Speed Detection Using IOT

A Seminar I report submitted in

partial fulfillment of the
requirements for the Degree of

B.Tech.
in

Computer Engineering
Submitted by

CHAITANYA ARVIND GIRASE

DEPARTMENT OF COMPUTER ENGINEERING

S.S.V.P.S.’s B.S. DEORE COLLEGE OF ENGINEERING, DHULE 2023-
24

1
 Speed Detection Using IOT

A Seminar I report submitted in partial

fulfillment of the requirements for the
Degree of

Bachelor of Technology
in

Computer Engineering
Submitted by

CHAITANYA ARVIND GIRASE

Guided by

PROF:B.D.PATIL

DEPARTMENT OF COMPUTER ENGINEERING

S.S.V.P.S.’s B.S. DEORE COLLEGE OF ENGINEERING, DHULE
2023-24

2
 S.S.V.P.S.’s B.S. DEORE COLLEGE OF ENGINEERING,
DHULE
DEPARTMENT OF COMPUTER ENGINEERING

CERTIFICATE

This is to certify that the Seminar I entitled “speed ditection usihg IOT” has
been carried out by
Chaitanya Arvind Girase
under my guidance in partial fulfillment of the degree of Bachelor of
Technology in Computer Engineering of Dr. Babasaheb Ambedkar
Technological University, Lonere during the academic year 2022-23. To the
best of my knowledge and belief this work has not been submitted elsewhere
for the award of any other degree.

Date:

Place: Dhule

Guide

PROF.B.D.PATIL

Head Principal
Prof. B. R. Mandre Dr. Hitendra D.
Patil

3
 ACKNOWLEDGEMENT

This Seminar I report has taken its current shape after a lot of hard work and
perseverance- not only just by me. I would like to express our sincere
gratitude for the assistance and support of a number of people who are
helping to make this success.

Immeasurable appreciation and deepest gratitude are extended for the

help and support to Prof. B. R. Mandre, my guide for his guidance and
enlightening comments throughout the project work. It has been an
altogether different experience to work with him and I would like to thank
for his helpful suggestion and numerous discussions. I gladly take this
opportunity to thank Prof. B.R. Mandre (Head Of Department, Computer
Engineering) and Dr. Hitendra D. Patil (Principal, SSVPS, BSD, College of
Engineering, Dhule) for providing facilities during progress of the thesis.

I wish to express my sincere thanks to Prof. B.D.Patil for his expert,

sincere and valuable guidance and encouragement extended to me.

I am also thankful to all those who helped us directly or indirectly to

develop this thesis and complete it successfully. Then I would like to thank
all the Staff for their encouragement. They had always been very prompt at
extending in their helping hand and sharing valuable technical knows.
Special thanks to my Family and Friends.

Chaitanya Arvind Girase

4
 Table of Contents
ABSTRACT........................................................................................................................6
1.INTRODUCTION............................................................................................................7
2..SYSTEM DESCRIBTION ..............................................................................................8
3.IMPLEMENTATION …………………………………………………………………10
4.HARDWARE AND SOFTWARE IPLENTATION……………………………………16
5.FURTHER SCOPE………………………………………………………………….17
6. CONCLUTION……………………………………………………………………......18
7. REFERENCES………………………………………………………………………...19

5
ABSTRACT

Road accidents have been very common in the present world

with the prime cause being the careless driving.The necessity to
check this has been very `essential and different methods have
been used for. However with the advancement in the technology,
different governing bodies are demanding some sort of
computerized technology to control this problem of over speed
driving. At this scenario, we are proposing a system to detect the
vehicle which are being driven above the given maximum speed
limit that the respective roads or highway lights.

Keywords

Object tracking, Centroid Tracking,

MobileNet SSD.

