Train and deploy a gesture recognition model on ESP32 boards using Edge Impulse, covering data collection, model training, and on-device inference.
Edge Impulse Gesture Recognition
Build a gesture detection system that runs fully offline on your ESP32. This guide uses Edge Impulse to train a model and export it as a ready-to-use Arduino library.
How it Works? (The Simple Version)
Data: You record motion data (gestures) using your smartphone or sensor.
Train: Edge Impulse uses that data to teach an AI model to recognize those patterns.
Deploy: You export the model as code and upload it to your ESP32. It then runs locally without needing the internet.
What You Need
Before starting, make sure you have your hardware and software environment ready.
Hardware Required
ESP32 DevKit (or any ESP32 board).
IMU Sensor (e.g., MPU6050 or LSM6DS3).
Smartphone (To record initial data).
USB Cable (For power and communication).
Software
Arduino IDE: To upload the code.
ESP32 Board Package: Installed via Arduino Boards Manager.
Edge Impulse Account: To train and export your model.
Software Setup
Step 1: Create a Project
Go to edgeimpulse.com, log in, and create a new project named something like “Gesture Detection”.
Step 2: Connect Your Phone
In the Devices tab, connect your smartphone by scanning the QR code. Your phone now acts as the motion sensor for data collection.
Step 3: Collect Data
Go to Data Acquisition, type a label like "up-down", hit Start Sampling, and perform the gesture. Repeat for each gesture you want to teach. Keep the data balanced and save some as Test Data.
Step 4: Design the Impulse
Go to Impulse Design:
Set Window Size to ~2 seconds.
Add Spectral Analysis as the processing block.
Add Neural Network as the learning block.
Step 5: Check Accuracy
Open Feature Explorer and check that your gestures form separate clusters. The more separated they are, the better your accuracy will be.
Step 6: Train the Model
Go to the Classifier tab and hit Start Training. Expect around 80–90% accuracy.
If accuracy is low, collect more data or be more consistent with your gestures.
Step 7: Export as Code
Go to Deployment, select Arduino Library, and download the ZIP file. This is your AI model exported as standard C++ code.
Step 8: Upload to ESP32
Extract the ZIP file.
Open Arduino IDE and go to File → Examples → [Your Project Name] → ESP32 → ESP32 Fusion.
Install the ESP32 board package, wire up your ESP32 + IMU sensor, select the right board and COM port, then click Upload.
Step 9: Test Your Gestures
Open the Serial Monitor and perform your gestures. You will see real-time predictions like "Gesture: up-down". It runs fully offline on the ESP32!Have fun with your mini AI Assistant!
{"docsConfig":{"theme":"mint","$schema":"https://mintlify.com/docs.json","name":"PCB Cupid","colors":{"primary":"#0D9373"},"favicon":"https://mintcdn.com/pcbcupid-bae3761c/4dXNuJjZhqL5zqVd/images/favicon_PCBcupid.png?fit=max\u0026auto=format\u0026n=4dXNuJjZhqL5zqVd\u0026q=85\u0026s=697c4189e0a983e1722bddbedde79f61","appearance":{"strict":true},"background":{"decoration":"gradient"},"navbar":{"links":[{"href":"https://spell.pcbcupid.com","label":"Circuit Spell"},{"href":"https://shop.pcbcupid.com","label":"Shop"},{"href":"/","label":"Learn"},{"href":"https://events.pcbcupid.com","label":"Events"},{"href":"https://forum.pcbcupid.com","label":"Forum"},{"href":"https://pcbcupid.com/articles","label":"Articles"},{"href":"https://pcbcupid.com/tools","label":"Tools"}]},"seo":{"indexing":"all"},"fonts":{"family":"Space