シーン中の位置と共起を考慮した Semantic Segmentation に関する研究

島崎 謙; 長尾 智晴

doi:10.11371/aiieej.42.0_42

Proceedings of the 42nd Annual Conference of the Institute of Image Electronics Engineers of Japan 2014

Session ID : S7-4

DOI https://doi.org/10.11371/aiieej.42.0_42

Conference information

Host: The Institute of Image Electronics Engineers of Japan

Co-host: Global Information and Telecommunication Institute, Waseda University

Name : Proceedings of the 42nd Annual Conference of the Institute of Image Electronics Engineers of Japan 2014

Number : 42

Location : [in Japanese]

Date : June 29, 2014 - June 30, 2014

A Research of Semantic Segmentation Considering Location and Co-occurrence of Object in Outdoor Scene

*Ken SHIMAZAKI, Tomoharu NAGAO

Author information

Keywords: Semantic Segmentation, Scene classification, Generic object recognition

CONFERENCE PROCEEDINGS RESTRICTED ACCESS

Details

Abstract

This paper presents a method of semantic segmentation considering location and co-occurrence in natural outdoor scene. Before recognizing objects in image, we classify image in terms of scene using Support Vector Machine (SVM), and recognize objects using Semantic Texton Forests (STF). In addition, we consider the location and co-occurrence of object in scene. Experimental results show that our proposed system is effective in several categories.

Corresponding author

Register with J-STAGE for free!