6
 Chapter – 1

INTRODUCTION

Over speeding vehicles are major issues foe road safety and needs
proper addressing to minimize the accidents. Excessive speed is
factor in one third of all fatal crashes. Keeping in mind all these
issues that are faced, this paper gives a clear view of how the
process will flow through the software and hardware. A speed
detection means detecting the speed of the vehicles at some
certain range using the internet of things. In this, the monitoring of
all the vehicles in the road and detecting the speed of the vehicle as
well its number plate. If any over speed occurs then it can be
detected by the system and information about the driver and will
be uploaded to traffic police department so that automatic case
filing can be done without any complaint. From this method people
will automatically become aware of the speed in which they are
riding and thus decreasing the speed leading to a safe environment.
Vehicle Speed Detection is done by using the Object Tracking and
the Centroid Tracking where the object tracking is used to detect
the objects on the road and the centroid tracking is used to detect
the speed of the vehicle. The Algorithm used here is MobileNet SSD
algorithm.

7
 2.System Describtion

The system aims to develop a hardware and software based speed

detector where the accidents can be reduced and maintain safe
environment. Automatic case filing can be done without any
complaint. The architecture diagram describes the entire working
process of the application. As shown in the architecture,the whole
system is automated

The speed formula is speed=distance/time. It has a known distance

measured by a tape at the roadside. The cameras will face at the
road perpendicular to the distance measurement unobstructed by
obstacles. The meters per pixel are calculated by dividing the
distance constant by the frame width in pixels. Distance in pixels is
calculated as the difference between the centroids as they pass by
the columns for the zone Distance in meters is then calculated for
the particular zone. Four timestamps (t) will be collected as the car
moves through the FOV past four waypoint columns of the video
frame. Three pairs of the four timestamps will be used to determine
three delta t values. It will calculate three speed values for each of
the pairs of timestamps and estimated distances

8
 Fig.1 Descriptive System Architecture

Hardware Components: Raspberry pi 4

with 4GB RAM Raspberry pi 3b+ Two
cameras Power supply Software
Components: OS:linuxPycharm(code
editor) Python
3.Implemention

The objective of the project is to track the speed of the vehicle

by four point tracking estimation and recognizes the number
plate of the vehicle. The Arduino kit is placed with two cameras.
When a vehicle crosses the first camera it detects the speed of
the vehicle using speed detecting camera and as it detects over
speed it captures the vehicle and stores the data. The image is
then processed using the optical character recognition (OCR) to
detect the registration number from the number plate. A simple
object tracking algorithm relies on keeping track of the
centroids of objects. Typically an object tracker works hand-
inhand with a lessefficient object detector. The object detector
is responsible for localizing an object. The object tracker is

9
responsible for keeping track of which object is which by
assigning and maintaining identification numbers (IDs). This

object tracking algorithm being implemented is called centroid

tracking as it relies on the Euclidean distance between (1)
existing object centroids (i.e., objects the centroid tracker has
already seen before) and (2) new object centroids between
subsequent frames in a video. The centroid tracking algorithm is
a multi-step process. The five steps include:

1. Accept bounding box coordinates and compute centroids

2. Compute Euclidean distance between new bounding
boxes and existing objects
3. Update (x, y)-coordinates of existing objects
4. Register new objects
5. Deregister old objects In order to track and calculate the
speed of objects in a video stream,it need an easy way to store
information regarding the object itself, including:

Its object ID. Its previous centroids (so it can easily compute
the direction the object is moving). A dictionary of timestamps

10
corresponding to each of the four columns in the frame. A
dictionary of x-coordinate positions of the object. These

positions reflect the actual position in which the timestamp was

recorded so speed can accurately be calculated. The last point
boolean serves as a flag to indicate that the object has passed
the last waypoint (i.e. column) in the frame. The calculated
speed in MPH and KMPH. It calculate both and the user can
choose to use by a small modification to the driverscript.Boolean
to indicate if the speed has been estimated (i.e. calculated) yet.

11
Fig.1 This OpenCV vehicle speed estimation project assumes the
camera is aimed perpendicular to the road. Timestamps of a

vehicle are collected at waypoints ABCD or DCBA. From there,

our speed = distance / time equation is put to use to calculate 3
speeds among the 4 waypoints. Speeds are averaged together
and converted to km/hr and miles/hr

12
Fig.2 Top-left: To build a simple object tracking algorithm using centroid
tracking, the first step is to accept bounding box coordinates from an
object detector and use them to compute centroids. Top-right: In the
next input frame, three objects are now present. It need to compute
the Euclidean distances between each pair of original centroids (circle)
and new centroids (square). Bottom-left: The simple centroid object
tracking method has associated objects with minimized object
distances. Bottom-right: It has a new object that wasn’t matched with
an existing object, so it is register
13
14
 Fig.3 Sample screenshot of source code14

Fig.4 Sample screenshot of the implementation.

