{"id":2526,"date":"2021-12-21T09:00:30","date_gmt":"2021-12-21T01:00:30","guid":{"rendered":"https:\/\/blog.ailia.ai\/uncategorized\/mobileobjectlocalizer-object-detection-model-that-can-detect-arbitrary-objects\/"},"modified":"2025-05-20T21:13:32","modified_gmt":"2025-05-20T13:13:32","slug":"mobileobjectlocalizer-object-detection-model-that-can-detect-arbitrary-objects","status":"publish","type":"post","link":"https:\/\/blog.ailia.ai\/en\/tips-en\/mobileobjectlocalizer-object-detection-model-that-can-detect-arbitrary-objects\/","title":{"rendered":"MobileObjectLocalizer : Class-agnostic Mobile Object Detector"},"content":{"rendered":"\n<h3 class=\"wp-block-heading\" id=\"68bc\"><strong>Overview<\/strong><\/h3>\n\n\n\n<p id=\"d82b\"><em>MobileObjectLocalizer<\/em>\u00a0is a general-purpose object detection model developed by Google that can be used for any type of object. Unlike models such as\u00a0<a href=\"https:\/\/medium.com\/axinc-ai\/yolox-object-detection-model-exceeding-yolov5-d6cea6d3c4bc\">YOLO<\/a>\u00a0which classifies objects among the 80 classes of COCO,\u00a0<em>MobileObjectLocalizer<\/em>\u00a0does not assign any category but it can detect any object.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"640\" height=\"426\" src=\"https:\/\/blog.ailia.ai\/wp-content\/uploads\/image-53.png\" alt=\"\" class=\"wp-image-387\"\/><figcaption class=\"wp-element-caption\">Source:\u00a0<a href=\"https:\/\/pixabay.com\/photos\/hot-air-balloons-sky-sunrise-dawn-4561263\/\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/pixabay.com\/photos\/hot-air-balloons-sky-sunrise-dawn-4561263\/<\/a><\/figcaption><\/figure>\n\n\n\n<p><a href=\"https:\/\/tfhub.dev\/google\/object_detection\/mobile_object_localizer_v1\/1?source=post_page-----595b54cfab26--------------------------------\" target=\"_blank\" rel=\"noreferrer noopener\"><\/a><a href=\"https:\/\/tfhub.dev\/google\/object_detection\/mobile_object_localizer_v1\/1\" target=\"_blank\" rel=\"noreferrer noopener\">TensorFlow Hub<\/a><\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"0637\"><strong>Architecture<\/strong><\/h3>\n\n\n\n<p id=\"1b92\"><em>MobileObjectLocalizer&nbsp;<\/em>uses&nbsp;<em>MobileNetV2&nbsp;<\/em>and&nbsp;<em>SSD-Lite<\/em>. The input resolution is 192&#215;192, and it outputs up to 100 bounding boxes.<\/p>\n\n\n\n<p id=\"30df\">Although the accuracy is not that high, it can detect the bounding box of any object without learning. It can be used for various applications, such as creating a 1000-class discriminator by adding&nbsp;<em>ResNet50<\/em>&nbsp;in the later stage, or using it for auto-focus by detecting the bounding box with the highest confidence value on the screen.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"fe95\"><strong>Usage<\/strong><\/h3>\n\n\n\n<p id=\"16b7\">You can use\u00a0<em>MobileObjectLocalizer\u00a0<\/em>with ailia SDK using the following command.<\/p>\n\n\n\n<p><code>$ python3 mobile_object_localizer.py -v 0<\/code><\/p>\n\n\n\n<p><a href=\"https:\/\/github.com\/axinc-ai\/ailia-models\/tree\/master\/object_detection\/mobile_object_localizer?source=post_page-----595b54cfab26--------------------------------\" target=\"_blank\" rel=\"noreferrer noopener\"><\/a><a href=\"https:\/\/github.com\/axinc-ai\/ailia-models\/tree\/master\/object_detection\/mobile_object_localizer\" target=\"_blank\" rel=\"noreferrer noopener\">ailia-models\/object_detection\/mobile_object_localizer<\/a><\/p>\n\n\n\n<p id=\"e25c\">Here is an example output.<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"ailia MODELS : MobileObjectLocalizer (r2)\" width=\"500\" height=\"281\" src=\"https:\/\/www.youtube.com\/embed\/U9Z2eJaT_Go?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<p id=\"0973\"><a href=\"https:\/\/axinc.jp\/en\/\" rel=\"noreferrer noopener\" target=\"_blank\">ax Inc.<\/a>&nbsp;has developed&nbsp;<a href=\"https:\/\/ailia.jp\/en\/\" rel=\"noreferrer noopener\" target=\"_blank\">ailia SDK<\/a>, which enables cross-platform, GPU-based rapid inference.<\/p>\n\n\n\n<p id=\"0973\">ax Inc. provides a wide range of services from consulting and model creation, to the development of AI-based applications and SDKs. Feel free to&nbsp;<a href=\"https:\/\/axinc.jp\/en\/\" rel=\"noreferrer noopener\" target=\"_blank\">contact us<\/a>&nbsp;for any inquiry.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Overview MobileObjectLocalizer\u00a0is a general-purpose object detection model developed by Google that can be used for any type of object. Unlike models such as\u00a0YOLO\u00a0which classifies objects among the 80 classes of COCO,\u00a0MobileObjectLocalizer\u00a0does not assign any category but it can detect any object. TensorFlow Hub Architecture MobileObjectLocalizer&nbsp;uses&nbsp;MobileNetV2&nbsp;and&nbsp;SSD-Lite. The input resolution is 192&#215;192, and it outputs up to 100 bounding boxes. Although the accuracy is not that high, it can detect the bounding box of any object without learning. It can be used for various applications, such as creating a 1000-class discriminator by adding&nbsp;ResNet50&nbsp;in the later stage, or using it for auto-focus by detecting the bounding box with the highest confidence value on [&hellip;]<\/p>\n","protected":false},"author":5,"featured_media":2442,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[255],"tags":[266],"class_list":["post-2526","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tips-en","tag-ailiamodels-en"],"acf":[],"_links":{"self":[{"href":"https:\/\/blog.ailia.ai\/en\/wp-json\/wp\/v2\/posts\/2526","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.ailia.ai\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.ailia.ai\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.ailia.ai\/en\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.ailia.ai\/en\/wp-json\/wp\/v2\/comments?post=2526"}],"version-history":[{"count":1,"href":"https:\/\/blog.ailia.ai\/en\/wp-json\/wp\/v2\/posts\/2526\/revisions"}],"predecessor-version":[{"id":2528,"href":"https:\/\/blog.ailia.ai\/en\/wp-json\/wp\/v2\/posts\/2526\/revisions\/2528"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blog.ailia.ai\/en\/wp-json\/wp\/v2\/media\/2442"}],"wp:attachment":[{"href":"https:\/\/blog.ailia.ai\/en\/wp-json\/wp\/v2\/media?parent=2526"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.ailia.ai\/en\/wp-json\/wp\/v2\/categories?post=2526"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.ailia.ai\/en\/wp-json\/wp\/v2\/tags?post=2526"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}