Publikasi Penelitian

Permanent URI for this collection

Now showing 1 - 1 of 1

LICODS: A CNN BASED, LIGHTWEIGHT RGB-D SEMANTIC SEGMENTATION FOR OUTDOOR SCENES
(IJICIC Editorial Office, 2019-10) Ali Suryaperdana Agoes; Zhencheng Hu; Nobutomo Matsunaga
One way to visually understand the scenes is through per-pixel semantic segmentation. Recently, this field has undergone heavy development following the recent success of feature learning method based on the Convolutional Neural Network (CNN). Encouraged by this observation, we present Lightweight Color Depth Semantic Segmentation (LICODS), a small numbered parameter model based on the CNN for RGB-D image semantic segmentation. Additional input modality besides the color information to enhance per-pixel class prediction accuracy is employed. On the other side, our model parameter number remains low, although dual branches exist along our model’s network. The model performs better compared with the recently published RGB-D semantic segmentation models in terms of accuracy and processing time, despite of its small parameter number.