{"id":38786,"date":"2024-11-02T00:57:05","date_gmt":"2024-11-02T00:57:05","guid":{"rendered":"http:\/\/atmokpo.com\/w\/?p=38786"},"modified":"2024-11-26T06:43:20","modified_gmt":"2024-11-26T06:43:20","slug":"opencv-%ea%b0%95%ec%a2%8c-%ea%b0%84%eb%8b%a8%ed%95%9c-mask-r-cnn-%eb%aa%a8%eb%8d%b8-%ec%82%ac%ec%9a%a9%eb%b2%95","status":"publish","type":"post","link":"https:\/\/atmokpo.com\/w\/38786\/","title":{"rendered":"OpenCV \uac15\uc88c, \uac04\ub2e8\ud55c Mask R-CNN \ubaa8\ub378 \uc0ac\uc6a9\ubc95"},"content":{"rendered":"

<\/p>\n

\n \ucd5c\uadfc \ucef4\ud4e8\ud130 \ube44\uc804 \ubd84\uc57c\uc5d0\uc11c Mask R-CNN\uc740 \uac1d\uccb4 \ud0d0\uc9c0 \ubc0f \ubd84\ud560 \uc791\uc5c5\uc744 \uc704\ud55c \ub9e4\uc6b0 \uc778\uae30 \uc788\ub294 \ubc29\ubc95\ub860 \uc911 \ud558\ub098\uc785\ub2c8\ub2e4.
\n Mask R-CNN\uc740 Faster R-CNN\uc744 \uae30\ubc18\uc73c\ub85c \ud558\uc5ec, \uac01 \uac1d\uccb4\uc5d0 \ub300\ud574 \ud53d\uc140 \uc218\uc900\uc758 \ub9c8\uc2a4\ud06c\ub97c \uc0dd\uc131\ud558\ub294 \uae30\ub2a5\uc744 \ucd94\uac00\ud569\ub2c8\ub2e4.
\n \ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 Python\uacfc OpenCV\ub97c \uc0ac\uc6a9\ud558\uc5ec Mask R-CNN \ubaa8\ub378\uc744 \ud65c\uc6a9\ud558\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4.\n<\/p>\n

1. Mask R-CNN \uac1c\uc694<\/h2>\n

\n Mask R-CNN\uc740 \ub2e8\uc21c\ud55c \uac1d\uccb4 \ud0d0\uc9c0\ub97c \ub118\uc5b4, \uac01 \uac1d\uccb4\uc758 \uc724\uacfd\uc744 \ud53d\uc140 \ub2e8\uc704\ub85c \ud45c\ud604\ud560 \uc218 \uc788\ub294 \ubc29\ubc95\uc744 \uc81c\uacf5\ud569\ub2c8\ub2e4.
\n \uc774 \ubaa8\ub378\uc740 \uc7a0\uc7ac\uc801\uc73c\ub85c \ubaa8\ub4e0 \ud53d\uc140\uc5d0\uc11c \uac1d\uccb4\uac00 \uc18d\ud558\ub294 \ud074\ub798\uc2a4\uc640 \ub9c8\uc2a4\ud06c\ub97c \uc608\uce21\ud569\ub2c8\ub2e4.
\n Mask R-CNN\uc740 \uc8fc\ub85c COCO(Common Objects in Context) \ub370\uc774\ud130\uc14b\uc5d0\uc11c \ud6c8\ub828\ub418\uc5b4 \ub9ce\uc740 \uac1d\uccb4\ub97c \uc778\uc2dd\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.\n<\/p>\n

2. Mask R-CNN \ubaa8\ub378 \ub2e4\uc6b4\ub85c\ub4dc \ubc0f \uc124\uc815<\/h2>\n

\n Mask R-CNN\uc744 \uc0ac\uc6a9\ud558\uae30 \uc704\ud574 \uc0ac\uc804 \ud6c8\ub828\ub41c \ubaa8\ub378 \ud30c\uc77c\uc744 \ub2e4\uc6b4\ub85c\ub4dc\ud574\uc57c \ud569\ub2c8\ub2e4.
