{"id":7596,"date":"2024-11-01T07:14:32","date_gmt":"2024-11-01T07:14:32","guid":{"rendered":"https:\/\/www.mixtile.com\/?post_type=ht_kb&#038;p=7596"},"modified":"2024-11-06T02:57:36","modified_gmt":"2024-11-06T02:57:36","slug":"edge-ai-box-powered-by-mixtile-edge-2","status":"publish","type":"ht_kb","link":"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/","title":{"rendered":"\u30a8\u30c3\u30b8AI\u30dc\u30c3\u30af\u30b9 Powered by Mixtile Edge 2"},"content":{"rendered":"<div class=\"wp-block-jetpack-markdown\"><p><!-- # Edge AI Box Powered by Mixtile Edge 2 --><\/p>\n<p>Mixtile provides an <a href=\"https:\/\/github.com\/Buyuliang\/aiBox\">AI box<\/a> project that allows you perform object detection for the use cases below at a time:<\/p>\n<ul>\n<li>Detect fire\/smoke.<\/li>\n<li>Detect falldown.<\/li>\n<li>Count people.<\/li>\n<\/ul>\n<p>The detection results are categorized for each use case. In addition, we also provide a unified results for you to view the comprehensive situation.<\/p>\n<p>You can follow this tutorial to set up the Mixtile AI box project on Mixtile Edge 2 Kit (also known as Edge 2) and perform inference.<\/p>\n<h2>\u524d\u63d0\u6761\u4ef6<\/h2>\n<ol>\n<li>\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb <a href=\"https:\/\/downloads.mixtile.com\/edge2\/ubuntu_image\/image-release-raw-format-mixtile-edge2-ubuntu-22.04-desktop.img.zip\">Ubuntu 22.04 Desktop<\/a> on Edge 2 (see <a href=\"https:\/\/www.mixtile.com\/ja\/docs\/installing-an-operating-system-on-mixtile-edge2-kit\/\">Mixtile Edge 2\u30ad\u30c3\u30c8\u3078\u306e\u30aa\u30da\u30ec\u30fc\u30c6\u30a3\u30f3\u30b0\u30b7\u30b9\u30c6\u30e0\u306e\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb<\/a>).<\/li>\n<li>Connect Edge 2 to the Internet.<\/li>\n<\/ol>\n<h2>Setting up AI box<\/h2>\n<ol>\n<li>\n<p>\u4f9d\u5b58\u95a2\u4fc2\u3092\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3057\u307e\u3059\uff1a<\/p>\n<pre><code class=\"language-sh\">sudo apt update &amp;&amp; sudo apt install -y build-essential cmake libopencv-dev libjsoncpp-dev\n<\/code><\/pre>\n<\/li>\n<li>\n<p>Clone project repository:<\/p>\n<pre><code class=\"language-sh\">git clone https:\/\/github.com\/Buyuliang\/aiBox.git\n<\/code><\/pre>\n<\/li>\n<li>\n<p>Build the <code>aibox<\/code> executable file:<\/p>\n<pre><code class=\"language-sh\">cd aiBox\nbash build.sh\n<\/code><\/pre>\n<p>If <code>Build and installation completed successfully<\/code> is displayed, the <code>aibox<\/code> executable file is built to the <code>install<\/code> directory successfully:<\/p>\n<pre><code class=\"language-sh\">install\n\u251c\u2500\u2500 aibox\n\u251c\u2500\u2500 lib\n\u2502\u00a0\u00a0 \u251c\u2500\u2500 librga.so\n\u2502\u00a0\u00a0 \u2514\u2500\u2500 librknnrt.so\n\u2514\u2500\u2500 model\n    \u251c\u2500\u2500 coco_80_labels_list.txt\n    \u251c\u2500\u2500 falldet.rknn\n    \u251c\u2500\u2500 firesmoke.rknn\n    \u2514\u2500\u2500 perdet.rknn\n<\/code><\/pre>\n<\/li>\n<\/ol>\n<h2>Performing inference<\/h2>\n<p>Now that you have compiled the <code>aibox<\/code> executable file, you can run it as follows:<\/p>\n<pre><code class=\"language-sh\">cd install\n.\/aibox video-input # replace video-input with the actual video source.\n\n# Example:\n.\/aibox ..