Localization of Objects in Noisy Scenes for Robotics Applications Using Wigner Distribution

This paper presents a new method for localization of objects in a noisy scene using Wigner Distribution (WD). We have superimposed noise as high 100% random noise as well as upto -10 dB Signal to Noise Ratio (SNR). With such extreme amount of noise, it is difficult to locate the object with our eyes. However, with the proposed method we can locate the object. The Wigner distribution has been extensively used for speech processing. However, its use for image processing is relatively new. The proposed method can be used for robotics application, where a robot has to locate the objects in highly noisy scenario. The method can also be utilized for finding out the path for robot movement in a cluttered environment. The results indicate that the proposed method deals efficiently with high noise and segments out the objects from the scene.