Parking Space Detection Using Image Processing

Poorva P. Jadhav1, a *, Shriraj J. Bakade2,b , Manthan P. Dalvi3,c and Akansha V. Gandhi4,d

1
At Post Indapur,Raigad, India
2At Post Kolad,Raigad, India
3
At Post Indapur,Raigad, India
At Post Kolad,Raigad, India
4

[email protected], [email protected], [email protected],

a b
d
[email protected]

Keywords: Parking Space Detection,DCNN,DNN,Image Processing,Visualization, Wireless

Communication.

Abstract. In populated metropolitan cities searching for parking space is extremely difficult for
drivers. Serious traffic congestion may occur due to unavailable parking spaces. Automatic smart
parking systems are an emerging field and have attracted computer vision researchers to contribute
to this area of technology. In this paper, we have presented a vision-based smart parking framework
to assist drivers in efficiently finding suitable parking slots and reserving them.

Introduction

Nowadays most of the parking areas are manually managed by human manpower and there is no
automatic system to manage the parking area in an efficient way. Growing in the technology make
evolution in day-to-day life. Coming to the point there should be the easy way to complete the work.
In this system we use algorithms such as image processing and DNN.
Here we use image processing to detect the objects. In CS, image processing is use for computer
algorithms to perform image processing on digital images. The process for searching the free parking
space is time consuming and also wastage of fuel. Image Processing base systems are a reasonably
priced alternative to systems employing other sensor types and their camera input can be used for
various tasks within the system.
Current systems detecting vacant parking spaces are either very expensive due to their hardware
requirements or do not provide a detailed occupancy map. Now a day, the parking system has
increased rapidly.

Proposed System

We make a system parking space detection system. In that we use DNN algorithm. Find available
slot using image processing and DNN. Firstly we take one image and compare it with previous
dataset. Find how many vehicle are present on that image or this image is having available slot or not.

Existing System

For research purpose, here are some examples of the applications to be compared in term of
operational features. Below are list of similar existing systems:
i. Car-Park Occupancy Information System (COINS).
 ii. Locating Vehicle in a Parking Lot by image Processing.
iii. Parking Guidance System using RFID and Image Processing Technique in WSN
Environment.
iv. Parking Space Vacancy Monitoring.
The time period clever parking refer to the generation which lets in people to dynamically reserve
and pay for parking, whereas gadget is a set of laptop thing or orderliness. By means of standard
understanding, a smart parking machine is a aggregate of clever actions using a mixture of hardware,
software program and data communications to efficiently manage a automobile parking vicinity.
The improved charge of technologies development through year can be considered as a revolution,
permitting technologies like the smart parking system to be produced. This gadget particularly
concentrates in solving the problem of parking management or to be unique, parking vicinity
management. The clever parking device can be divided into five main classes which include parking
steerage and facts device (PGIS), transit based information machine, smart charge device, e-parking
and automated device.
E-parking offers another manner for drivers to order a parking space at their favoured automobile
park facility of choice to make sure a vacant parking area is to be had when they come. The
reservation for a parking area may be made via SMS, phone call, thru the net and/or PDA. discuss
the transformation of unified modelling language (UML)fashions into software program execution
models and simulate the overall performance prediction taking e-parking device as her case take a
look at.

Literature Survey

1. Parking Lot Occupancy Tracking Through Image Processing, Marcos Lopez1, Terry Griffin1,
Kevin Ellis1, Anthony Enem1, and Christopher Duhan1, 2018.

This system processes live images from a web connected camera and determines if a vehicle is
currently stationed in each individual space of a parking lot. Disadvantages of the system is the
results of this program are then relayed to the user in a multiplatform mobile application.

2. Automatic Parking Space Detection System, Nazia Bibi 1, Muhammad

Nadeem,Majid2,Hassan Dawood3,& Ping guo4, 2017.

This system segmented the parking area into blocks using calibration. Then, classify each block to
identify car and intimate the driver about the status of parking either reserved or free. This is time
consuming process.

3. Vision-Based Parking-Slot Detection: A Benchmark and A Learning-Based Approach, L.

Zhang, Xiyuan Li, Junhao Huang, Ying Shen, D. Wang, 2018.

Database can serve as a benchmark to design and validate parking-slot detection algorithms.
Proposed Using P S D L , given a surround-view image, the marking-points will be detected first and
then the valid parking-slots can be inferred. This system works only on previously recorded database.
 4. A Smart Image Processing-based System for Parking Space Vacancy Management,
Benjamin Kommey Kumasi, Ghana Ernest O. Addo Kumasi, Ghana Andrew S. Agbemenu,
2018.
This system processes the image, extracts occupancy information concerning spots, and their
positions thereof. The system also reports if individual parking spots are occupied. This system is
based on image processing.