\/sources\/fire.mp4\n<\/code><\/pre>\n<h3>Input description<\/h3>\n<p><code>video-input<\/code>: video source to perform inference on. Supported values:<\/p>\n<ul>\n<li>Video file<\/li>\n<li>USB camera (e.g., <code>\/dev\/video1<\/code>)<\/li>\n<li>RTSP camera (e.g., <code>rtsp:\/\/camera-ip-address:554\/stream1<\/code>)<\/li>\n<\/ul>\n<h3>Output description<\/h3>\n<p>This command outputs PNG images and relevant JSON files to <code>install\/output<\/code>:<\/p>\n<pre><code class=\"language-bash\">install\/output\/\n\u251c\u2500\u2500 falldet # people falldown results\n\u251c\u2500\u2500 firesmokedet # fire and smoke results\n\u2502   \u251c\u2500\u2500 20241029111828.json # inference results in json\n\u2502   \u251c\u2500\u2500 20241029111828.png # inference results in png\n\u2502   \u251c\u2500\u2500 20241029111829.json\n\u2502   \u251c\u2500\u2500 20241029111829.png\n\u2502   \u251c\u2500\u2500 20241029111830.json\n\u2502   \u251c\u2500\u2500 20241029111830.png\n\u2502   \u251c\u2500\u2500 20241029111831.json\n\u2502   \u251c\u2500\u2500 20241029111831.png\n\u2502   \u251c\u2500\u2500 20241029111832.json\n\u2502   \u2514\u2500\u2500 20241029111832.png\n\u251c\u2500\u2500 perdet # people count results\n\u2514\u2500\u2500 result # unified results for falldown, fire and smoke, and people count\n    \u251c\u2500\u2500 20241029111828.json\n    \u251c\u2500\u2500 20241029111828.png\n    \u251c\u2500\u2500 20241029111829.json\n    \u251c\u2500\u2500 20241029111829.png\n    \u251c\u2500\u2500 20241029111830.json\n    \u251c\u2500\u2500 20241029111830.png\n    \u251c\u2500\u2500 20241029111831.json\n    \u251c\u2500\u2500 20241029111831.png\n    \u251c\u2500\u2500 20241029111832.json\n    \u2514\u2500\u2500 20241029111832.png\n<\/code><\/pre>\n<p>You can go to these directories to look at the output images and JSON files. For more information about the output, see <a href=\"#inference-examples\">Inference examples<\/a>.<\/p>\n<blockquote>\n<p>\u6ce8<\/p>\n<p>If your source is from a USB or RTSP camera, it keeps outputting files to the <code>output<\/code> folder until you stop the terminal.<\/p>\n<\/blockquote>\n<h2>Inference examples<\/h2>\n<blockquote>\n<p>\u6ce8\uff1a<\/p>\n<p>Commands below perform inference on video files. You can use other video sources, such as a USB camera videos, as you like.<\/p>\n<\/blockquote>\n<h3>Counting people<\/h3>\n<p>Run this command to try out the people count feature:<\/p>\n<pre><code class=\"language-sh\">.\/aibox ..\/sources\/people.mp4\n<\/code><\/pre>\n<p>If people appear in the pre-configured green area, results will be saved to <code>install\/output\/perdet<\/code>, including images with the count numbers and the corresponding JSON files.<\/p>\n<p><strong>Output image:<\/strong><\/p>\n<p><img src=\"https:\/\/i0.wp.com\/downloads.mixtile.com\/doc-images\/aibox\/count-people-results.png?w=1020&#038;ssl=1\" alt=\"\" data-recalc-dims=\"1\"><\/p>\n<blockquote>\n<p>\u6ce8\uff1a <code>Count: 3<\/code> indicates three people appear in the green area.<\/p>\n<\/blockquote>\n<p><strong>Snippet of an output JSON:<\/strong><\/p>\n<pre><code class=\"language-json\">[\n    {\n        &quot;height&quot;: 77.448562622070312,\n        &quot;id&quot;: 1,\n        &quot;width&quot;: 40.873950958251953,\n        &quot;x&quot;: 621.55810546875,\n        &quot;y&quot;: 363.69189453125\n    },\n    {\n        &quot;height&quot;: 88.120887756347656,\n        &quot;id&quot;: 2,\n        &quot;width&quot;: 46.946933746337891,\n        &quot;x&quot;: 763.70953369140625,\n        &quot;y&quot;: 310.00149536132812\n    },\n    {\n        &quot;height&quot;: 91.801826477050781,\n        &quot;id&quot;: 3,\n        &quot;width&quot;: 43.065662384033203,\n        &quot;x&quot;: 542.39923095703125,\n        &quot;y&quot;: 360.87911987304688\n    }\n]\n<\/code><\/pre>\n<h3>Detecting fire and smoke<\/h3>\n<p>Run this command to try out fire and smoke detection:<\/p>\n<pre><code class=\"language-sh\">.