\n \uc77c\ubc18\uc801\uc73c\ub85c Mask R-CNN\uc744 \uc0ac\uc6a9\ud558\ub294 \ub370 \ud544\uc694\ud55c \ub77c\uc774\ube0c\ub7ec\ub9ac\ub294 TensorFlow \ub610\ub294 PyTorch\uc774\uba70, \uc5ec\uae30\uc11c\ub294 TensorFlow\ub97c \uae30\ubc18\uc73c\ub85c \uc124\uc815\ud558\uaca0\uc2b5\ub2c8\ub2e4.\n<\/p>\n

\n\n# \ud544\uc694\ud55c \ub77c\uc774\ube0c\ub7ec\ub9ac \uc124\uce58\n!pip install tensorflow opencv-python\n<\/code>\n<\/pre>\n
\n    \ub2e4\uc74c\uc73c\ub85c Mask R-CNN \ubaa8\ub378\uc744 \ub2e4\uc6b4\ub85c\ub4dc\ud569\ub2c8\ub2e4. TensorFlow Model Zoo\uc5d0\uc11c \uc77c\ubc18\uc801\uc73c\ub85c \uc0ac\uc6a9\ub418\ub294 \uc0ac\uc804 \ud6c8\ub828\ub41c \ubaa8\ub378 \ud30c\uc77c\uc744 \ub2e4\uc6b4\ub85c\ub4dc\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.\n<\/p>\n
\n\n# Mask R-CNN \ubaa8\ub378 \ub2e4\uc6b4\ub85c\ub4dc\nMODEL_URL = \"https:\/\/github.com\/matterport\/Mask_RCNN\/releases\/download\/v1.0\/mask_rcnn_coco.h5\"\n!wget {MODEL_URL} -O mask_rcnn_coco.h5\n<\/code>\n<\/pre>\n
3. OpenCV\ub97c \uc0ac\uc6a9\ud55c Mask R-CNN \ubaa8\ub378 \uad6c\ud604<\/h2>\n
\n    \uc774\uc81c OpenCV\ub97c \uc0ac\uc6a9\ud558\uc5ec Mask R-CNN\uc744 \uad6c\ud604\ud574\ubcf4\uaca0\uc2b5\ub2c8\ub2e4.
\n    OpenCV\ub294 \uc774\ubbf8\uc9c0\uc640 \ube44\ub514\uc624 \ucc98\ub9ac\uc5d0\uc11c \ub110\ub9ac \uc0ac\uc6a9\ub418\ub294 \ub77c\uc774\ube0c\ub7ec\ub9ac\ub85c, Mask R-CNN\uc758 \ucd94\ub860\uc5d0 \ud544\uc694\ud55c \uc804\ucc98\ub9ac \ubc0f \ud6c4\ucc98\ub9ac \uc791\uc5c5\uc744 \uc27d\uac8c \uc218\ud589\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.\n<\/p>\n
3.1 \uc774\ubbf8\uc9c0 \uc804\ucc98\ub9ac<\/h3>\n
\n    Mask R-CNN\uc740 \uace0\uc815\ub41c \ud06c\uae30\uc758 \uc785\ub825 \uc774\ubbf8\uc9c0\ub97c \ud544\uc694\ub85c \ud558\ubbc0\ub85c, \uc6d0\ubcf8 \uc774\ubbf8\uc9c0\ub97c \ud574\ub2f9 \ud06c\uae30\ub85c \uc870\uc815\ud574\uc57c \ud569\ub2c8\ub2e4.\n<\/p>\n
\n\nimport cv2\nimport numpy as np\n\n# \uc774\ubbf8\uc9c0 \uc804\ucc98\ub9ac \ud568\uc218\ndef preprocess_image(image, target_size=(1024, 1024)):\n    # \uc774\ubbf8\uc9c0 \ud06c\uae30 \uc870\uc815\n    h, w, _ = image.shape\n    ratio = min(target_size[0] \/ h, target_size[1] \/ w)\n    new_size = (int(w * ratio), int(h * ratio))\n    image_resized = cv2.resize(image, new_size)\n\n    # \uc815\uaddc\ud654\n    image_normalized = image_resized \/ 255.0\n    return image_normalized\n<\/code>\n<\/pre>\n
3.2 Mask R-CNN \ubaa8\ub378 \ub85c\ub4dc<\/h3>\n
\n    TensorFlow\ub97c \uc0ac\uc6a9\ud558\uc5ec \uc0ac\uc804 \ud6c8\ub828\ub41c Mask R-CNN \ubaa8\ub378\uc744 \ub85c\ub4dc\ud569\ub2c8\ub2e4.\n<\/p>\n
\n\nimport tensorflow as tf\n\n# Mask R-CNN \ubaa8\ub378 \ub85c\ub4dc\nmodel = tf.keras.models.load_model('mask_rcnn_coco.h5', compile=False)\n<\/code>\n<\/pre>\n
3.3 \ucd94\ub860 \uc218\ud589<\/h3>\n
