Object Detection in Image Using Particle Swarm Optimization

Abstract

Image matching is a key component in almost any image analysis process. Image matching is crucial to a wide range of applications, such as in navigation, guidance, automatic surveillance, robot vision, and in mapping sciences. Any automated system for three-dimensional point positioning must include a potent procedure for image matching. Most biological vision systems have the talent to cope with changing world. Computer vision systems have developed in the same way. For a computer vision system, the ability to cope with moving and changing objects, changing illumination, and changing viewpoints is essential to perform several tasks. Object detection is necessary for surveillance applications, for guidance of autonomous vehicles, for efficient video compression, for smart tracking of moving objects, for automatic target recognition (ATR) systems and for many other applications. Cross-correlation and related techniques have dominated the field since the early fifties. Conventional template matching algorithm based on cross-correlation requires complex calculation and large time for object detection, which makes difficult to use them in real time applications. The shortcomings of this class of image matching methods have caused a slow-down in the development of operational automated correlation systems. In the proposed work particle swarm optimization & its variants based algorithm is used for detection of object in image. Implementation of this algorithm reduces the time required for object detection than conventional template matching algorithm. Algorithm can detect object in less number of iteration & hence less time & energy than the complexity of conventional template matching. This feature makes the method capable for real time implementation. In this thesis a study of particle Swarm optimization algorithm is done & then formulation of the algorithm for object detection using PSO & its variants is implemented for validating its effectiveness.