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

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) CAM ±â¹ÝÀÇ °èÃþÀû ¹× ¼öÆòÀû ºÐ·ù ¸ðµ¨À» °áÇÕÇÑ ¿îÀüÀÚ ºÎÁÖÀÇ °ËÃâ ¹× Æ¯Â¡ ¿µ¿ª Áö¿ªÈ­
¿µ¹®Á¦¸ñ(English Title) Distracted Driver Detection and Characteristic Area Localization by Combining CAM-Based Hierarchical and Horizontal Classification Models
ÀúÀÚ(Author) °í¼ö¿¬   ÃÖ¿µ¿ì   Sooyeon Go   Yeongwoo Choi  
¿ø¹®¼ö·Ïó(Citation) VOL 10 NO. 11 PP. 0439 ~ 0448 (2021. 11)
Çѱ۳»¿ë
(Korean Abstract)
±³Åë»ç°í ¿øÀÎ Áß °¡Àå Å« ºñÀ²À» Â÷ÁöÇÏ´Â °ÍÀÌ ¿îÀüÀÚÀÇ ºÎÁÖÀǷμ­ À̸¦ °ËÃâÇÏ´Â ¿¬±¸°¡ ²ÙÁØÈ÷ ÁøÇàµÇ°í ÀÖ´Ù. º» ³í¹®Àº ºÎÁÖÀÇÇÑ ¿îÀüÀÚ¸¦ Á¤È®È÷ °ËÃâÇÏ°í, °ËÃâµÈ ¿îÀüÀÚÀÇ ¸ð½À¿¡¼­ °¡Àå Ư¡ÀûÀÎ ¿µ¿ªÀ» ¼±Á¤(Localize)ÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÏ´Â ¹æ¹ýÀº ¿îÀüÀÚÀÇ ºÎÁÖÀǸ¦ °ËÃâÇϱâ À§Çؼ­ CAM(Class Activation Map) ±â¹ÝÀÇ Àüü Ŭ·¡½º¸¦ ºÐ·ùÇÏ´Â CNN ¸ðµ¨°ú ÀÌ ¸ðµ¨¿¡¼­ È¥µ¿Çϰųª °øÅëµÈ Ư¡ ¿µ¿ªÀ» °®´Â Ŭ·¡½ºµé¿¡ ´ëÇÑ »ó¼¼ ºÐ·ù°¡ °¡´ÉÇÑ ³× °³ÀÇ ¼­ºê Ŭ·¡½º CNN ¸ðµ¨À» °èÃþÀûÀ¸·Î ±¸¼ºÇÑ´Ù. °¢ ¸ðµ¨¿¡¼­ Ãâ·ÂÇÑ ºÐ·ù °á°ú´Â CNN Ư¡¸Êµé°úÀÇ ¸ÅĪ Á¤µµ¸¦ Ç¥ÇöÇÏ´Â »õ·Î¿î Ư¡À¸·Î °£ÁÖÇؼ­ ¼öÆòÀûÀ¸·Î °áÇÕÇÏ°í ÇнÀÇÏ¿© ºÐ·ùÀÇ Á¤È®¼ºÀ» ³ô¿´´Ù. ¶ÇÇÑ Àüü ¹× »ó¼¼ ºÐ·ù ¸ðµ¨ÀÇ ºÐ·ù °á°ú¸¦ ¹Ý¿µÇÑ È÷Æ®¸Ê °á°ú¸¦ °áÇÕÇÏ¿© À̹ÌÁöÀÇ Æ¯Â¡ÀûÀÎ ÁÖÀÇ ¿µ¿ªÀ» ã¾Æ³½´Ù. Á¦¾ÈÇÑ ¹æ¹ýÀº State Farm µ¥ÀÌÅÍ ¼ÂÀ» ÀÌ¿ëÇÑ ½ÇÇè¿¡¼­ 95.14%ÀÇ Á¤È®µµ¸¦ ¾ò¾úÀ¸¸ç, ÀÌ´Â ±âÁ¸¿¡ µ¿ÀÏÇÑ µ¥ÀÌÅÍ ¼ÂÀ» ÀÌ¿ëÇÑ °á°ú Áß °¡Àå ³ôÀº Á¤È®µµÀÎ 92.2%º¸´Ù 2.94% Çâ»óµÈ ¿ì¼öÇÑ °á°úÀÌ´Ù. ¶ÇÇÑ Àüü ¸ðµ¨¸¸À» ÀÌ¿ëÇßÀ» ¶§ ã¾ÆÁø ÁÖÀÇ ¿µ¿ªº¸´Ù ÈξÀ ÀÇ¹Ì ÀÖ°í Á¤È®ÇÑ ÁÖÀÇ ¿µ¿ªÀÌ Ã£¾ÆÁüÀ» ½ÇÇèÀ¸·Î È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Driver negligence accounts for the largest proportion of the causes of traffic accidents, and research to detect them is continuously being conducted. This paper proposes a method to accurately detect a distracted driver and localize the most characteristic parts of the driver. The proposed method hierarchically constructs a CNN basic model that classifies 10 classes based on CAM in order to detect driver distraction and 4 subclass models for detailed classification of classes having a confusing or common feature area in this model. The classification result output from each model can be considered as a new feature indicating the degree of matching with the CNN feature maps, and the accuracy of classification is improved by horizontally combining and learning them. In addition, by combining the heat map results reflecting the classification results of the basic and detailed classification models, the characteristic areas of attention in the image are found. The proposed method obtained an accuracy of 95.14% in an experiment using the State Farm data set, which is 2.94% higher than the 92.2%, which is the highest accuracy among the results using this data set. Also, it was confirmed by the experiment that more meaningful and accurate attention areas were found than the results of the attention area found when only the basic model was used.
Å°¿öµå(Keyword) ¿îÀüÀÚ ºÎÁÖÀÇ °ËÃâ   ÇÕ¼º°ö½Å°æ¸Á   CAM(Class Activation Map)   ÁÖÀÇ¿µ¿ª Áö¿ªÈ­   Distracted Driver Detection   Convolutional Neural Networks   Class Activation Maps   Attention Area Localization  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå