[{"data":1,"prerenderedAt":750},["ShallowReactive",2],{"node-red-\u002Fnode-red\u002Fflowfuse\u002Fai\u002Fobject-detection":3},{"id":4,"title":5,"body":6,"description":742,"extension":743,"meta":744,"navigation":745,"path":746,"seo":747,"stem":748,"__hash__":749},"nodeRed\u002Fnode-red\u002Fflowfuse\u002Fai\u002Fobject-detection.md","Object Detection",{"type":7,"value":8,"toc":727},"minimark",[9,17,37,44,49,54,95,99,127,136,140,151,155,163,166,170,173,302,307,310,316,350,353,358,410,414,418,425,564,567,590,594,597,666,673,677,714,718,723],[10,11,13],"h1",{"id":12},"",[14,15],"binding",{"value":16},"meta.title",[18,19,20,21,24,25,28,29,32,33,36],"p",{},"The ",[22,23,5],"strong",{}," node enables detection of objects within images using ",[22,26,27],{},"ONNX models",".\nIt supports a wide range of architectures, including ",[22,30,31],{},"DETR"," and ",[22,34,35],{},"YOLO",", and accepts image data in multiple formats such as Buffers, base64 strings, or tensors.",[18,38,39,40,43],{},"This node is ideal for computer vision use cases like identifying objects in images, counting items, or performing scene analysis directly within ",[22,41,42],{},"Node-RED",".",[45,46,48],"h2",{"id":47},"inputs","Inputs",[50,51,53],"h3",{"id":52},"general","General",[55,56,57,68,84],"ul",{},[58,59,60,63,64],"li",{},[22,61,62],{},"Property:"," ",[65,66,67],"code",{},"input",[58,69,70,63,73,76,77,76,80,83],{},[22,71,72],{},"Type:",[65,74,75],{},"object",", ",[65,78,79],{},"buffer",[65,81,82],{},"string"," or tensor.",[58,85,86,89,90,94],{},[22,87,88],{},"Description:"," The input image or tensor to classify. See the ",[91,92,93],"em",{},"Details"," section for supported formats.",[50,96,98],{"id":97},"model-selection","Model Selection",[55,100,101,107],{},[58,102,103,106],{},[22,104,105],{},"model:"," Path to a local ONNX model file or the name of a model to download from Hugging Face.",[58,108,109,112,113,116,117,76,120,76,123,126],{},[22,110,111],{},"type:"," Data type for the model when using a model name. Supported values include ",[65,114,115],{},"q8"," (default), ",[65,118,119],{},"fp16",[65,121,122],{},"fp32",[65,124,125],{},"int8",", and others.",[128,129,130],"blockquote",{},[18,131,132,135],{},[22,133,134],{},"Note:","\nWhen a model name is provided, the node automatically downloads and caches it locally if it is not already available.",[50,137,139],{"id":138},"configuration","Configuration",[55,141,142],{},[58,143,144,147,148,43],{},[22,145,146],{},"threshold:"," Minimum confidence score (0.0–1.0) required for a prediction to be included in the output.\nThis can also be passed dynamically via ",[65,149,150],{},"msg.threshold",[45,152,154],{"id":153},"outputs","Outputs",[55,156,157],{},[58,158,159,162],{},[22,160,161],{},"payload:"," Contains the detection results.\nDepending on the model type and processing support, the output can be an array or an object.",[45,164,93],{"id":165},"details",[50,167,169],{"id":168},"supported-input-formats","Supported Input Formats",[18,171,172],{},"The node supports multiple input formats depending on the model’s requirements:",[55,174,175,181,187,197],{},[58,176,177,180],{},[22,178,179],{},"Buffer"," — Binary image data, typically from a file or camera input.",[58,182,183,186],{},[22,184,185],{},"Base64 string"," — Base64-encoded image data.",[58,188,189,192,193,196],{},[22,190,191],{},"Jimp Image Object"," — An image object (e.g, output from ",[65,194,195],{},"node-red-contrib-image-tools",").",[58,198,199,202,203],{},[22,200,201],{},"Tensor"," — A pre-processed tensor object in the following format:",[204,205,209],"pre",{"className":206,"code":207,"language":208,"meta":12,"style":12},"language-json shiki shiki-themes github-light github-dark","{\n  \"data\": [0.0, 0.1, 0.2, ...],\n  \"type\": \"float32\",\n  \"dim\": [1, 3, 224, 224]\n}\n","json",[65,210,211,220,252,268,296],{"__ignoreMap":12},[212,213,216],"span",{"class":214,"line":215},"line",1,[212,217,219],{"class":218},"sVt8B","{\n",[212,221,223,227,230,233,235,238,240,243,245,249],{"class":214,"line":222},2,[212,224,226],{"class":225},"sj4cs","  \"data\"",[212,228,229],{"class":218},": [",[212,231,232],{"class":225},"0.0",[212,234,76],{"class":218},[212,236,237],{"class":225},"0.1",[212,239,76],{"class":218},[212,241,242],{"class":225},"0.2",[212,244,76],{"class":218},[212,246,248],{"class":247},"s7hpK","...",[212,250,251],{"class":218},"],\n",[212,253,255,258,261,265],{"class":214,"line":254},3,[212,256,257],{"class":225},"  \"type\"",[212,259,260],{"class":218},": ",[212,262,264],{"class":263},"sZZnC","\"float32\"",[212,266,267],{"class":218},",\n",[212,269,271,274,276,279,281,284,286,289,291,293],{"class":214,"line":270},4,[212,272,273],{"class":225},"  \"dim\"",[212,275,229],{"class":218},[212,277,278],{"class":225},"1",[212,280,76],{"class":218},[212,282,283],{"class":225},"3",[212,285,76],{"class":218},[212,287,288],{"class":225},"224",[212,290,76],{"class":218},[212,292,288],{"class":225},[212,294,295],{"class":218},"]\n",[212,297,299],{"class":214,"line":298},5,[212,300,301],{"class":218},"}\n",[128,303,304],{},[18,305,306],{},"TIP: If the model supports batching, the input can be an array of images in one of the supported formats.",[50,308,98],{"id":309},"model-selection-1",[18,311,20,312,315],{},[65,313,314],{},"model"," property defines which ONNX model to use. You can either:",[55,317,318,329],{},[58,319,320,321,324,325,328],{},"Provide a ",[22,322,323],{},"local path"," (for example, ",[65,326,327],{},"\u002Fdata\u002Fmodels\u002Fyolov5.onnx","), or",[58,330,331,332,335,336,324,345,196],{},"Specify a ",[22,333,334],{},"model name"," available on ",[22,337,338],{},[339,340,344],"a",{"href":341,"rel":342},"https:\u002F\u002Fhuggingface.co\u002Fmodels?pipeline_tag=object-detection&library=transformers.js,onnx&sort=trending",[343],"nofollow","Hugging Face",[339,346,349],{"href":347,"rel":348},"https:\u002F\u002Fhuggingface.co\u002FXenova\u002Fdetr-resnet-50",[343],"Xenova\u002Fdetr-resnet-50",[18,351,352],{},"When a model name is provided, it is automatically fetched and cached locally for reuse.",[354,355,357],"h4",{"id":356},"model-type-options","Model Type Options",[55,359,360,366,371,376,381,387,392,398,404],{},[58,361,362,365],{},[65,363,364],{},"auto"," — Automatically selects the most suitable type.",[58,367,368,370],{},[65,369,122],{}," — Standard 32-bit floating-point model.",[58,372,373,375],{},[65,374,119],{}," — Half-precision 16-bit floating-point model.",[58,377,378,380],{},[65,379,125],{}," — 8-bit integer quantized model.",[58,382,383,386],{},[65,384,385],{},"uint8"," — 8-bit unsigned integer model.",[58,388,389,391],{},[65,390,115],{}," — Quantized Int8 model (default).",[58,393,394,397],{},[65,395,396],{},"q4"," — Quantized Int4 model.",[58,399,400,403],{},[65,401,402],{},"q4f16"," — Quantized Int4 with Float16 model.",[58,405,406,409],{},[65,407,408],{},"bnb4"," — BNB4 