15
 4.Hardware and Software
implentation

Intel core i5 processor is used with a hard disk comprising of 100GB

space to ensure that the smooth functioning of the software adding
up with a raspberry pi and an aurdino kit is connected to the
system. The raspberry pi comes with an operating system Linux
which is used in overall of this system. The pycharm code editor is
used to program the system with the python programming
language. The two cameras are connected to the raspberry kit to
capture the image of the vehicles.

16
Every development has some drawback or lack of
necessary feature that emerges with the usage and need.
The project can be developed even more by adding vehicle
detection wireless sensing networks and implementing a
wireless sensor network will be another interesting which
will open up much more application areas. Advanced image
processing algorithms and libraries could be used so that
the system can be used efficiently even during
unfavourable lighting conditions and during the night time
as well.

5.Further scope

17
 6.Conclusion

The accidents can be reduced and a safe environment is

implemented. This device is suited for all roads which saves the
lives of many people and is also used to find the stolen vehicles
by using the registered vehicle number.The goal of the project is
to save many lives and reduce accidents in a better way.
Earlydays, the paper represents the aerial tracking in the
hyperspectral domain i.e., the deep tracker performs
exceptionally well with deep features setup in a synthetic
hyperspectral video generated by the digital imaging and
remote sensing image generation(DIRSIG) software where only
the type of the type of the vehicle is determined. Also the
present VASCAR technique is inefficient
18 to track the speed of the
vehicles.
 6. REFERENCES

[1] R. Pelapur, S. Candemir, F. Bunyak, M. Poostchi, G. Seetharaman, and

K. Palaniappan, ―Persistent target tracking using likelihood fusion in
widearea and full motion video sequences,‖ in Proc. 15th Int. Conf.
Inf. Fusion (FUSION), Jul. 2012, pp. 2420–2427.
[2] J. Portmann, S. Lynen, M. Chli, and R. Siegwart, ―People detection
and tracking from aerial thermal views,‖ in Proc. IEEE Int. Conf.
Robot.
Automat. (ICRA), May/Jun. 2014, pp. 1794–1800.
[3] M. Danelljan, G. Bhat, F. S. Khan, and M. Felsberg. (2016).
ECO:Efficient convolution operators for tracking.‖ [Online]. Available:

https:// arxiv.org/abs/1611.09224

19
[4] B. Uzkent, M. J. Hoffman, and A. Vodacek, ―Efficient integration of
spectral features for vehicle tracking utilizing an adaptive sensor,‖
Proc.
SPIE, vol. 9407, p. 940707, Mar. 2015.
[5] B. Uzkent, Real-Time Aerial Vehicle Detection and Tracking Using a
Multi-Modal Optical Sensor. Rochester, NY, USA: Rochester
Institute Technology, 2016.

B. Uzkent, A. Rangnekar, and M. J. Hoffman, ―Aerial vehicle tracking

by adaptive fusion of hyperspectral likelihood maps,‖ in Proc. IEEE
Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), Jul. 2017,
pp. 233– 242.
[6] AFRL. (2009). Wright-Patterson Air Force Basevvi (WPAFB) Dataset.
[Online]. Available:
https://www.sdms.afrl.af.mil/index.php?collection= wpaf
b2009
[7] AFRL. (2007). WAMI Columbus Large Image Format (CLIF) Dataset.
[9][Online].Available:https://www.sdms.afrl.af.mil/index.ph p?
collection= clif2007

20
[10] O. Russakovsky et al., ―ImageNet large scale visual
recognition challenge,‖ Int. J. Comput. Vis., vol. 115, no. 3, pp.
211–252, Dec. 2015.
[11] B. Uzkent, M. J. Hoffman, A. Vodacek, J. P. Kerekes, and B.
Chen, ―Feature matching and adaptive prediction models in an
object tracking DDDAS,‖ Procedia Comput. Sci., vol. 18, pp.
1939–1948, Jan. 2013.
[12] B. Uzkent, M. J. Hoffman, A. Vodacek, and B. Chen,

21