Grotesk","weight":400},"icons":{"library":"lucide"},"styling":{"eyebrows":"breadcrumbs","latex":true},"contextual":{"options":["copy","chatgpt","claude","cursor","vscode","mcp"],"display":"toc"},"thumbnails":{"appearance":"dark"},"navigation":{"pages":[]}},"deployment":{"deploymentMetadataValue":{"subdomain":"pcbcupid-bae3761c","hasAudioNarration":false,"actualSubdomain":"pcbcupid-bae3761c","customDomains":["learn.pcbcupid.com"],"gitSource":{"type":"github","owner":"pcbcupid","repo":"pcbcupid-docs","deployBranch":"main","contentDirectory":"","isPrivate":false,"mountPath":"","label":""},"feedback":{"thumbs":true,"edits":true,"issues":true},"entitlements":{"AI_CHAT":{"status":"DISABLED"}},"buildId":"6ae268427b458a5c875a9a81","clientVersion":"0.0.4177","searchFilterCounts":[{"language":"default","tag":"Documentation","count":77},{"language":"default","tag":"Modules","count":67},{"language":"default","tag":"PCB Design","count":45},{"language":"default","tag":"Examples","count":32},{"language":"default","tag":"Glyph","count":25},{"language":"default","tag":"G-Mod","count":17},{"language":"default","tag":"KiCad","count":16},{"language":"default","tag":"Basic","count":15},{"language":"default","tag":"Welcome","count":9},{"language":"default","tag":"G-Sense","count":8}]},"assistantConfig":{"enableAskAiButton":false,"enableStarterQuestions":false,"enableContextualStarterQuestions":false,"enableAskAiSearchBar":true},"basePath":"","hasChatPermissions":false,"hasWebMcpPermissions":false,"toggles":[],"googleFontsInlined":true},"customCss":[],"page":{"pagePath":"guides/ai/edge-impulse","slug":"/guides/ai/edge-impulse","pageMetadata":{"description":"Train and deploy a gesture recognition model on ESP32 boards using Edge Impulse, covering data collection, model training, and on-device inference.","title":"Edge Impulse Gesture Recognition","sidebarTitle":"Edge Impulse","href":"/guides/ai/edge-impulse"},"description":{"compiledSource":"\"use strict\";\nconst {jsx: _jsx} = arguments[0];\nconst {useMDXComponents: _provideComponents} = arguments[0];\nfunction _createMdxContent(props) {\n const _components = {\n p: \"p\",\n ..._provideComponents(),\n ...props.components\n };\n return _jsx(_components.p, {\n children: \"Train and deploy a gesture recognition model on ESP32 boards using Edge Impulse, covering data collection, model training, and on-device inference.\"\n });\n}\nfunction MDXContent(props = {}) {\n const {wrapper: MDXLayout} = {\n ..._provideComponents(),\n ...props.components\n };\n return MDXLayout ? _jsx(MDXLayout, {\n ...props,\n children: _jsx(_createMdxContent, {\n ...props\n })\n }) : _createMdxContent(props);\n}\nreturn {\n default: MDXContent\n};\n","frontmatter":{},"scope":{}},"pageType":"default","mdx":{"mdxSource":{"compiledSource":"\"use strict\";const{Fragment:_Fragment,jsx:_jsx,jsxs:_jsxs}=arguments[0];const{useMDXComponents:_provideComponents}=arguments[0];function _createMdxContent(props){const _components={a:`a`,code:`code`,hr:`hr`,img:`img`,li:`li`,ol:`ol`,p:`p`,strong:`strong`,ul:`ul`,..._provideComponents(),...props.components},{Heading,Tip}=_components;if(!Heading)_missingMdxReference(`Heading`,true);if(!Tip)_missingMdxReference(`Tip`,true);return _jsxs(_Fragment,{children:[_jsx(Heading,{level:`1`,id:`edge-impulse-gesture-recognition`,children:`Edge Impulse Gesture Recognition`}),`\n`,_jsx(_components.p,{children:`Build a gesture detection system that runs fully offline on your ESP32. This guide uses Edge Impulse to train a model and export it as a ready-to-use Arduino library.`}),`\n`,_jsx(Heading,{level:`2`,id:`how-it-works-the-simple-version`,children:`How it Works? (The Simple Version)`}),`\n`,_jsxs(_components.ol,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Data`}),`: You record motion data (gestures) using your smartphone or sensor.