Documente Academic
Documente Profesional
Documente Cultură
Accident
Anuj Jain1*, Nitin Kumar2, Surender Kumar3, Manoj Kumar Shukla4
124
SEEE,Lovely professional university Punjab
a1978jain@gmail.com
3
Professor,ADGITM New Delhi
ABSTRACT
The project involves automation of vehicles for safety purposes. We tried to automate the car to prevent accidents in
the best way, by incorporating ingenuity into it with the help of controllers and microwaves, interacting with the
basic structure of the steering wheel and accelerating.
KEYWORDS: Augmented Car Display; Face Detection, Optical Character
Recognition, Android Control etc.
1
INTRODUCTION
Traditionally, the vehicle has been the development of the man's ambulatory system, meek
to the driver's orders. Recent proposition in communications, controls and embedded
systems have changed this model, bricking the way to the Intelligent Vehicle
Framework. The car is now a dreadful sensor platform, fascinating information from
the environment (and from other cars) and delivering it to drivers and framework to
assist in safe steering, pollution control and traffic administration.
Automation or automatic control is the use of different systems for managing operating devices
such as processors in boiler and boiler treatment, heat transfer to telephone networks,
management and stabilization of aircraft carriers and other applications with interventions.
Minimalism or reduction.
Autonomous vehicles detect the surroundings with the help of laser radar, MPOS audio and
computer vision. Autonomous vehicles have a monitoring system that can analyze sensor data
to distinguish different vehicles on the road, which is very useful when planning a route to the
desired destination.
Tesla Motors is currently promoting technology for driverless cars with automatic systems. The
previous system required the driver to keep his hand on the steering wheel, while the Tesla
allows for an idle period. The system was implemented on October 14, 2015 at Tesla
Software Release 7.0
Google self-driving cars are one of the autonomous vehicles that were developed by Google
Inc. as part of its project to develop technology for most electric vehicles. The software
installed on the Google car is called Google Chrome. The car collects data every time they
rotate, which they then share with other cars in Google, which means Google's self-driving car
program has a 90-year collective driving experience.
The final prototype has developed with new technology which is not only a breakthrough in heavy
traffic congestion, but sensor technology can improve traffic safety. Countries such as the United
Kingdom and the United States are implementing legislation to allow driverless cars.
In February, the U.S. NHTSA has to provide Vehicle-to-Vehicle (V2V) technology for light vehicles.
The technology will allow vehicles to "talk" with each other and ultimately avoid many dangers by
sharing basic safety data such as speed and location 10 times more than a second to improve
safety.
Figure 2-0-3 V2V Communications
It uses an "ad hoc network" where each vehicle has the ability to connect to other vehicles on the
network and have a status equal. V2V, also known as van Net (ad hoc car network), is a variant of
the Mart (Mobile Broadband Network). Many automakers including BMW, Audi, Honda, General
Motors, Volvo and Daimler are working on and developing this technology to improve safety,
blindness and avoid accidents.
Different Technology
Over the last two decades, face detection has proved to be the most interesting field of study for image
processing. In this project, we will cover some of the key aspects of face recognition that are most
profitable in a variety of applications, such as face recognition, facial recognition, facial expression,
gender classification. Identification system. Documentation and monitoring, access to clusters,
science, biology, human computer systems (HIC), digital cosmetics, and more.
Hypothesis:
Face detection is a procedure by which we can extract facial expressions from the human body. Ideas
can now be addressed in different ways, but we generally use four steps to achieve this goal.
In the first step, we localize the areas of the face, which means that we expect those elements of the
image that a person may have.
In the second step, we normalize the open areas, placing the individual front alignment in the correct
position.
In the third step, we extract different facial features, such as eyes, nose and mouth. Etc. And in Step 4,
we are looking at whether the expected item is implemented by one person. We do this using either
sample rules or image databases. The concept of extraction can be solved by various techniques
Hypothesis:
An automated license plate identification (ANPR) was established in 1976 at the United Kingdom
Police Research Branch. However, over the last decade, it has gained significant traction, along
with the improvement of digital cameras and the increase in computing capacity. It is just the
ability to automatically download and recognize symbols on a license plate from an automated
image. It is necessary to have a camera or frame detector that can capture the image, locate the
number in the image, and then extract the symbol of the character marker to translate the pixel into
a numeric character.
The first step is to capture the image using a camera and convert them into RGB so they can be
recycled to carry license plates.
The second step of the developed ANRP algorithm uses the optical recognition algorithm to
identify the vehicle number. The result cropped image is inverted, e.g. All white pixels turn black
and white pixels.
When the lines in the disassembled vehicle license plate are split, the process of dividing the line
now applies the column so that each character can be separated. Each character separately is stored
in a separate variable.
Hypothesis:
.
Humanity is among the most important components of the machine environment, and
donating machines capable of interacting with humans is one of the most interesting and
potentially challenging challenges for modern engineering. Therefore, detecting and tracking
people is an integral part of machine learning and vision should play an important role.
Programs include robotics, entertainment, elderly and disabled research, content-based
indexing.
Our system shows a high detection efficiency compared to many modern detectors and can
run 14 feet on a Raspberry PI computer when using a 640 × 480 image. Our method uses
geometric threshold analysis to efficiently search pyramids and improve accuracy detection
using multi-resolution pedestrian models for pixel-sized pedestrians, which are usually
omitted from a single display method.
Hypothesis:
Hardware
Overrides the level of digital material in the physical world around us. With one of these apps on
your smartphone, you can hold your camera's camera to capture pictures on city streets and then get
on-screen material for your surroundings.
While these augmented reality programs can provide information and entertainment, format factors
remain elusive. We have to hold a smartphone and watch the screen like you're in a Star Trek
audience, and you're the one with the eye on Trida instead of drinking.
Figure 3-0-4 Components of Google Glass
References
1. HLDI, Honda Accord collision avoidance features: an update. Bulletin Vol. 31. No. 16, Highway
Loss Data Institute, Insurance Institute for Highway Safety, Arlington, Va, USA, 2014.
3. DPTI, SA becomes first Australian jurisdiction to allow on-road driverless car trials, Department
of Planning, Transport and Infrastructure, 2016.
6. BITRE, Fatal road crashes in Australia in the 1990s and 2000s: crash types and major factors,
Bureau of Infrastructure, Transport and Regional Economics, Canberra, Australia, 2011.
7. NHTSA, National Motor Vehicle Crash Causation Survey, National Highway Traffic Safety
Administration, U.S. Department of Transportation, 2008.
9. R. Hoogendoorn, B. Van Arem, and S. Hoogendoorn, “Automated driving, traffic flow efficiency,
and human factors,” Transportation Research Record, vol. 2422, pp. 113–120, 2014.
12. D. Milakis, B. Van Arem, and B. Vanwee, “Policy and society related implications of automated
driving: A review of literature and directions for future research,” Journal of Intelligent Transportation
Systems: Technology, Planning, and Operations, vol. 21, no. 4, pp. 324–348, 2017.