quantized model.",[50,411,413],{"id":412},"output-format","Output Format",[354,415,417],{"id":416},"when-supported-yolodetr-models","When Supported (YOLO\u002FDETR Models)",[18,419,420,421,424],{},"If the model output is recognized by the node, ",[65,422,423],{},"msg.payload"," contains structured detection results:",[204,426,428],{"className":206,"code":427,"language":208,"meta":12,"style":12},"[\n  {\n    \"label\": \"dog\",\n    \"score\": 0.9796,\n    \"bbox\": [130, 218, 309, 538]\n  },\n  {\n    \"label\": \"person\",\n    \"score\": 0.9451,\n    \"bbox\": [420, 110, 640, 520]\n  }\n]\n",[65,429,430,435,440,452,464,491,497,502,514,526,553,559],{"__ignoreMap":12},[212,431,432],{"class":214,"line":215},[212,433,434],{"class":218},"[\n",[212,436,437],{"class":214,"line":222},[212,438,439],{"class":218},"  {\n",[212,441,442,445,447,450],{"class":214,"line":254},[212,443,444],{"class":225},"    \"label\"",[212,446,260],{"class":218},[212,448,449],{"class":263},"\"dog\"",[212,451,267],{"class":218},[212,453,454,457,459,462],{"class":214,"line":270},[212,455,456],{"class":225},"    \"score\"",[212,458,260],{"class":218},[212,460,461],{"class":225},"0.9796",[212,463,267],{"class":218},[212,465,466,469,471,474,476,479,481,484,486,489],{"class":214,"line":298},[212,467,468],{"class":225},"    \"bbox\"",[212,470,229],{"class":218},[212,472,473],{"class":225},"130",[212,475,76],{"class":218},[212,477,478],{"class":225},"218",[212,480,76],{"class":218},[212,482,483],{"class":225},"309",[212,485,76],{"class":218},[212,487,488],{"class":225},"538",[212,490,295],{"class":218},[212,492,494],{"class":214,"line":493},6,[212,495,496],{"class":218},"  },\n",[212,498,500],{"class":214,"line":499},7,[212,501,439],{"class":218},[212,503,505,507,509,512],{"class":214,"line":504},8,[212,506,444],{"class":225},[212,508,260],{"class":218},[212,510,511],{"class":263},"\"person\"",[212,513,267],{"class":218},[212,515,517,519,521,524],{"class":214,"line":516},9,[212,518,456],{"class":225},[212,520,260],{"class":218},[212,522,523],{"class":225},"0.9451",[212,525,267],{"class":218},[212,527,529,531,533,536,538,541,543,546,548,551],{"class":214,"line":528},10,[212,530,468],{"class":225},[212,532,229],{"class":218},[212,534,535],{"class":225},"420",[212,537,76],{"class":218},[212,539,540],{"class":225},"110",[212,542,76],{"class":218},[212,544,545],{"class":225},"640",[212,547,76],{"class":218},[212,549,550],{"class":225},"520",[212,552,295],{"class":218},[212,554,556],{"class":214,"line":555},11,[212,557,558],{"class":218},"  }\n",[212,560,562],{"class":214,"line":561},12,[212,563,295],{"class":218},[18,565,566],{},"Each object includes:",[55,568,569,575,581],{},[58,570,571,574],{},[22,572,573],{},"label:"," Detected class name (for example, dog, person, car)",[58,576,577,580],{},[22,578,579],{},"score:"," Confidence score for the detection",[58,582,583,586,587],{},[22,584,585],{},"bbox:"," Bounding box coordinates ",[65,588,589],{},"[x_min, y_min, x_max, y_max]",[354,591,593],{"id":592},"when-not-supported-raw-output","When Not Supported (Raw Output)",[18,595,596],{},"If the node cannot interpret the model output automatically, it returns the raw response:",[204,598,600],{"className":206,"code":599,"language":208,"meta":12,"style":12},"{\n  \"result\": [...],\n  \"labels\": {\n    \"0\": \"person\",\n    \"1\": \"bicycle\",\n    \"2\": \"car\"\n  }\n}\n",[65,601,602,606,617,625,636,648,658,662],{"__ignoreMap":12},[212,603,604],{"class":214,"line":215},[212,605,219],{"class":218},[212,607,608,611,613,615],{"class":214,"line":222},[212,609,610],{"class":225},"  \"result\"",[212,612,229],{"class":218},[212,614,248],{"class":247},[212,616,251],{"class":218},[212,618,619,622],{"class":214,"line":254},[212,620,621],{"class":225},"  \"labels\"",[212,623,624],{"class":218},": {\n",[212,626,627,630,632,634],{"class":214,"line":270},[212,628,629],{"class":225},"    \"0\"",[212,631,260],{"class":218},[212,633,511],{"class":263},[212,635,267],{"class":218},[212,637,638,641,643,646],{"class":214,"line":298},[212,639,640],{"class":225},"    \"1\"",[212,642,260],{"class":218},[212,644,645],{"class":263},"\"bicycle\"",[212,647,267],{"class":218},[212,649,650,653,655],{"class":214,"line":493},[212,651,652],{"class":225},"    \"2\"",[212,654,260],{"class":218},[212,656,657],{"class":263},"\"car\"\n",[212,659,660],{"class":214,"line":499},[212,661,558],{"class":218},[212,663,664],{"class":214,"line":504},[212,665,301],{"class":218},[18,667,668,669,672],{},"You can then use a ",[22,670,671],{},"Function"," node for custom post-processing.",[45,674,676],{"id":675},"notes","Notes",[55,678,679,687,694,705],{},[58,680,681,682,32,684,686],{},"The node currently supports ",[22,683,31],{},[22,685,35],{},"-style object detection models.",[58,688,689,690,693],{},"YOLO models currently accept ",[22,691,692],{},"only single-image input"," (batching support will be added in future releases).",[58,695,696,697,700,701,704],{},"Ensure that your model is compatible with ",[22,698,699],{},"ONNX Runtime"," and designed for ",[22,702,703],{},"object detection"," tasks.",[58,706,707,708,711,712,43],{},"For improved performance on devices with limited resources, use ",[22,709,710],{},"quantized models"," such as ",[65,713,115],{},[45,715,717],{"id":716},"example-flow","Example Flow",[719,720],"render-flow",{":height":721,"flow":722},"200","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",[724,725,726],"style",{},"html pre.shiki code .sVt8B, html code.shiki .sVt8B{--shiki-default:#24292E;--shiki-dark:#E1E4E8}html pre.shiki code .sj4cs, html code.shiki .sj4cs{--shiki-default:#005CC5;--shiki-dark:#79B8FF}html pre.shiki code .s7hpK, html code.shiki .s7hpK{--shiki-default:#B31D28;--shiki-default-font-style:italic;--shiki-dark:#FDAEB7;--shiki-dark-font-style:italic}html pre.shiki code .sZZnC, html code.shiki .sZZnC{--shiki-default:#032F62;--shiki-dark:#9ECBFF}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"title":12,"searchDepth":222,"depth":222,"links":728},[729,734,735,740,741],{"id":47,"depth":222,"text":48,"children":730},[731,732,733],{"id":52,"depth":254,"text":53},{"id":97,"depth":254,"text":98},{"id":138,"depth":254,"text":139},{"id":153,"depth":222,"text":154},{"id":165,"depth":222,"text":93,"children":736},[737,738,739],{"id":168,"depth":254,"text":169},{"id":309,"depth":254,"text":98},{"id":412,"depth":254,"text":413},{"id":675,"depth":222,"text":676},{"id":716,"depth":222,"text":717},"The Object Detection node identifies and locates objects within images using ONNX models such as YOLO and DETR, enabling real-time computer vision directly in Node-RED without external AI services.","md",{},true,"\u002Fnode-red\u002Fflowfuse\u002Fai\u002Fobject-detection",{"title":5,"description":742},"node-red\u002Fflowfuse\u002Fai\u002Fobject-detection","PkZE00aIA-CllGA-DSEaU0Caw_90LBbcAYckjK4sg0Y",1780070556766]