Semantic Segmentation Using Fully Convolutional Network for An Autonomous Vehicle

Rohan Dandekar; Ashu Prasad; Sagar Devanpalli

Abstract

Numerous individuals inside the profound learning and PC vision networks comprehend what picture arrangement is. We would like to inform about our model that, what single object or scene is present within the image. Semantic segmentation is the most informative segmentation, where we wish to classify each and every pixel within the image. Deep networks have proved to be encoded with highlevel feature like semantic means which can deliver superior performance in salient object detection. Our key insight is to create “Semantic Segmentation using Fully Convolutional Network for an Autonomous Vehicle” where semantic segmentation is one of the key problems within the field of computer vision. Watching the larger picture, semantic segmentation is among one of the high-level tasks that paves the way towards complete scene understanding. The significance of scene understanding as a center PC vision issue is featured by the established truth that an expanding number of uses feed from deriving information from symbolism. A number of those applications include self-driving vehicles, human-computer interaction, geo-sensing etc. Self-driving vehicles require a profound comprehension of their environmental factors. To support this, fully convolutional networks classifies the road, pedestrians, cars, and sidewalks at pixel-level accuracy.During this project, we develop a neural network and optimize it to perform semantic segmentation using fully convolutional network models.

Abstract

Keywords