DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

TECHNICAL SEMINAR

ON

“REAL-TIME ACCIDENT DETECTION IN ROAD SURVEILLANCE ’’

PRESENTED BY:
NAME : M. SUDHIR

BRANCH : CSE-B

ROLLNO : 195U1A0576
ABSTRACT
• Accidents have been a major cause of deaths in India. More than 80% of accident-related
deaths occur not due to the accident itself but the lack of timely help reaching the accident
victims. In highways where the traffic is really light and fast-paced an accident victim
could be left unattended for a long time. The intent is to create a system which would
detect an accident based on the live feed of video from a CCTV camera installed on a
highway. The idea is to take each frame of a video and run it through a deep learning
convolution neural network model which has been trained to classify frames of a video
into accident or non-accident. Convolutional Neural Networks has proven to be a fast and
accurate approach to classify images. CNN based image classifiers have given accuracy's
of more than 95% for comparatively smaller datasets and require less preprocessing as
compared to other image classifying algorithms
INTRODUCTION
• Nowadays, road accidents have become very common. As more and more people are buying automobiles,
the chances of road accidents are increasing day by day. Also, people have also become more careless now
as compared to earlier times. Not many people follow the traffic rules and in larger cities, there are various
modes of transports available, the roads are becoming narrower day by day and the cities have become
more crowded. Thus, road accidents are bound to happen
• Around to 1.35 million people lose their lives due to road accidents with every passing year. ▪Talking about
the India, as per the reports approx. 13 people die each hour as a victim to it. ▪ Looking to the present
scenario about 140,000 people die per year making India being the top on the list of losing lives due to
road traffic accidents. Such accidents undergo in three phases. ▪First phase of an accident is considered
with the last few minutes or seconds of the victim’s death by the accident, as of 10% of such deaths
contributed in it. ▪The Second phase holds the time of an hour of the accident that is with the death
percentage as (75% of all). Third phase of it holds 15% as a death rate and the duration is a week or more..
EXISTING SYSTEM

• ▪In existing system live videos are visible to security personalities but due to
large number of cameras fast detection of accident is not possible.
• Video based and call based emergency services are provided in existing system.
PROPOSED SYSTEM
• The main moto is to incorporate or propose such a system that is properly able to detect an
accident from the available video footages provided through the cameras. The system
behaves as a tool that works out at the time of need along with the quick response time to
the authorities for the same.
• The main focus is to have a short or quick response time in order to implement the further
things early as possible. For this we are using advanced Deep Learning Algorithms
• The proposed model is a fusion of CNN and LSTM layers for continuous video
classification taken from a camera
CONVOLUTION NEURAL NETWORK

• A CNN is a kind of network architecture

for deep learning algorithms and is
specifically used for image recognition
and tasks that involve the processing
of pixel data. There are other types of
neural networks in deep learning, but for
identifying and recognizing objects, CNNs
are the network architecture of choice.
LONG SHORT –TERM MEMORY

• LSTMs are predominately used to learn, process,

and classify sequential data because these
networks can learn long-term dependencies
between time steps of data. Common LSTM
applications include sentiment analysis,
language modeling, speech recognition,
and video analysis.
• Long short-term memory is an artificial neural
network used in the fields of artificial
intelligence and deep learning.
ADVANTAGES
• The major advantages of this system are cost effective,
• assured safety,
• victim life can be save quickly,
• better accuracy,
• reduce the chance of human error.
• Keywords: GPS, GSM, Accelerometer Sensor, Mobile Application
DISADVANTAGES

• The main weakness of this system is that there is a possibility of false

reporting of an accident at low speeds, where the system struggles to
ascertain reliably whether the user is in the vehicle.
FUTURE SCOPE

• Future Enhancement is being planned to further analyze and enhance the protocol
towards a social cause and helps create a system which guarantees that no individual is
left unattended or
• helpless in an unforeseen event of an accident, in turn, securing and maintaining the
quality of
• life to the highest standards
CONCLUSION

• We conclude that Accidents are one of the most common problems that humanity faces
on a daily basis, leading to loss of both life as well as property. The proposed system
provides a very viable
• and effective solution to this problem. The proposed vehicle accident detection system
can track an accident at its moment of occurrence and sends an instantaneous alert SMS
regarding
• the accident to the nearby hospitals and police stations which includes details like
timestamp and the geographical location
THANK YOU