RESEARCH

Image & Vision

Investigates Image data fusion techniques that combine image and track data from multiple sensors to achieve improved accuracies and more specific inferences than could be achieved by the use of a single sensor alone. Our aim is to explore the state-of-the-art image processing algorithms for achieving effective data fusion as in:

Vision-based Robot Navigation

Admin    2021-04-08    👁️ 207

1. Gradient-based Feature Extraction        

    Feature Extraction technique is important to effective presentation of image information and accuracy of recoginition. The features are extracted from gradient vectors that are not much affected by illumination. Following demostration is the implementation of  the feature extraction.

2. Scale Invariant Feature Transformation   

   The idea here is to detect features that are invariant to rotation and translation so that the robot is known whether the scene is seen before or not, etc. These features are detected by means of cascade filtering, and a continuous function of scale known as scale space.

3. Retinex Algorithm       

   The Retinex Image Enhancement Algorithm is an automatic image enhancement method that enhances a digital image in terms of dynamic range compression, color independence from the spectral distribution of the scene illuminant, and color/lightness rendition. The digital image enhanced by the Retinex Image Enhancement Algorithm is much closer to the scene perceived by the human visual system, under all kinds and levels of lighting variations, that the digital image enhanced by any other method. This algorithm enables robot to detect keypoints under the insufficiency of light.