\/aibox ..\/sources\/fire.mp4\n<\/code><\/pre>\n<p>If smoke or fire is detected, results will be saved to <code>install\/output\/firesmokedet<\/code>, including images with fire or smoke, and the corresponding JSON files.<\/p>\n<p><strong>Output image:<\/strong><\/p>\n<p><img src=\"https:\/\/i0.wp.com\/downloads.mixtile.com\/doc-images\/aibox\/fire-smoke-results.png?w=1020&#038;ssl=1\" alt=\"\" data-recalc-dims=\"1\"><\/p>\n<p><strong>Output JSON:<\/strong><\/p>\n<pre><code class=\"language-json\">[\n    {\n        &quot;height&quot;: 150.0,\n        &quot;id&quot;: &quot;fire&quot;,\n        &quot;width&quot;: 211.0,\n        &quot;x&quot;: 46.0,\n        &quot;y&quot;: 219.0\n    },\n    {\n        &quot;height&quot;: 121.0,\n        &quot;id&quot;: &quot;smoke&quot;,\n        &quot;width&quot;: 226.0,\n        &quot;x&quot;: 320.0,\n        &quot;y&quot;: 220.0\n    }\n]\n<\/code><\/pre>\n<h3>Detecting falldown<\/h3>\n<p>Run this command to try out falldown detection:<\/p>\n<pre><code class=\"language-sh\">.\/aibox ..\/sources\/falldown.mp4\n<\/code><\/pre>\n<p>If someone falls, results will be saved to <code>install\/output\/falldet<\/code>, including the falldown images and the corresponding JSON files.<\/p>\n<p><strong>Output image:<\/strong><\/p>\n<p><img src=\"https:\/\/i0.wp.com\/downloads.mixtile.com\/doc-images\/aibox\/falldown-results.png?w=1020&#038;ssl=1\" alt=\"\" data-recalc-dims=\"1\"><\/p>\n<blockquote>\n<p>Note: The black rectangle with the number <code>0<\/code> indicates falldown is detected.<\/p>\n<\/blockquote>\n<p><strong>Output JSON:<\/strong><\/p>\n<pre><code class=\"language-json\">[\n    {\n        &quot;height&quot;: 229.0,\n        &quot;id&quot;: 0,\n        &quot;width&quot;: 440.0,\n        &quot;x&quot;: 13.0,\n        &quot;y&quot;: 293.0\n    }\n]\n<\/code><\/pre>\n<h3>Unified inference: count people and detect falldown<\/h3>\n<p>In the <a href=\"#detecting-falldown\">Detecting falldown<\/a> example above, the <code>falldown.mp4<\/code> video actually <strong>has people to count<\/strong> \u305d\u3057\u3066 <strong>people falldown<\/strong> at the same time. In this case, Mixtile AI box detects falldown and also counts people, and then not only outputs the results to the standalone <code>install\/output\/falldet<\/code> \u305d\u3057\u3066 <code>install\/output\/perdet<\/code> directories, but also provides unified results in <code>install\/output\/result<\/code> as follows:<\/p>\n<p><strong>Unified output image:<\/strong><\/p>\n<p><img src=\"https:\/\/i0.wp.com\/downloads.mixtile.com\/doc-images\/aibox\/falldown-and-count.png?w=1020&#038;ssl=1\" alt=\"\" data-recalc-dims=\"1\"><\/p>\n<p>This image contains results for both people count and falldown:<\/p>\n<ul>\n<li>The black rectangle with the number <code>0<\/code> indicates falldown is detected.<\/li>\n<li><code>Count: 1<\/code> indicates 1 person appears in the specified green area.