IJRIT International Journal of Research in Information Technology, Volume 1, Issue 11, November, 2013, Pg. 469-475

International Journal of Research in Information Technology (IJRIT)

www.ijrit.com

ISSN 2001-5569

Detection of Sudden Pedestrian Crossings for Driving Assistance Systems Gopu Sudarshan Reddy1, Aruna Kumari Kakumani2 1

2

PG student, Department of Electronics and Communication Engineering, VNR Vignana Jyothi Institute of Technology, Hyderabad, India. 1 [email protected]

Assistant Professor, Department of Electronics and Communication Engineering, VNR Vignana Jyothi Institute of Technology, Hyderabad, India [email protected]

Abstract In this paper, Detection of Sudden Pedestrian Crossings For Driving Assistance System based on ARM is designed, in which the embedded chip and the programming techniques are adopted. The central monitor which adopts S3C2440 chip as controller is the core of the whole system. First, USB camera video images are collected by the embedded Linux system, processed, compressed and transferred by the processing chip. And then detects, only the crossing pedestrians as early as possible just as they enter the view of the mounted camera using OpenCV and maintains an alarm System to alert the Driver, and then slowly applies break system. Tests show that the presented Pedestrian detection system is reliable and stable. And it has a perfect application prospects with real-time.

Keywords: Video Capture, S3C2440A, Embedded Linux, DC Motor.

I.INTRODUCTION The main aim of this system is to design DETECTION OF SUDDEN PEDESTRIAN CROSSINGS FOR DRIVING ASSISTANCE SYSTEMS. We are aware of the problem of detecting sudden pedestrian crossings to assist drivers in avoiding accidents. In this embedded system, the application has two major requirements: to detect crossing pedestrians as early as possible, just as they enter the view of the car-mounted camera and to maintain alarm System to alert the Driver. In this System using ARM 32 bit Microcontroller has feature of image/video processing by using various features and classification algorithms have been used for pedestrian detection. It

Gopu Sudarshan Reddy , IJRIT

469

overcomes the performance in terms of sensors and hardware cost is also too high. So, our design Embedded system that detects partially visible pedestrians just as they enter the camera view, with low false alarm rate and high speed. This system takes capture image by means of web camera connected to ARM microcontroller through USB and the image is processed by using image processing technique. Image processing is any form of signal processing for which the input is an image, such as a photograph or video frame; the output of image processing may be either an image or a set of characteristics or parameters related to the image. When any pedestrian is detected it alerts driver by providing alarm sound and also it stops vehicle automatically. The display unit in vehicle provides clear details at position it detects pedestrian either right or left. In this system we are going use S3C2440 based microcontroller, which the current dominant microcontroller in mobile based products.

II. HARDWARE SYSTEM DESIGN The hardware system includes processor, USB Camera, Stepper Motor, and a Buzzer to make an alert signal. In this paper SAMSUNG S3C2440 [2] ARM9 processor is chosen to complete the core control; Logitech CMOS camera is used as a video-capture. As shown in Figure 1, block diagram of the hardware system design.

REGULATED POWER SUPPLY

S3C2440 (ARM9)

USB DEVICE

DISPLAY UNIT

USB CAMERA

STEPPER MOTOR

BUZZER

Figure 1.Block diagram of the hardware system design.

2.1 SAMSUNG S3C2440 Processor . S3C2440A microcontroller [1]. As shown the block diagram in Fig 1. We use the latest SAMSUNG’s S3C2440A. Its low power, simple, elegant and fully static design is particularly suitable for cost- and powersensitive applications. It adopts a new bus architecture known as Advanced Micro controller Bus Architecture (AMBA). The S3C2440A offers outstanding features with its CPU core, a 16/32-bit ARM920T RISC processor Gopu Sudarshan Reddy , IJRIT