\n    \uc804\ucc98\ub9ac\ub41c \uc774\ubbf8\uc9c0\ub97c \ubaa8\ub378\uc5d0 \uc785\ub825\ud558\uc5ec \uac1d\uccb4 \ud0d0\uc9c0 \ubc0f \ubd84\ud560\uc744 \uc218\ud589\ud569\ub2c8\ub2e4.\n<\/p>\n
\n\ndef detect_objects(image):\n    # \uc774\ubbf8\uc9c0\ub97c \uc804\ucc98\ub9ac\n    preprocessed_image = preprocess_image(image)\n\n    # \ubaa8\ub378 \uc0ac\uc6a9\n    detections = model.predict(np.expand_dims(preprocessed_image, axis=0))\n\n    return detections\n<\/code>\n<\/pre>\n
3.4 \uacb0\uacfc \ud6c4\ucc98\ub9ac<\/h3>\n
\n    \ubaa8\ub378\uc758 \ucd9c\ub825\uc744 \ud574\uc11d\ud558\uace0 \uacb0\uacfc\ub97c \uc2dc\uac01\ud654\ud569\ub2c8\ub2e4.\n<\/p>\n
\n\ndef visualize_results(image, detections):\n    for i in range(len(detections['rois'])):\n        roi = detections['rois'][i]\n        score = detections['scores'][i]\n        if score > 0.5:  # \uc2e0\ub8b0\ub3c4 \uae30\uc900\n            # \ubc14\uc6b4\ub529 \ubc15\uc2a4 \uadf8\ub9ac\uae30\n            cv2.rectangle(image, (int(roi[1]), int(roi[0])), \n                          (int(roi[3]), int(roi[2])), (255, 0, 0), 2)\n    cv2.imshow('Result', image)\n    cv2.waitKey(0)\n    cv2.destroyAllWindows()\n<\/code>\n<\/pre>\n
4. \uc804\uccb4 \ucf54\ub4dc<\/h2>\n
\n    \uc704\uc758 \ubaa8\ub4e0 \ub2e8\uacc4\ub97c \ud1b5\ud569\ud55c \uc804\uccb4 \ucf54\ub4dc\uc785\ub2c8\ub2e4.\n<\/p>\n
\n\nimport cv2\nimport numpy as np\nimport tensorflow as tf\n\ndef preprocess_image(image, target_size=(1024, 1024)):\n    h, w, _ = image.shape\n    ratio = min(target_size[0] \/ h, target_size[1] \/ w)\n    new_size = (int(w * ratio), int(h * ratio))\n    image_resized = cv2.resize(image, new_size)\n    image_normalized = image_resized \/ 255.0\n    return image_normalized\n\ndef detect_objects(image):\n    preprocessed_image = preprocess_image(image)\n    detections = model.predict(np.expand_dims(preprocessed_image, axis=0))\n    return detections\n\ndef visualize_results(image, detections):\n    for i in range(len(detections['rois'])):\n        roi = detections['rois'][i]\n        score = detections['scores'][i]\n        if score > 0.5:\n            cv2.rectangle(image, (int(roi[1]), int(roi[0])), \n                          (int(roi[3]), int(roi[2])), (255, 0, 0), 2)\n    cv2.imshow('Result', image)\n    cv2.waitKey(0)\n    cv2.destroyAllWindows()\n\n# \uc8fc\uc694 \uc2e4\ud589 \ucf54\ub4dc\nif __name__ == \"__main__\":\n    model = tf.keras.models.load_model('mask_rcnn_coco.h5', compile=False)\n    image = cv2.imread('input_image.jpg')  # \ud14c\uc2a4\ud2b8\ud560 \uc774\ubbf8\uc9c0\n    detections = detect_objects(image)\n    visualize_results(image, detections)\n<\/code>\n<\/pre>\n
5. \uacb0\ub860<\/h2>\n
\n    \uc774\ubc88 \uac15\uc88c\uc5d0\uc11c\ub294 OpenCV\uc640 Mask R-CNN\uc744 \uc0ac\uc6a9\ud558\uc5ec \uac1d\uccb4 \ud0d0\uc9c0 \ubc0f \ubd84\ud560\uc744 \uc218\ud589\ud558\ub294 \ubc29\ubc95\uc744 \uc54c\uc544\ubcf4\uc558\uc2b5\ub2c8\ub2e4.
