{"author_url":"https://blog.hatena.ne.jp/weed_7777/","provider_name":"Hatena Blog","type":"rich","version":"1.0","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fblog.feel-physics.jp%2Fentry%2F2015%2F08%2F10%2F000000\" title=\"\u3010\u65e5\u672c\u8a9e\u8a33\u30112 Background Modelling: An Improved Adaptive Background Mixture Model for Real- time Tracking with Shadow Detection - Feel Physics | Blog\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","blog_url":"https://blog.feel-physics.jp/","published":"2015-08-10 00:00:00","blog_title":"Feel Physics | Blog","description":"2 Background Modelling 2 \u80cc\u666f\u30e2\u30c7\u30eb In this section, we discuss the work of Grimson and Stauffer [2,3] and its shortcomings. \u3053\u306e\u7bc0\u3067\u306f\u3001\u30b0\u30ea\u30e0\u30bd\u30f3\u3068\u30b9\u30bf\u30a6\u30d5\u30a1\u30fc\u306e\u4ed5\u4e8b\u3068\u305d\u306e\u6b20\u70b9\u306b\u3064\u3044\u3066\u8b70\u8ad6\u3059\u308b\u3002 The authors introduces a method to model each background pixel by a mixture of K Gaussian distributions (K is a small number from 3 to 5). \u3053\u306e\u8457\u8005\u305f\u2026","categories":["Development diary"],"provider_url":"https://hatena.blog","url":"https://blog.feel-physics.jp/entry/2015/08/10/000000","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/w/weed_7777/20150810/20150810112848.png","title":"\u3010\u65e5\u672c\u8a9e\u8a33\u30112 Background Modelling: An Improved Adaptive Background Mixture Model for Real- time Tracking with Shadow Detection","height":"190","author_name":"weed_7777","width":"100%"}