`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Train`}),`: Edge Impulse uses that data to teach an AI model to recognize those patterns.`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Deploy`}),`: You export the model as code and upload it to your ESP32. It then runs locally without needing the internet.`]}),`\n`]}),`\n`,_jsx(_components.hr,{}),`\n`,_jsx(Heading,{level:`2`,id:`what-you-need`,children:`What You Need`}),`\n`,_jsx(_components.p,{children:`Before starting, make sure you have your hardware and software environment ready.`}),`\n`,_jsx(Heading,{level:`3`,id:`hardware-required`,children:`Hardware Required`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`ESP32 DevKit`}),` (or any ESP32 board).`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`IMU Sensor`}),` (e.g., MPU6050 or LSM6DS3).`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Smartphone`}),` (To record initial data).`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`USB Cable`}),` (For power and communication).`]}),`\n`]}),`\n`,_jsx(_components.p,{children:_jsx(_components.img,{src:`https://files.pcbcupid.com/Documentation/Boards/Examples/AI/Edge_impulse/Edge_impulse_cktdiag.avif`,alt:`Circuit Diagram`})}),`\n`,_jsx(Heading,{level:`3`,id:`software`,children:`Software`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Arduino IDE`}),`: To upload the code.`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`ESP32 Board Package`}),`: Installed via Arduino Boards Manager.`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Edge Impulse Account`}),`: To train and export your model.`]}),`\n`]}),`\n`,_jsx(_components.hr,{}),`\n`,_jsx(Heading,{level:`2`,id:`software-setup`,children:`Software Setup`}),`\n`,_jsx(Heading,{level:`3`,id:`step-1-create-a-project`,children:`Step 1: Create a Project`}),`\n`,_jsxs(_components.p,{children:[`Go to `,_jsx(_components.a,{href:`https://edgeimpulse.com`,children:`edgeimpulse.com`}),`, log in, and create a new project named something like `,_jsx(_components.strong,{children:`“Gesture Detection”`}),`.`]}),`\n`,_jsx(_components.p,{children:_jsx(_components.img,{src:`https://files.pcbcupid.com/Documentation/Boards/Examples/AI/Edge_impulse/Edge_impulse_1-.avif`,alt:`Project creation `})}),`\n`,_jsx(Heading,{level:`3`,id:`step-2-connect-your-phone`,children:`Step 2: Connect Your Phone`}),`\n`,_jsxs(_components.p,{children:[`In the `,_jsx(_components.strong,{children:`Devices`}),` tab, connect your smartphone by scanning the QR code. Your phone now acts as the motion sensor for data collection.`]}),`\n`,_jsx(_components.p,{children:_jsx(_components.img,{src:`https://files.pcbcupid.com/Documentation/Boards/Examples/AI/Edge_impulse/Edge_impulse_2-.avif`,alt:`Connect your phone`})}),`\n`,_jsx(Heading,{level:`3`,id:`step-3-collect-data`,children:`Step 3: Collect Data`}),`\n`,_jsxs(_components.p,{children:[`Go to `,_jsx(_components.strong,{children:`Data Acquisition`}),`, type a label like `,_jsx(_components.code,{children:`\"up-down\"`}),`, hit `,_jsx(_components.strong,{children:`Start Sampling`}),`, and perform the gesture. Repeat for each gesture you want to teach. Keep the data balanced and save some as `,_jsx(_components.strong,{children:`Test Data`}),`.`]}),`\n`,_jsx(_components.p,{children:_jsx(_components.img,{src:`https://files.pcbcupid.com/Documentation/Boards/Examples/AI/Edge_impulse/Edge_impulse_3-.avif`,alt:`Collect data`})}),`\n`,_jsx(Heading,{level:`3`,id:`step-4-design-the-impulse`,children:`Step 4: Design the Impulse`}),`\n`,_jsxs(_components.p,{children:[`Go to `,_jsx(_components.strong,{children:`Impulse Design`}),`:`]}),`\n`,_jsxs(_components.ol,{children:[`\n`,_jsxs(_components.li,{children:[`Set `,_jsx(_components.strong,{children:`Window Size`}),` to ~2 seconds.