\n    Mask R-CNN\uc740 \ub2e4\uc591\ud55c \uc751\uc6a9 \ubd84\uc57c\uc5d0\uc11c \uac1d\uccb4 \uc778\uc2dd \ub2a5\ub825\uc744 \uac15\ud654\ud558\ub294 \ub370 \ub9e4\uc6b0 \ud6a8\uacfc\uc801\uc785\ub2c8\ub2e4.
\n    \uc774 \ucf54\ub4dc\ub97c \ubc14\ud0d5\uc73c\ub85c \ub2e4\ub978 \ub370\uc774\ud130\uc14b\uc774\ub098 \uc0ac\uc6a9\uc790 \uc815\uc758 \ubaa8\ub378\ub85c \ud655\uc7a5\ud558\uc5ec \ub354 \ub9ce\uc740 \uac1d\uccb4 \ud0d0\uc9c0 \uc791\uc5c5\uc744 \uc218\ud589\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.
\n    \ucef4\ud4e8\ud130 \ube44\uc804 \ubd84\uc57c\uc5d0\uc11c\uc758 \uc9c0\uc18d\uc801\uc778 \ubc1c\uc804\uc5d0 \ubc1c\ub9de\ucd94\uc5b4 \ub098\uac00\uc2dc\uae30 \ubc14\ub78d\ub2c8\ub2e4.\n<\/p>\n
<\/body><\/p>\n","protected":false},"excerpt":{"rendered":"
\ucd5c\uadfc \ucef4\ud4e8\ud130 \ube44\uc804 \ubd84\uc57c\uc5d0\uc11c Mask R-CNN\uc740 \uac1d\uccb4 \ud0d0\uc9c0 \ubc0f \ubd84\ud560 \uc791\uc5c5\uc744 \uc704\ud55c \ub9e4\uc6b0 \uc778\uae30 \uc788\ub294 \ubc29\ubc95\ub860 \uc911 \ud558\ub098\uc785\ub2c8\ub2e4. Mask R-CNN\uc740 Faster R-CNN\uc744 \uae30\ubc18\uc73c\ub85c \ud558\uc5ec, \uac01 \uac1d\uccb4\uc5d0 \ub300\ud574 \ud53d\uc140 \uc218\uc900\uc758 \ub9c8\uc2a4\ud06c\ub97c \uc0dd\uc131\ud558\ub294 \uae30\ub2a5\uc744 \ucd94\uac00\ud569\ub2c8\ub2e4. \ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 Python\uacfc OpenCV\ub97c \uc0ac\uc6a9\ud558\uc5ec Mask R-CNN \ubaa8\ub378\uc744 \ud65c\uc6a9\ud558\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. Mask R-CNN \uac1c\uc694 Mask R-CNN\uc740 \ub2e8\uc21c\ud55c \uac1d\uccb4 \ud0d0\uc9c0\ub97c \ub118\uc5b4, … \ub354 \ubcf4\uae30 “OpenCV \uac15\uc88c, \uac04\ub2e8\ud55c Mask R-CNN \ubaa8\ub378 \uc0ac\uc6a9\ubc95”<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[187],"tags":[],"class_list":["post-38786","post","type-post","status-publish","format-standard","hentry","category-opencv"],"yoast_head":"\nOpenCV \uac15\uc88c, \uac04\ub2e8\ud55c Mask R-CNN \ubaa8\ub378 \uc0ac\uc6a9\ubc95 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8<\/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:\/\/atmokpo.com\/w\/38786\/\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"OpenCV \uac15\uc88c, \uac04\ub2e8\ud55c Mask R-CNN \ubaa8\ub378 \uc0ac\uc6a9\ubc95 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"og:description\" content=\"\ucd5c\uadfc \ucef4\ud4e8\ud130 \ube44\uc804 \ubd84\uc57c\uc5d0\uc11c Mask R-CNN\uc740 \uac1d\uccb4 \ud0d0\uc9c0 \ubc0f \ubd84\ud560 \uc791\uc5c5\uc744 \uc704\ud55c \ub9e4\uc6b0 \uc778\uae30 \uc788\ub294 \ubc29\ubc95\ub860 \uc911 \ud558\ub098\uc785\ub2c8\ub2e4. Mask R-CNN\uc740 Faster R-CNN\uc744 \uae30\ubc18\uc73c\ub85c \ud558\uc5ec, \uac01 \uac1d\uccb4\uc5d0 \ub300\ud574 \ud53d\uc140 \uc218\uc900\uc758 \ub9c8\uc2a4\ud06c\ub97c \uc0dd\uc131\ud558\ub294 \uae30\ub2a5\uc744 \ucd94\uac00\ud569\ub2c8\ub2e4. \ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 Python\uacfc OpenCV\ub97c \uc0ac\uc6a9\ud558\uc5ec Mask R-CNN \ubaa8\ub378\uc744 \ud65c\uc6a9\ud558\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. Mask R-CNN \uac1c\uc694 Mask R-CNN\uc740 \ub2e8\uc21c\ud55c \uac1d\uccb4 \ud0d0\uc9c0\ub97c \ub118\uc5b4, … \ub354 \ubcf4\uae30 "OpenCV \uac15\uc88c, \uac04\ub2e8\ud55c Mask R-CNN \ubaa8\ub378 \uc0ac\uc6a9\ubc95"\" \/>\n<meta property=\"og:url\" content=\"https:\/\/atmokpo.com\/w\/38786\/\" \/>\n<meta property=\"og:site_name\" content=\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"article:published_time\" content=\"2024-11-02T00:57:05+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-11-26T06:43:20+00:00\" \/>\n<meta name=\"author\" content=\"root\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@bebubo4\" \/>\n<meta name=\"twitter:site\" content=\"@bebubo4\" \/>\n<meta name=\"twitter:label1\" content=\"\uae00\uc4f4\uc774\" \/>\n\t<meta