470

designed by Advanced RISC Machines, Ltd. The ARM920T implements MMU, AMBA BUS, and Harvard cache architecture with separate 16KB instruction and 16KB data caches, each with an 8-word line length. By providing a complete set of common system peripherals, the S3C2440A minimizes overall system costs and eliminates the need to configure additional components. Mini2440 have two flashes, one is the NOR flash, model SST39VF1601, size 2 Mbytes. The other is the NAND flash, model K9F1208, size 64 Mbytes. S3C2440 [1]support both flash to start the department of EC, by DIP switch S2, you can choose from NAND or NOR for your system. Most of the actual products using a NAND flash chip are enough, because we learn for the convenience of users, it also retains the NOR flash. NAND flash does not have the address line, it has a dedicated control interface connected with the CPU, for the 8-bit data bus, but this does not mean that NAND flash read and write data will be very slow. Most of the USB or SD cards are made of NAND flash equipment.

2.2. USB Camera Camera with 1.3 million pixels is selected in the built system. Particularly in poor light, the speed of CMOS camera is slower, but its price very low, and CMOS has power consumption only when the circuit is connected, it is generally used low-end cameras, digital cameras and toys. There is a 20P plug with 2mm pitch in ARM used as extension to connect the camera. This web camera continuously monitors the room and sends the video.

2.3 DC MOTOR AND DRIVER IC In any electric motor, operation is based on simple electromagnetism. A current-carrying conductor generates a magnetic field; when this is then placed in an external magnetic field, it will experience a force proportional to the current in the conductor, and to the strength of the external magnetic field. As you are well aware of from playing with magnets as a kid, opposite (North and South) polarities attract, while like polarities (North and North, South and South) repel. The internal configuration of a DC motor is designed to harness the magnetic interaction between a current-carrying conductor and an external magnetic field to generate rotational motion.

2.4 Buzzer A buzzer or beeper is an audio signaling device, which may be mechanical, electromechanical, or piezoelectric. Typical uses of buzzers and beepers include alarm devices, timers and confirmation of user input such as a mouse click or keystroke.

III.SOFTWARE DESIGN The system selected Linux operating system [3][4] as software platform, the code for the application is developed using QTCreater Software in C++ language and the main functions are Capturing the image, Processing the image to find whether detected image is human ,or not Using openCV libraries, an alarm system and then slowly applying breaks to stop the vehicle.

Gopu Sudarshan Reddy , IJRIT

471

Initialization Of Camera

If No Image captured Image Capturization

If yes

Pedestrian Detection Using Haar Features Motor Runs Normally

Alert sound of Alarm

Applying Break System Figure 2: Flow chart of software system

3.1 Video capture module Video Capture Based Video4Linux Video4Linux (referred to as "V4L") [1][5] is a Linux kernel on the video device driver, which is for video equipment, application programming interface functions to provide a system. The basic process of video capture shown in Figure 3. V4L USB camera using the programming on the need to use Linux system calls the next two, respectively, ioctl () and mmap (). Application to get the camera image data collected in two ways, namely read() (method of direct reading) and mmap() (memory mapping method). mmap() system call allows processes mapping the same file through memory sharing achieved, the advantages of high efficiency, because the process can directly read and write memory, copy any data without the need to speed up the I / O access, the system is Using this method. 3.2 QT Creator Qt is a cross-platform application framework that is widely used for developing application software with a graphical user interface and also used for developing non-GUI programs such as command-line tools and consoles for servers. Qt uses standard C++ but makes extensive use of a special code generator together with several macros to enrich the language. Qt can also be used in several other programming languages via language bindings. It runs on the major desktop platforms and some of the mobile platforms. It has extensive internationalization support. NonGUI features include SQL database access, XML parsing; thread management, network support, and a unified crossplatform application programming interface (API) for file handling. 3.4 OpenCV Computer vision is a rapidly growing field, partly as a result of both cheaper and more capable cameras, partly because of affordable processing power, and partly because vision algorithms are starting to mature. OpenCV itself has played a role in the growth of computer vision by enabling thousands of people to do more productive Gopu Sudarshan Reddy , IJRIT

