| ³í¹®¸í |
±¸±Û ½ºÆ®¸®Æ® ºä µ¥ÀÌÅÍ¿Í ÀΰøÁö´ÉÀ» Ȱ¿ëÇÑ À§Ä¡±â¹Ý °¡·Î°ø°£ º¸ÇàÀÚ µ¥ÀÌÅÍ ¼öÁý ¹æ¹ý °³¹ß / Developing Geo-coded Street-level Pedestrian Volume Data Using Google Street View Data and Artificial Intelligence Models |
| ÀúÀÚ¸í |
±è¿µ¿ì(Kim, Youngwoo) ; Ȳ¿ëÇÏ(Hwang, Yongha) ; Á¤Àº¼®(Jeong, Eunseok) ; °¹üÁØ(Kang, Bumjoon) |
| ¼ö·Ï»çÇ× |
´ëÇѰÇÃàÇÐȸ³í¹®Áý, Vol.39 No.9 (2023-09) |
| ÆäÀÌÁö |
½ÃÀÛÆäÀÌÁö(57) ÃÑÆäÀÌÁö(12) |
| ÁÖÁ¦¾î |
°¡·ÎȰµ¿; °¡·Îµ¥ÀÌÅÍ; º¸Çà·®; À̹ÌÁöÆÇº°; ÀΰøÁö´É ; Street Activities; Street Data; Pedestrian Volume; Image Detection; Artificial Intelligence |
| ¿ä¾à1 |
º¸Çà·® µ¥ÀÌÅÍ´Â °ÇÃà°èȹ, µµ½Ã¼³°è µî ´Ù¾çÇÑ ¹æ¸é¿¡¼ Ȱ¿ëµµ°¡ ³ô¾Æ Á¤ºÎ±â°ü¿¡¼ ȤÀº »ó¾÷Àû ¸ñÀûÀ¸·Î ÀÎÇÑ Á¶»ç±â°ü¿¡¼ ÇØ´ç µ¥ÀÌÅ͸¦ ÃëµæÇϰí ÀÖ´Ù. ÇÏÁö¸¸ ÀüÅëÀûÀÎ º¸Çà·® ÃøÁ¤ ¹æ¹ýÀº ¸ñÃø ¹× ¼ö±â±âÀÔ ¹æ½ÄÀ¸·Î ÀڷḦ ±¸ÃàÇÏ´Â ¹Ù ½Ã°£ ¹× ³ëµ¿ ºñ¿ëÀÌ ³ôÀ» ¼ö¹Û¿¡ ¾ø´Ù. ¶ÇÇÑ Æ¯Á¤ ÁöÁ¡ÀÇ º¸Çà·®Àº ¾òÀ» ¼ö À־ ¿¬¼ÓµÈ °ø°£ÀÇ º¸Çà·®À» ÃøÁ¤Çϱ⿡´Â ¾î·Á¿òÀÌ ÀÖ´Ù. º» ¿¬±¸¿¡¼´Â ÀÌó·³ ÃøÁ¤ÀÌ ºÒ°¡´ÉÇÑ Áö¿ªÀÇ º¸Çà·®À» ¿¹ÃøÇϱâ À§ÇÏ¿© GSV(Google Street View) µ¥ÀÌÅ͸¦ Ȱ¿ëÇÒ ¼ö ÀÖ´ÂÁö¸¦ °ËÁõÇϰíÀÚ ÇÏ¿´´Ù. ¿¬±¸¹æ¹ýÀº °´Ã¼Å½Áö ±â¼úÀ» Ȱ¿ëÇÏ¿© GSV¿¡¼ »ç¶÷À» ÆÇº°Çϰí, ±× È®·ü°ú °ø°ø¿¡¼ ÃøÁ¤ÇÑ º¸Çà·® Á¶»ç µ¥ÀÌÅ͸¦ »óÈ£ ºñ±³ÇÑ´Ù. ºÐ¼® ÀÚ·á´Â ´º¿å½Ã¿¡¼ Á¦°øÇÏ´Â µ¥ÀÌÅÍ´Â 114°³¼Ò ÁöÁ¡¿¡ °üÇÑ º¸Çà·® µ¥ÀÌÅ͸¦ ÀÌ¿ëÇÑ´Ù. ÁöÁ¡º° À§µµ, °æµµ Á¤º¸ ¹× ÃøÁ¤ ½Ã°£°ú º¸Çà·® Á¤º¸°¡ Æ÷ÇԵǾî ÀÖ´Ù. À§µµ °æµµ Á¤º¸¸¦ ÀÌ¿ëÇÏ¿© ÁöÁ¡º° GSV ÀڷḦ ¼öÁý, ÇØ´ç ÁöÁ¡ÀÇ º¸ÇàÀÚ ¼ö¸¦ °´Ã¼Å½Áö ±â¼úÀ» Åä´ë·Î ÆÇº°ÇÏ¿´´Ù. º» ¿¬±¸¿¡¼ ºÐ¼®ÇÏ´Â µÎ µ¥ÀÌÅÍ´Â È®·üÇÕ°è ¹æ½Ä°ú È®·üºóµµ ºÐ¼®À» ÅëÇØ ¿¹Ãø·ÂÀ» È®ÀÎÇϰí, ¹Î°¨µµ ºÐ¼®À» ÅëÇØ ¿¹Ãø·ÂÀ» ³ôÀÌ´Â °ÍÀ» ÁøÇàÇÑ´Ù. º» ¹æ¹ý·ÐÀº »ç¶÷ÀÌ °³ÀÔÇÏÁö ¾Ê´Â º¸Çà·® ¿¹Ãø±â¹ýÀ̶ó´Â Á¡¿¡¼ ¿øÇÏ´Â ÁöÁ¡ÀÇ º¸Çà·® ¿¹Ãø°ªÀ» ½±°í ºü¸£°Ô µµÃâÇÒ ¼ö ÀÖ´Ù´Â Á¡¿¡¼ º» ¿¬±¸ÀÇ ÀÇÀǰ¡ ÀÖ´Ù. |
| ¿ä¾à2 |
Pedestrian count data serves various purposes within architectural, urban planning, and related fields. Typically, this data is collected by government agencies and commercial survey companies. However, conventional methods of recording pedestrian data demand significant time and effort. Consequently, data availability is restricted to specific timeframes and limited locations. In response to this, we conducted feasibility tests for an object-based pedestrian detection procedure. Google Street View data was used to capture geocoded pedestrian counts at street levels in New York City, the U.S. A validation study was performed against historical pedestrian count data recorded officially in the city at 114 different locations. The results indicated a high agreement rate of over 0.8, suggesting that street-level image data could effectively and economically replace conventional pedestrian counting methods. |