binary image IM, returning the closed down image, . The structuring element must be considered a single structuring element object, instead of an array of objects.
Results of feature evaluation phase were identified after feature extraction phase where in fact the classification of image will define and depend the available auto parking space. Approach that uses to get the removal value of image is size and border of object discovered in the image. The value of object fix to be higher than 15% and the advantage fix to be higher than 10. If size and advantage is match the criteria, then the system will decide that there surely is an automobile.
If not, minimum value of image will be determine. Minimal value fix to be greater than 20 of course, if that conditions is satisfied, then it'll proceed to the RGB color subtraction + grayscale process. If size recognized image is greater than 40% and significantly less than 90% then car is exist in that block.
After that, rectangle will be display in the result to show that the stop of auto parking is having an automobile. The result will appear after all process has done.
The software of the system is shown in the Physique 4. 1. This technique can get image directly from webcam or browse image in the local computer.
Figure 4. 1 Software of Counting Available Car parking Space
To test the machine, there are two method can be used specifically test in real environment and using simulation model. The positioning of webcam which used must be put in suitable elevation and parallel with parking great deal. The system that developed has been developed is can catch straight from webcam and also browse image in local computer.
But to test using this method is difficult because every changes of the auto parking lot must be captured manually. So, the real time system has been developed to testing the machine easily. The true time system will detect every changes of the car parking lot, the system automatically detect and shows result without discussion from individual.
Area to be processed
- This is the qualifications image which is used as
input of the machine.
- Parking space set to five (5) space only
- This is the foreground image with red lines.
- Red line will appear in the end process detection
- The machine detect 4 vehicles in the car parking lot. It is
means that only 1 (1) parking space is
These parts were explained about assumption that face by author when completing the thesis and a concept for an additional research.
In order to complete this prototype, there are two (2) constraints that have an effect on the smoothness of the execution. There are complex knowledge and insufficient an event.
This task is using MATLAB (Matrix Laboratory) software and ADOBE PHOTOSHOP. It will take a chance to learn the software and familiar with it.
The system can used only daytime and if there is any strong darkness, it cannot discover whether it car or not. Other than that, the position of webcam and backdrop must be set. In addition, the machine not well analyzed because of not enough of needed equipment such as high quality webcam which is utilized to test the machine in real world environment.
For the further research, it is strongly recommended to increase the methodology, strategy and algorithm to obtain the better effect and can solve the strong darkness problem.
There are a great deal of technique that had been applied nowadays and other developer can apply the prototype by using other approach and program. Besides that, the creator can apply the prototype with new algorithm to produce the better end result. Besides that, other developer can form real time system such that it can be utilized in real life environmnet.
This task can be applied in many places such as school because it will help user to learn just how many available of parking very quickly.