Intelligent Car

Gabriel Gheonea
Transilvania University from Brasov
Sibiu, Romania
See full Bio Contact
Entry date: 17-Apr-2013
Final Submission: 01-Jan-2014
The porpouse of this project is to design and build an inteligent car that is able to recognise traffic signs and obstacles.
Using a video camera and a powerful processing unit, the car can adapt the speed and avoiding obstacles without manual intervention.

Project details

I. Introduction

 Autonomous mobile robots are  characterized by nonlinear and complex dynamics, such as turning and static friction, and noisy and typical harsh outdoor environments. Robot navigation in outdoor environments requires a real time image processing at variable natural illumination, bright sunlight, clouds, etc. Different methods on mobile robot navigation include behavioral based of vehicle from combination of  several behaviors including trajectory tracking, target tracking, obstacles avoidance, landmark recognition systems, number recognition, soccer robot navigation.

II. Intelligent Car Architecture Design

The system architecture design is composed of embedded modules with special or universal function for the car control process. The central control embedded has many functions such as the system for battery management, motion control system, image recognize system and others.

 Basically this intelligent robot car consists of an process unit (Colibri - Toradex) and a video camera placed in front. The function of the camera is to capture the image (scene) in front of the robot car. In this project, special ability goes to the robot car where it can detect a color object or number in front of it, avoid obstacles and recognize traffic signs.

III. Software Implementation 

Computer Vision is the science of extracting useful information from a digitalimage. A digital camera or camcorder captures an image. Next, the image is processedand useful information gathered from the image (ie. objects) is relayed to the maincontrol program.

The vision system capability is to react to various types of traffic situations. Together with processing image data there has to be artificial intelligence implemented with ability to predict a critical traffic situations.

 This project describes an automatic navigation of a intelligent robot car that utilizes the video feedback from a camera to a process unit for the purpose of video processing. That would than enable the robot car to track and move without manual intervention.

 A series of algorithm for object and number recognition will be applied to recognize the  obstacles and traffic signs in the video frame that is captured by the video camera.This application is similar to the human eyes. Normally human eyes will focus on any object in front of him or her if there is movement of object in front of the human eyes. Human eyes will start to move to left or right if the target object moves to left or right. This is much similar to the project where the intelligent robot car will decide on its own whether it should turn left, turn right, or remain unchanged.

 IV. Object Recognition

 Object recognition in computer vision is the task of finding a given object in an image or video sequence. Humans recognize a multitude of objects in images with littleeffort, despite the fact that the image of the objects may vary somewhat in different viewpoints, in many different sizes and scale or even when they are translated or rotated. Objects can even be recognized when they are partially obstructed from view. This task is still a challenge forcomputer vision system in general.

Object tracking, by definition, is to track an object (or multiple objects) over a sequence of images. Object tracking, in general, is a challenging problem. Difficulties in tracking objects can arise due to abrupt object motion, changing appearance patterns of the object and the scene, non-rigid object structures, object-to-object and object-to-scene occlusions, and camera motion. Tracking is usually performed in the context of higher level applications that require the location and/or shape of the object in every frame.

V. Traffic Sign Recognition

 Traffic Sign Recognition (TSR) is used to regulate traffic signs, warn a driver, and command or prohibit certain actions. Fast real-time and robust automatic traffic sign detection and recognition can support and disburden the driver and significantly increase driving safety and comfort.




Automatic recognition of traffic signs is also important for an automated intelligent driving vehicle or for driver assistance systems


Comments Hide