name=\"twitter:data1\" content=\"root\" \/>\n\t<meta name=\"twitter:label2\" content=\"\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04\" \/>\n\t<meta name=\"twitter:data2\" content=\"2\ubd84\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/atmokpo.com\/w\/38786\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/38786\/\"},\"author\":{\"name\":\"root\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\"},\"headline\":\"OpenCV \uac15\uc88c, \uac04\ub2e8\ud55c Mask R-CNN \ubaa8\ub378 \uc0ac\uc6a9\ubc95\",\"datePublished\":\"2024-11-02T00:57:05+00:00\",\"dateModified\":\"2024-11-26T06:43:20+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/atmokpo.com\/w\/38786\/\"},\"wordCount\":59,\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"articleSection\":[\"OpenCV\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/atmokpo.com\/w\/38786\/\",\"url\":\"https:\/\/atmokpo.com\/w\/38786\/\",\"name\":\"OpenCV \uac15\uc88c, \uac04\ub2e8\ud55c Mask R-CNN \ubaa8\ub378 \uc0ac\uc6a9\ubc95 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#website\"},\"datePublished\":\"2024-11-02T00:57:05+00:00\",\"dateModified\":\"2024-11-26T06:43:20+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/atmokpo.com\/w\/38786\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/atmokpo.com\/w\/38786\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/atmokpo.com\/w\/38786\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\ud648\",\"item\":\"https:\/\/atmokpo.com\/w\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"OpenCV \uac15\uc88c, \uac04\ub2e8\ud55c Mask R-CNN \ubaa8\ub378 \uc0ac\uc6a9\ubc95\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/atmokpo.com\/w\/#website\",\"url\":\"https:\/\/atmokpo.com\/w\/\",\"name\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/atmokpo.com\/w\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ko-KR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\",\"name\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"url\":\"https:\/\/atmokpo.com\/w\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png\",\"contentUrl\":\"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png\",\"width\":400,\"height\":400,\"caption\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\"},\"image\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/bebubo4\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\",\"name\":\"root\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g\",\"caption\":\"root\"},\"sameAs\":[\"http:\/\/atmokpo.com\/w\"],\"url\":\"https:\/\/atmokpo.com\/w\/author\/root\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"OpenCV \uac15\uc88c, \uac04\ub2e8\ud55c Mask R-CNN \ubaa8\ub378 \uc0ac\uc6a9\ubc95 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","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:\/\/atmokpo.com\/w\/38786\/","og_locale":"ko_KR","og_type":"article","og_title":"OpenCV \uac15\uc88c, \uac04\ub2e8\ud55c Mask R-CNN \ubaa8\ub378 \uc0ac\uc6a9\ubc95 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","og_description":"\ucd5c\uadfc \ucef4\ud4e8\ud130 \ube44\uc804 \ubd84\uc57c\uc5d0\uc11c Mask R-CNN\uc740 \uac1d\uccb4 \ud0d0\uc9c0 \ubc0f \ubd84\ud560 \uc791\uc5c5\uc744 \uc704\ud55c \ub9e4\uc6b0 \uc778\uae30 \uc788\ub294 \ubc29\ubc95\ub860 \uc911 \ud558\ub098\uc785\ub2c8\ub2e4. Mask R-CNN\uc740 Faster R-CNN\uc744 \uae30\ubc18\uc73c\ub85c \ud558\uc5ec, \uac01 \uac1d\uccb4\uc5d0 \ub300\ud574 \ud53d\uc140 \uc218\uc900\uc758 \ub9c8\uc2a4\ud06c\ub97c \uc0dd\uc131\ud558\ub294 \uae30\ub2a5\uc744 \ucd94\uac00\ud569\ub2c8\ub2e4. \ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 Python\uacfc OpenCV\ub97c \uc0ac\uc6a9\ud558\uc5ec Mask R-CNN \ubaa8\ub378\uc744 \ud65c\uc6a9\ud558\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. Mask R-CNN \uac1c\uc694 Mask R-CNN\uc740 \ub2e8\uc21c\ud55c \uac1d\uccb4 \ud0d0\uc9c0\ub97c \ub118\uc5b4, … \ub354 \ubcf4\uae30 \"OpenCV \uac15\uc88c, \uac04\ub2e8\ud55c Mask R-CNN \ubaa8\ub378 \uc0ac\uc6a9\ubc95\"","og_url":"https:\/\/atmokpo.com\/w\/38786\/","og_site_name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","article_published_time":"2024-11-02T00:57:05+00:00","article_modified_time":"2024-11-26T06:43:20+00:00","author":"root","twitter_card":"summary_large_image","twitter_creator":"@bebubo4","twitter_site":"@bebubo4","twitter_misc":{"\uae00\uc4f4\uc774":"root","\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04":"2\ubd84"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/atmokpo.com\/w\/38786\/#article","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/38786\/"},"author":{"name":"root","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7"},"headline":"OpenCV \uac15\uc88c, \uac04\ub2e8\ud55c Mask R-CNN \ubaa8\ub378 \uc0ac\uc6a9\ubc95","datePublished":"2024-11-02T00:57:05+00:00","dateModified":"2024-11-26T06:43:20+00:00","mainEntityOfPage":{"@id":"https:\/\/atmokpo.com\/w\/38786\/"},"wordCount":59,"publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"articleSection":["OpenCV"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/atmokpo.com\/w\/38786\/","url":"https:\/\/atmokpo.com\/w\/38786\/","name":"OpenCV \uac15\uc88c, \uac04\ub2e8\ud55c Mask R-CNN \ubaa8\ub378 \uc0ac\uc6a9\ubc95 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/#website"},"datePublished":"2024-11-02T00:57:05+00:00","dateModified":"2024-11-26T06:43:20+00:00","breadcrumb":{"@id":"https:\/\/atmokpo.com\/w\/38786\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/atmokpo.com\/w\/38786\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/atmokpo.com\/w\/38786\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\ud648","item":"https:\/\/atmokpo.com\/w\/en\/"},{"@type":"ListItem","position":2,"name":"OpenCV \uac15\uc88c, \uac04\ub2e8\ud55c Mask R-CNN \ubaa8\ub378 \uc0ac\uc6a9\ubc95"}]},{"@type":"WebSite","@id":"https:\/\/atmokpo.com\/w\/#website","url":"https:\/\/atmokpo.com\/w\/","name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","description":"","publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/atmokpo.com\/w\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ko-KR"},{"@type":"Organization","@id":"https:\/\/atmokpo.com\/w\/#organization","name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","url":"https:\/\/atmokpo.com\/w\/","logo":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/","url":"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png","contentUrl":"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png","width":400,"height":400,"caption":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8"},"image":{"@id":"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/bebubo4"]},{"@type":"Person","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7","name":"root","image":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g","caption":"root"},"sameAs":["http:\/\/atmokpo.com\/w"],"url":"https:\/\/atmokpo.com\/w\/author\/root\/"}]}},"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack-related-posts":[],"_links":{"self":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/38786","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/comments?post=38786"}],"version-history":[{"count":1,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/38786\/revisions"}],"predecessor-version":[{"id":38787,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/38786\/revisions\/38787"}],"wp:attachment":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/media?parent=38786"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/categories?post=38786"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/tags?post=38786"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}