5. Detection and Simulation of Vacant Parking Lot Space Using EAST Algorithm and Haar
Cascade, Rizki Alfarizi Harahap; Eri Prasetyo Wibowo, 2020.
In this paper, The methods used include character recognition with the EAST text detector algorithm,
vehicle detection with the Haar cascade classification algorithm, and Detection of vacant parking
spots. This research presents a detector using feature text to detect vehicles in parking slots. The
three methods are then combined into a simulation systems. This system required more time to find
result and does not produce accurate result.

Methodology

Fig. 1 DNN

Step 1: For each read each test instances using below equation.

�
testFeature � = . featureSet [A i ……. . A n ⃪ TestDBLits
�=1
 Eq.1

Step 2 : extract each feature as a hot vector or input neuron from testFeature(m) using below
equation.

�
Extracted_FeatureSetx[t……n] = � ⃪ testFeature(m)
�=1
Eq.2

Extracted FeatureSetx[t] contains the feature vector of respective domain.

Step 3: create the number of convolutional For each read each train instances using below equation.

�
trainFeature(m) = . featureSet [A i ……. . A n ⃪ TrainDBLits
�=1
Eq.3

Step 4 : extract each feature as a hot vector or input neuron from testFeature(m) using below
equation.

�
Extracted_FeatureSetx[t……n] = � ⃪ testFeature(m)
�=1
Eq.4

Extracted FeatureSetx[t] contains the feature vector of respective domain.

Step 5 : Now map each test feature set to all respective training feature set.

�
Weight = calcSim (FeatureSetx || �=1
FeatureSety[y])
Eq.5

 Unable to classify sentiment for heterogeneous images like nature images, animal face
images etc.
 Traditional CNN is takes more time to train each object and testing respectively.
 Good accuracy for human face images only not others.
 Only localize features has consider for sentiment classification is existing research it effect on
overall accuracy of error rate.

Verification And Validation For Acceptance =

  “Validation. The assurance that a product, service, or system meets the needs of the customer
and other identified stakeholders. It often involves acceptance and suitability with external
customers. Contrast with verification.”
 “Verification. The evaluation of whether or not a product, service, or system complies with a
regulation, requirement, specification, or imposed condition. It is often an internal process.
Contrast with validation.
 Verification and validation are independent procedures that are used together for checking
that a product, service, or system meets requirements and specifications and that it fulfils its
intended purpose.[1] These are critical components of a quality management system such as
ISO 9000. The words ”verification” and ”validation” are sometimes preceded
with ”independent”, indicating that the verification and validation is to be performed by a
disinterested third party. ”Independent verification and validation” can be abbreviated
as ”IV&V”

Conclusion
The intelligent parking area detection device primarily based on picture processing was designed and
examined in this project. By using pick out the rounded brown photograph drawn at each car parking
zone as a reference on picture detection, it makes the technique of detecting picture as a reference
extra efficient as compared to using a moving item. The conceptualization of this undertaking is to
discover the parking gadget by way of the usage of image processing in place of using sensor base.
Wise parking device is evolved the usage of an integrated image processing technique to reduce
price of sensor and wiring problem.
Acknowledgement
In our endeavour to achieve the success in completing our project Parking Space Detection Using
Image Processing in the Fourth Year Computer Engineering. We take this opportunity to express our
deep sense of gratitude to our guide Prof. S. N. Jadhav for his valuable guidance and kind
cooperation throughout the period of work. We are also very thankful to our respected H.O.D Prof.
K. R. Metha for providing us with adequate facilities, ways. We express our thankfulness to all
teachers and staff of computer department for their timely help. We acknowledge with thanks, the
assistance provided by department staff, library, and lab attendants.

References
[1] Shao, Y., Chen, P. and Cao, T. (2018) A Grid Projection Method Based on Ultrasonic Sensor for
Parking Space Detection. In: IGARSS 2018 - 2018 IEEE International Geoscience and Remote
Sensing Symposium. Valencia. pp. 3378-3381.
[2] Zhou, F. and Li, Q. (2014) Parking Guidance System Based on ZigBee and Geomagnetic Sensor
Technology. In: 2014 13th International Symposium on Distributed Computing and Applications to
Business, Engineering and Science. Xian Ning. pp. 268-271.
[3] Chen, H., Huang, C. and Lu, K. (2017) Design of a non-processor OBU device for parking
system based on infrared communication. In: 2017 IEEE International Conference on Consumer
Electronics - Taiwan (ICCE-TW). Taipei. pp. 297-298.
[4] Yuan, C. and Qian, L. (2017) Design of intelligent parking lot system based on wireless network.
In: 2017 29th Chinese Control And Decision Conference (CCDC). Chongqing. pp. 3596-3601.
[5] Dhawad, S.R., Itkarkar, R.R. (2016) Car Detecting Method using high Resolution images.
International Journal on Recent and Innovation Trends in Computing and Communication, 4:197-
203.