Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 17

WELCOME

TO

ANNAMACHARYA P.G. COLLEGE OF COMPUTER


STUDIES NEW BOYANAPALLI, RAJAMPET - 516126.
Embeeded night vision system for pedestrain detection

Under the Guidance of Presented By


C.SIVAKRISHNAIAH, K.V. Rakesh Kumar
ASSISTANT PROFESSOR, (regd.no.215N1F00C9)
DEPT of MCA, II MCA, IV SEM,
APGCCS, Rajampet. APGCCS,RAJAMPET.
Abstract
• Assistive vision-based solutions for the driver extend the capabilities of human vision and support
safe travel.
• The proposed night-vision system for pedestrian detection processes thermal images using a
proprietary ODROID XU4 microcomputer under Ubuntu MATE operating system.
• We applied a cascade object detector for the task of human silhouette detection in context of thermal
imagery and contrasted the results with the state of the art deep learning approach.
CONTENTS
• ABSTRACT
• EXISTING SYSTEM
▫ Dis Advantages
• Proposed system
▫ Advantages
• System Architecture
• System Modules
▫ User module
Existing System
 In recent years, many systems have been developed to improve driving in poor visibility conditions.
 Most of the elaborated scientific solutions, apart from products implemented in premium cars, were
designed in the form of a system operating on a laptop, with quite large system resources and
computing power.
 Moreover, it is indispensable in the development of a new device, where tests under real-life
conditions are carried out.
Disadvantages
 Until now, no perfect system has been obtained and researches on improving are still ongoing.
PROPOSED SYSTEM
 we show that a mobile system for pedestrian detection in severe lighting conditions
can be build using state of the art algorithms and widely available hardware.
 The proposed night-vision system for pedestrian detection processes thermal images
using a proprietary ODROID XU4 microcomputer under Ubuntu MATE operating
system. We applied a cascade object detector for the task of human silhouette
detection in context of thermal imagery and contrasted the results with the state of
the art deep learning approach.
Advantages of proposed system
 effectiveness
System Architecture
Modules
User module
Upload Night Vision Image
Night Vision Pedestrian Detection using YOLOV2
Vision Pedestrian Detection using HAAR + AdaBoost
Upload Night Vision Image

click on Upload Night Vision Image button and upload image and
I am selecting test.png image and then click on Open button to
load image.
Night Vision Pedestrian Detection Using YOLOV2

 uploaded original image and hardly we can see the pedestrian


and now try to detect that pedestrian using YOLOV2 algorithm by
clicking on Night Vision Pedestrian Detection using YOLOV2
button
Vision Pedestrian Detection Using HAAR + Adaboost

First image is the original image and second image is the resultant
image from HAAR + ADABOOST algorithm .
Algorithm able to detect pedestrian successfully and putting
bounding box across detected pedestrian.
Algorithms
Yolov2
HAAR + ADABOOST
These Algorithms Are Used To Develop The Project
Yolov2
The basic flow of YOLOV2 face detection algorithm
In the YOLOV2 algorithm, the resolution of the pre-training
image is 448×448
YOLO v2 is faster than other two-stage deep learning object
detectors, such as regions with convolutional neural networks
(Faster R-CNNs).
The YOLO v2 model runs a deep learning CNN on an input image
to produce network predictions. The object detector decodes the
predictions and generates bounding boxes.
Haar + Adaboost

Haar cascade is an algorithm that can detect objects in images,


irrespective of their scale in image and location.
This algorithm is not so complex and can run in real-time. We can
train a Haar-cascade detector to detect various objects like cars,
bikes, buildings, fruits, persons also etc.
THANK YOU

You might also like