2018-19

Permanent URI for this collection

http://172.16.1.132:4000/handle/123456789/10414

Browse

Browsing 2018-19 by Subject "1NH15EC004"

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    “Semantic Segmentation for Automated Driving system using MATLAB”
    (2019-06-17T10:00:26Z) MANIKANTA K; AKASH MALAPPA MANTUR; JAYANTH M K
    The task of Semantic Segmentation is to annotate every pixel of an image with an object class. These classes could be “pedestrians, vehicles, buildings, vegetation, sky, void etc” in a self-driving environment. For example, semantic segmentation helps SDCs (Self Driving Cars) discover the driveable areas on an image. The semantic segmentation is done with the help of deep learning applications and frame works. Deep learning is a fast-growing machine learning approach to perceive and understand large amounts of data. It has considerably improved semantic image segmentation. However, its high accuracy is traded against larger computational costs which makes it unsuitable for embedded devices in self-driving cars. We propose a novel deep network architecture for image segmentation that keeps the high accuracy while being efficient enough for embedded devices. The architecture consists of ELU activation functions, a Squeeze Net-like encoder, followed by parallel dilated convolutions, and a decoder with Sharp Mask-like refinement modules. On the Cityscapes dataset, the new network achieves higher segmentation accuracy than other networks that are tailored to embedded devices. Simultaneously the frame-rate is still sufficiently high for the deployment in autonomous vehicles. The importance of implementing this technology in the driving system is to avoid the road accidents and build the automated driving system.