<\/li>\n<\/ul>\n<p><strong>Unified output JSON:<\/strong><\/p>\n<pre><code class=\"language-json\">{\n    &quot;RegionCoun&quot; : 1,\n    &quot;fallDetections&quot; : \n    [\n        {\n            &quot;height&quot; : 244.0,\n            &quot;id&quot; : 0,\n            &quot;width&quot; : 627.0,\n            &quot;x&quot; : 197.0,\n            &quot;y&quot; : 256.0\n        }\n    ],\n    &quot;frameID&quot; : 246,\n    &quot;personDetections&quot; : \n    [\n        {\n            &quot;height&quot; : 295.62838745117188,\n            &quot;id&quot; : 1,\n            &quot;width&quot; : 524.926513671875,\n            &quot;x&quot; : 221.60183715820312,\n            &quot;y&quot; : 235.85356140136719\n        }\n    ]\n}\n<\/code><\/pre>\n<\/div>","protected":false},"excerpt":{"rendered":"","protected":false},"author":110,"comment_status":"open","ping_status":"closed","template":"","format":"standard","meta":{"spay_email":""},"ht-kb-category":[211],"ht-kb-tag":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v17.8 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Edge AI Box Powered by Mixtile Edge 2 | Mixtile<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/\" \/>\n<meta property=\"og:locale\" content=\"ja_JP\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Edge AI Box Powered by Mixtile Edge 2 | Mixtile\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/\" \/>\n<meta property=\"og:site_name\" content=\"Mixtile\" \/>\n<meta property=\"article:modified_time\" content=\"2024-11-06T02:57:36+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/downloads.mixtile.com\/doc-images\/aibox\/count-people-results.png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.mixtile.com\/ja\/#organization\",\"name\":\"Mixtile Limited\",\"url\":\"https:\/\/www.mixtile.com\/ja\/\",\"sameAs\":[],\"logo\":{\"@type\":\"ImageObject\",\"@id\":\"https:\/\/www.mixtile.com\/ja\/#logo\",\"inLanguage\":\"ja\",\"url\":\"https:\/\/dh19rycdk230a.cloudfront.net\/app\/uploads\/2022\/02\/logo.svg\",\"contentUrl\":\"https:\/\/dh19rycdk230a.cloudfront.net\/app\/uploads\/2022\/02\/logo.svg\",\"caption\":\"Mixtile Limited\"},\"image\":{\"@id\":\"https:\/\/www.mixtile.com\/ja\/#logo\"}},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.mixtile.com\/ja\/#website\",\"url\":\"https:\/\/www.mixtile.com\/ja\/\",\"name\":\"Mixtile\",\"description\":\"Hardware for IoT Solutions\",\"publisher\":{\"@id\":\"https:\/\/www.mixtile.com\/ja\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.mixtile.com\/ja\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"ja\"},{\"@type\":\"ImageObject\",\"@id\":\"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/#primaryimage\",\"inLanguage\":\"ja\",\"url\":\"https:\/\/downloads.mixtile.com\/doc-images\/aibox\/count-people-results.png\",\"contentUrl\":\"https:\/\/downloads.mixtile.com\/doc-images\/aibox\/count-people-results.png\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/#webpage\",\"url\":\"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/\",\"name\":\"Edge AI Box Powered by Mixtile Edge 2 | Mixtile\",\"isPartOf\":{\"@id\":\"https:\/\/www.mixtile.com\/ja\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/#primaryimage\"},\"datePublished\":\"2024-11-01T07:14:32+00:00\",\"dateModified\":\"2024-11-06T02:57:36+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/#breadcrumb\"},\"inLanguage\":\"ja\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.mixtile.