• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

Ȩ Ȩ > ¿¬±¸¹®Çå >

Current Result Document : 2 / 42 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) Ŭ·¡½º ºÒ±ÕÇüÀ» °®´Â ȯ°æ¿¡¼­ÀÇ ½Ç½Ã°£ Àǹ̷ÐÀû ¿µ»óºÐÇÒ ¾Ë°í¸®Áò ¼º´É Çâ»ó¿¡ °üÇÑ ¿¬±¸
¿µ¹®Á¦¸ñ(English Title) A Study of Real-time Semantic Segmentation Performance Improvement in Class Imbalanced Datasets
ÀúÀÚ(Author) ±è´ë¿µ   ¼­½Â¿ì   Daeyoung Kim   Seung-Woo Seo  
¿ø¹®¼ö·Ïó(Citation) VOL 45 NO. 01 PP. 2193 ~ 2195 (2022. 06)
Çѱ۳»¿ë
(Korean Abstract)
¿µ¹®³»¿ë
(English Abstract)
Semantic segmentation in autonomous driving for unstructured environments is challenging due to the presence of class imbalance. To overcome these issues, we propose a deep learning framework for semantic segmentation based on BiSeNetV2. The evaluation of the framework is carried out on TAS500 off-road driving datasets. The results show that ours proposed method achieves high accuracy.
Å°¿öµå(Keyword)
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå