In recent years, extraction of information from remote sensing images is an active topic of research. Feature extraction from an image is performed by image segmentation by dividing the image into distinct and self-seminar pixel groups. In remote sensing images, large quantity of texture information is present. So, it is difficult and time consuming process to segment objects from the background in remote sensing images. Many algorithms have been proposed for the purpose of segmentation of remote sensing images. Thresholding is a simple technique but effective method to separate objects from the background. A commonly used method, the Otsu method, improves the image segmentation effectively. It is the most referenced thresholding methods, as it directly operates on the gray level histogram. In this project, Otsu thresholding algorithm is used to segment the roads and residential areas from the vegetation areas in remote sensing images.

The vehicle congestion on the road is increasing day by day and also the management of such large traffic by traditional approach isn’t adequate enough. To eliminate this problem, the project is developed using machine learning in which the testing model is trained to extract the needed image about traffic Information. Extracted information from image sequences of testing model can give us real information to create the database which is the captured images like accident, foggy places, collision of the vehicles, traffic signal, no traffic jam etc. take the image from testing model and processing the trained model which compares the new image and trained image and identify the reason for violation or reason for accident. Data processing will be done to determine the reason under the cause of the accident. This application is utilizing image processing methods designed and modified to the needs and constraints of traffic analysis. Therefore, it shows that it can reduce the traffic congestion and avoids the time being wasted.

No abstract

A flash and long-exposure image pair captured in a dark environment is blurred and noisy. To remove this blur or noise from the image pair there are so many deblurring techniques existing. In this paper implemented a new technique for Restoration of Color Images is introduced. In previous methods, image integration is performed only for well-aligned images, which is a difficult process. This problem can be solved by transferring the color of the flash image using a small fraction of the corresponding pixels in the long-exposure image. Proposed method integrates the color of the long-exposure image with the detail of the flash image using Speeded-Up Robust Features (SURF). This method does not require perfect alignment between the images than the previous methods. Proposed method generates integrated image which has a high contrast than the previous method which is based on SIFT.

Pick n place robot is very interesting, although this type of concept based circuits developed almost 10 years back ago. In previous pick n place robot circuits they may use Bluetooth or infrared, but in this we use radio frequency. Here in this, we use keypad which enables switching "forward, backward, right and left" to pick & place an object. It can be used to move the robot from any distance over limited range.