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Edge AI Box Powered by Mixtile Edge 2\"}]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Edge AI Box Powered by Mixtile Edge 2 | Mixtile","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/","og_locale":"ja_JP","og_type":"article","og_title":"Edge AI Box Powered by Mixtile Edge 2 | Mixtile","og_url":"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/","og_site_name":"Mixtile","article_modified_time":"2024-11-06T02:57:36+00:00","og_image":[{"url":"https:\/\/downloads.mixtile.com\/doc-images\/aibox\/count-people-results.png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Organization","@id":"https:\/\/www.mixtile.com\/ja\/#organization","name":"Mixtile Limited","url":"https:\/\/www.mixtile.com\/ja\/","sameAs":[],"logo":{"@type":"ImageObject","@id":"https:\/\/www.mixtile.com\/ja\/#logo","inLanguage":"ja","url":"https:\/\/dh19rycdk230a.cloudfront.net\/app\/uploads\/2022\/02\/logo.svg","contentUrl":"https:\/\/dh19rycdk230a.cloudfront.net\/app\/uploads\/2022\/02\/logo.svg","caption":"Mixtile Limited"},"image":{"@id":"https:\/\/www.mixtile.com\/ja\/#logo"}},{"@type":"WebSite","@id":"https:\/\/www.mixtile.com\/ja\/#website","url":"https:\/\/www.mixtile.com\/ja\/","name":"Mixtile","description":"Hardware for IoT Solutions","publisher":{"@id":"https:\/\/www.mixtile.com\/ja\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.mixtile.com\/ja\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"ja"},{"@type":"ImageObject","@id":"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/#primaryimage","inLanguage":"ja","url":"https:\/\/downloads.mixtile.com\/doc-images\/aibox\/count-people-results.png","contentUrl":"https:\/\/downloads.mixtile.com\/doc-images\/aibox\/count-people-results.png"},{"@type":"WebPage","@id":"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/#webpage","url":"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/","name":"Edge AI Box Powered by Mixtile Edge 2 | Mixtile","isPartOf":{"@id":"https:\/\/www.mixtile.com\/ja\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/#primaryimage"},"datePublished":"2024-11-01T07:14:32+00:00","dateModified":"2024-11-06T02:57:36+00:00","breadcrumb":{"@id":"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/#breadcrumb"},"inLanguage":"ja","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.mixtile.com\/ja\/docs\/edge-ai-box-powered-by-mixtile-edge-2\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.mixtile.com\/"},{"@type":"ListItem","position":2,"name":"Edge AI Box Powered by Mixtile Edge 2"}]}]}},"_links":{"self":[{"href":"https:\/\/www.mixtile.com\/ja\/wp-json\/wp\/v2\/ht-kb\/7596"}],"collection":[{"href":"https:\/\/www.mixtile.com\/ja\/wp-json\/wp\/v2\/ht-kb"}],"about":[{"href":"https:\/\/www.mixtile.com\/ja\/wp-json\/wp\/v2\/types\/ht_kb"}],"author":[{"embeddable":true,"href":"https:\/\/www.mixtile.com\/ja\/wp-json\/wp\/v2\/users\/110"}],"replies":[{"embeddable":true,"href":"https:\/\/www.mixtile.com\/ja\/wp-json\/wp\/v2\/comments?post=7596"}],"version-history":[{"count":3,"href":"https:\/\/www.mixtile.com\/ja\/wp-json\/wp\/v2\/ht-kb\/7596\/revisions"}],"predecessor-version":[{"id":7608,"href":"https:\/\/www.mixtile.com\/ja\/wp-json\/wp\/v2\/ht-kb\/7596\/revisions\/7608"}],"wp:attachment":[{"href":"https:\/\/www.mixtile.com\/ja\/wp-json\/wp\/v2\/media?parent=7596"}],"wp:term":[{"taxonomy":"ht_kb_category","embeddable":true,"href":"https:\/\/www.mixtile.com\/ja\/wp-json\/wp\/v2\/ht-kb-category?post=7596"},{"taxonomy":"ht_kb_tag","embeddable":true,"href":"https:\/\/www.mixtile.com\/ja\/wp-json\/wp\/v2\/ht-kb-tag?post=7596"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}