ãã£ãã㨠æµè¡ãã®ãã£ã¼ãã©ã¼ãã³ã°ã使ã£ã¦ãç»åã®ç©ä½æ¤åºãè¡ãã¾ããã ä»åã¯ãYOLOv2ã¨ããã¢ã«ã´ãªãºã ã使ã£ã¦ç©ä½æ¤åºãè¡ãªã£ã¦ãã¾ãã YOLO(You Only Look Once)ã¨ã¯ ç³ã¿è¾¼ã¿ãã¥ã¼ã©ã«ãããã¯ã¼ã¯(CNN:Convolutional Neural Network)ãç¨ããç©ä½æ¤åºã¢ã«ã´ãªãºã ã§ããç¾æç¹ã§ã¯v1ã¨v2ãåå¨ãã¾ãã YOLO(YOLOv1) è«æã¯ãã¡ã(2015å¹´)ã å¾æ¥ã¨ã¯ç°ãªããç»åããã¦ã³ãã£ã³ã°ããã¯ã¹ã§åå²ãã¦ã¯ã©ã¹åé¡ãè¡ãªã£ã¦ããã we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. çµæã¨ãã¦ã45FPSã®å¦çé度ãå®ç¾ã
{{#tags}}- {{label}}
{{/tags}}