Introduction :


Video-based car navigation systems are emerging as he n ext generation car navigation systems, which provide more realistic navigation services than conventional map-based car navigation systems. Fig. shows a block diagram of techniques required to make video-based navigation systems. First, object information is gathered via cameras, . Then, feature extraction is performed to obtain edge, color, object information. Extracted features contain various noises due to unknown objects such as shadow, damaged road surface and cars blocking road markings. Lastly, outliers removal and object recognition techniques are used to recognize road and objects on the road. To recognize objects on the road, lane detection is essential. However, lane detection is a tough problem for various illumination conditions such as shadow, sunset, backlights, and so on . In the paper, a novel idea is presented to recognize lane for a various road and illumination, lane markings conditions such as damaged road surfaces blocked by a car, shadow, backlights, etc. For robust lane detection, the shape information of extracted lane markings and a moving average filtering are combined, improving the recognition accuracy

A robust lane detection system is essential to make video-based navigation systems, making possible to provide more realistic navigation services on a live video. However, conventional lane recognition systems have a difficulty to recognize lanes due to various road conditions such as cars, damaged road surface, pedestrians, and so on. Here, a novel approach to make a robust lane recognition system is presented.




Existing System:


In the current scenario there is no navigation system by means of which a vehicle can navigate on its own and reach its destination. It is considered much difficult as the vehicle does not know how to navigate its path. Here we have designed a system by means of which we have created a robot that can navigate on its own without any third party help and reach its destination.


Proposed System:


Intelligent Vehicles, as a main part of Intelligent Transportation Systems (ITS), will have great impact on transportation in near future. They would be able to understand their immediate environment and also communicate with other traffic participants such as other vehicles, infrastructures and traffic management centres. Intelligent vehicles could navigate autonomously in highway and urban scenarios using maps, GPS, video sensors and so on. To navigate autonomously or follow a road, intelligent vehicles need to detect lanes. It seems that the best cue for lane detection is to use the lane markings painted on roads and it should be noticed that among passive and active sensors, the video sensors are the best candidate for finding lane markings. In this paper we present a method for lane detection in image sequences of a camera mounted on a vehicle. The main idea is to find the features of the lane in consecutive frames which match a particular geometric model.
There modules that are linked with the proposed system are

User management
Comm Communication
Image Capture
Image Processing
Training & Testing
Virtual image Representation

The Block Diagram of the proposed system is as given below




User Management:

Here the administrator is the one who is taking the initial positioning. Here we deal with the management of the system. The administrator can can do the testing. The administrator can even view the path that the robot traces and even control it manually if he desires.

Comm communication:

It is by means of this port that the robot can do the navigation. The instructions for the robot to proceed in any direction is give through this port. What we have to see here is that this is a single way communication . ie the robot is given instructions and the robot obeys it and does not give back the feedback for executing the command.



Image Capture:

Here in this module we deal with the image capture. The image is captured by means of a camera that is placed on the robot. It is by the video that is captured from the camera that the robot does the navigation properly.

Image Processing:

Here the image that has been captured is manipulated so that the robot can track its way . The processing of the image involves colour detection so that the path to move could be found out.

Training & Testing:

Here we deal with the training and he testing of the robot so that our system can work properly. We at first create a dummy path and then obtain the response and thereby determine if the robot is working properly. In this way we train the robot to obtain the correct output.

Virtual Image Representation:

This is a virtual representation to monitor the robot and the path that it is taking so as to monitor the robot.







Software Specification :
Front end : J2EE
Back end : My Sql
Operating System : Windows/ Linux
IDE : Net Beans

Hardware Specification :
Processor : Pentium IV

System Bus : 32 BIT

RAM : 512 MB

HDD : 40 GB

Display : SVGA Color
Key Board : Windows/Linux Compatible
Web Cam : Logitech

[attachment=4178]