Instance segmentation on real time object detection using mask R-CNN

Abstract

In the ever-advancing field of computer vision, image processing plays a prominent role. We can extend the applications of Image processing into solving real-world problems like substantially decreasing Human interaction over the art of driving. In the process of achieving this task, we face several challenges like Segmentation and Detection of objects. The proposed thesis overcomes the challenges effectively by introducing Instance segmentation and Binary masks along with Keras and Tensorflow. Instance segmentation is used to delineate and detect every unique object of interest according to their pixel characteristics in an image. Mask RCNN is the superior model over the existing CNN models and yields accurate detection of objects more efficiently. Unlike conventional Neural Networks which employs selective search algorithm to identify object of interest, Mask RCNN employs Regional Proposal Networks(RPN) to identify object of interest. For better results Image pre-processing techniques and morphological transformations are employed to reduce the noise and increase pixel clarity.