Compared to still images, video sequences provide more information about how objects and scenarios change over time. For many high vision purposes, detecting low-level objects in an image is of great importance. These objects, which can be 2D or 3D, are called blobs. This Project describes segmentation, detection, and counting of objects as blobs in a real scenario. For object recognition, navigation systems and surveillance systems, object tracking is an indispensable first-step. The conventional approach to object tracking is based on the difference between the current image and the background image. The algorithms based on the difference image are useful in extracting the moving objects from the image and track them in consecutive frames. The proposed algorithm, consisting of three stages i.e. background elimination, foreground detection and tracking using Gaussian Mixture Model. Blob Analysis is applied on an images, so as to observe the object size and counting of the object. Simulation has been done by MATLAB. Blood Vessel Segmentation & Detecting Multiple Objects Using Blob Detection
1.Blob analysis block, parameters such as number of blobs per image and the area of blobs can be used directly for object detection. Finally a Blob counting block is used to count and display the total number of objects.
2.In Image processing, blob detection refers to modules that are aimed at detecting points and/or regions in the image that differ in properties like brightness or color compared to the surrounding. Blobs is defined as a region of connected pixels. Blob analysis is the identification and study of these regions in an image.
In this project the algorithm uses Gaussian Mixture Model, a background modeling method to extracting moving objects and for trajectory prediction
To create optimized system for detecting and counting objects in real scenario.
Optimised segmentation technique for object detection
Verify the performance of our proposed work using Matlab r2013a