472

work in vision. With its focus on real-time vision, OpenCV helps students and professionals efficiently implement projects and jump-start research by providing them with a computer vision and machine learning infrastructure that was previously available only in a few mature research labs. The purpose of this text is to: Better document OpenCV—detail what function calling conventions really mean and how to use them correctly. Rapidly give the reader an intuitive understanding of how the vision algorithms work. Give the reader some sense of what algorithm to use and when to use it.Give the reader a boost in implementing computer vision and machine learning algorithms by providing many working coded examples to start from. 3.5 Detection Of Pedestrians using Haar-like features This paper describes a vision-based pedestrian detection system using Haar-like features. Pedestrian detection in cluttered environment is an open problem. The major difficulties lie in[4]:The size, color and style of pedestrian clothing are very diverse, which causes the different appearance of same pedestrian .A Pedestrian is a non-rigid body. In other words, the shape and size of a pedestrian varies greatly, and therefore the model of a pedestrian is much more complex than that of rigid objects. The clutter background. It does not matter if we are analyzing images from a typical city or from a country traffic environment the background formed by vehicles, trees, wire poles, and billboards is very cluttered. Hundreds of features are used in a real and robust classifier. Can a simple feature (i.e. a value) indicate the existence of a face? .All faces share some similar properties; the eyes region is darker than the upper-cheeks. The nose bridge region is brighter than the eyes. That is useful domain knowledge

Adaboost Constructs a “strong” classifier as a linear combination of weighted simple “weak” classifiers.

Initially, all the weights are set equally, Repeat T times Step 1: choose the most efficient weak classifier that will be a component of the final strong classifier Step 2: Update the weights to emphasize the examples which were incorrectly classified Final (strong) classifier is a weighted combination of the T “weak” classifiers Weighted according to their accuracy

 1 h(x)    0

Gopu Sudarshan Reddy , IJRIT

T

  h t 1

t

t

(x) 

1 2

T

  t 1

t

otherwise

473

Experimental Results: Here in the result only human being is detected but not any object. It justifies the title of the paper ” Sudden Pedestrian Detection”

Gopu Sudarshan Reddy , IJRIT

474

IV.CONCLUSION AND FUTURE SCOPE In this paper, The project detection of sudden pedestrian detection for driving assistance systems has been successfully designed and tested. It has been developed by integrating features of all the hardware components and software used. Presence of every module has been reasoned out and placed carefully thus contributing to the best working. Secondly, using highly advanced ARM9 board and with the help of growing technology the project has been successfully implemented. Here we are giving alert warning through buzzer. In future we can give alert message through voice commands from the board itself.

V. References [1]

Samsung. S3C2440A 32Bit CMOS Microcontroller User's Manual [Z]. Samsung Electronics Corp, 2003.

[2]

S3C2440A Microcontroller User's

[3]

Siyi.Zou, “Design and Application of Embedded Linux”. Beijing: Tsinghua University

ManualRevision1,http://www.sams ungsemi.com/ Press, pp:90-

93,2002. [4]

Hong Cheng and Nanning Zheng and Junjie Qin. "Pedestrian detection using sparse Gabor filter and

.

Support vector machine." In Pro-ceding’s of IEEE Intelligent Vehicles Symposium, 2005..

[5]

P Viola and M. Jones. "Rapid object detection using a boosted cascade of simple features." In IEEE CVPR 2001, 2001.

[6]

Cyber cars. Cybernetic technologies for the car in the city. [Online], www.cybercars.org, 2001.

[7] Intel - Intel Technologies Journal, http://www.intel.com/technology/itj/ 2005/volume09issue02/art03 Learning vision/p04 face detection.htm

Gopu Sudarshan Reddy , IJRIT

.

475

Detection of Sudden Pedestrian Crossings for Driving ... - IJRIT

a graphical user interface and also used for developing non-GUI programs such as command-line tools and consoles ... access, XML parsing; thread management, network support, and a unified cross- ... projects and jump-start research by providing them with a computer vision and machine learning infrastructure that.

463KB Sizes 2 Downloads 266 Views

Recommend Documents

Detection of Sudden Pedestrian Crossings for Driving ... - IJRIT
First, USB camera video images are collected by the embedded Linux system, processed, ... Keywords: Video Capture, S3C2440A, Embedded Linux, DC Motor.

Detection of Sudden Pedestrian Crossings for Driving ...
IJRIT International Journal of Research in Information Technology, Volume 1, Issue 11, ... VNR Vignana Jyothi Institute of Technology, Hyderabad, India.

Multispectral Pedestrian Detection: Benchmark Dataset ...
Multispectral Pedestrian Detection: Benchmark Dataset and Baseline. Soonmin Hwang, Jaesik Park, Namil Kim, Yukyung Choi, In So Kweon. Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea. Figure 1: Examples of proposed multis

A Framework for Real Time Detection of ... - IJRIT
widely used social networking sites. ... profiles [7], [8] for confusing users, blacklisting URLs for security reasons [9], [10] and tools for reporting spam. [11].

A Framework for Real Time Detection of ... - IJRIT
Twitter is one of the famous OSN sites that provide a platform for virtual communities. ... hackers who will make use of the service for sharing malicious content. ... profiles [7], [8] for confusing users, blacklisting URLs for security reasons [9],

Vision-Based Pedestrian Detection for Rear-View ...
object detection tasks and improve benchmark results [10],. [7]. As illustrated in .... system running on the laptop is composed of several algo- rithmic blocks as ...

Fast Pedestrian Detection Using a Cascade of Boosted ...
on pedestrian detection using state-of-the-art locally extracted fea- tures (e.g. ... meaningful features if there is a large variation in object's ap- pearance .... The final strong classifier can be .... simple nonpedestrian patterns in the early s

Pedestrian Detection with a Large-Field-Of-View ... - Semantic Scholar
miss rate on the Caltech Pedestrian Detection Benchmark. ... deep learning methods have become the top performing ..... not to, in the interest of speed.

Real-time Pedestrian Detection with Deformable Part Models
of a pedestrian model to detect small pixel-sized pedestrians normally missed by ..... processing the image data that consists of first creating a densely sampled ...

Real-Time Pedestrian Detection With Deep ... - Research at Google
More specifically, we employ the soft-cascade from Benenson et al. [4] ..... ments. IEEE Trans. on Pattern Analysis and Machine Intelligence (T-PAMI), 2009.

Real-Time Pedestrian Detection With Deep Network ...
We present a new real-time approach to object detection that exploits the efficiency of cascade .... Figure 2: The architecture of the baseline deep network for pedestrian detection. ..... Histograms of oriented gradients for human detection.

Sonar Signal Processing Methods for the Detection and ... - IJRIT
and active sonar systems can be used to monitor the underwater acoustic environment for incursions by rapidly moving ... detection and tracking of a small fast surface craft (via its wake) in a highly cluttered shallow water ..... automatic detection

Fire Detection Using Image Processing - IJRIT
These techniques can be used to reduce false alarms along with fire detection methods . ... Fire detection system sensors are used to detect occurrence of fire and to make ... A fire is an image can be described by using its color properties.

Fire Detection Using Image Processing - IJRIT
Keywords: Fire detection, Video processing, Edge detection, Color detection, Gray cycle pixel, Fire pixel spreading. 1. Introduction. Fire detection system sensors ...

Various possibilities of Clone Detection in Software's: A Review - IJRIT
In software development process, cloning of software code is becoming common. ... (C) Clone Types: Two code fragments are similar according to textual ...

Enhanced Dynamic Detection of Code Injection Attack in OS ... - IJRIT
At runtime, a monitor compares the behavior of the variants at certain ... The global decision is made by a data fusion center, ... complete solution. Modern static ...

Detection Elimination and Overcoming of Vampire Attacks in ... - IJRIT
Ad hoc wireless sensor networks (WSNs) promise exciting new applications in the near future, such as ubiquitous on-demand computing ... In the one cause of energy loss in wireless sensor network node in the idle consumption, when the nodes are not pa

Detection and Prevention of Intrusions in Multi-tier Web ... - IJRIT
In today's world there is enormous use of Internet services and applications. ... networking and e-commerce sites and other web portals are increasing day by ...