`]}),`\n`,_jsxs(_components.li,{children:[`Add `,_jsx(_components.strong,{children:`Spectral Analysis`}),` as the processing block.`]}),`\n`,_jsxs(_components.li,{children:[`Add `,_jsx(_components.strong,{children:`Neural Network`}),` as the learning block.`]}),`\n`]}),`\n`,_jsx(_components.p,{children:_jsx(_components.img,{src:`https://files.pcbcupid.com/Documentation/Boards/Examples/AI/Edge_impulse/Edge_impulse_4-.avif`,alt:`Design impulse`})}),`\n`,_jsx(Heading,{level:`3`,id:`step-5-check-accuracy`,children:`Step 5: Check Accuracy`}),`\n`,_jsxs(_components.p,{children:[`Open `,_jsx(_components.strong,{children:`Feature Explorer`}),` and check that your gestures form separate clusters. The more separated they are, the better your accuracy will be.`]}),`\n`,_jsx(_components.p,{children:_jsx(_components.img,{src:`https://files.pcbcupid.com/Documentation/Boards/Examples/AI/Edge_impulse/Edge_impulse_5-.avif`,alt:`Check accuracy`})}),`\n`,_jsx(_components.hr,{}),`\n`,_jsx(Heading,{level:`3`,id:`step-6-train-the-model`,children:`Step 6: Train the Model`}),`\n`,_jsxs(_components.p,{children:[`Go to the `,_jsx(_components.strong,{children:`Classifier`}),` tab and hit `,_jsx(_components.strong,{children:`Start Training`}),`. Expect around 80–90% accuracy.`]}),`\n`,_jsx(_components.p,{children:_jsx(_components.img,{src:`https://files.pcbcupid.com/Documentation/Boards/Examples/AI/Edge_impulse/Edge_impulse_6-.avif`,alt:`Train the model`})}),`\n`,_jsx(Tip,{children:_jsx(_components.p,{children:`If accuracy is low, collect more data or be more consistent with your gestures.`})}),`\n`,_jsx(Heading,{level:`3`,id:`step-7-export-as-code`,children:`Step 7: Export as Code`}),`\n`,_jsxs(_components.p,{children:[`Go to `,_jsx(_components.strong,{children:`Deployment`}),`, select `,_jsx(_components.strong,{children:`Arduino Library`}),`, and download the ZIP file. This is your AI model exported as standard C++ code.`]}),`\n`,_jsx(_components.p,{children:_jsx(_components.img,{src:`https://files.pcbcupid.com/Documentation/Boards/Examples/AI/Edge_impulse/Edge_impulse_7-.avif`,alt:`Export as code`})}),`\n`,_jsx(Heading,{level:`3`,id:`step-8-upload-to-esp32`,children:`Step 8: Upload to ESP32`}),`\n`,_jsxs(_components.ol,{children:[`\n`,_jsx(_components.li,{children:`Extract the ZIP file.`}),`\n`,_jsxs(_components.li,{children:[`Open Arduino IDE and go to `,_jsx(_components.strong,{children:`File → Examples → [Your Project Name] → ESP32 → ESP32 Fusion`}),`.`]}),`\n`,_jsxs(_components.li,{children:[`Install the ESP32 board package, wire up your ESP32 + IMU sensor, select the right board and COM port, then click `,_jsx(_components.strong,{children:`Upload`}),`.`]}),`\n`]}),`\n`,`\n`,_jsx(_components.p,{children:_jsx(_components.img,{src:`https://files.pcbcupid.com/Documentation/Boards/Examples/AI/Edge_impulse/Edge_impulse_8-.avif`,alt:`Upload to ESP32`})}),`\n`,_jsx(Heading,{level:`3`,id:`step-9-test-your-gestures`,children:`Step 9: Test Your Gestures`}),`\n`,_jsxs(_components.p,{children:[`Open the `,_jsx(_components.strong,{children:`Serial Monitor`}),` and perform your gestures. You will see real-time predictions like `,_jsx(_components.code,{children:`\"Gesture: up-down\"`}),`. It runs fully offline on the ESP32!`]}),`\n`,_jsx(_components.p,{children:_jsx(_components.img,{src:`https://files.pcbcupid.com/Documentation/Boards/Examples/AI/Edge_impulse/Edge_impulse_9-.avif`,alt:`Test Your Gestures`})}),`\n`,_jsx(_components.p,{children:`Have fun with your mini AI Assistant!`})]})}function MDXContent(props={}){const{wrapper:MDXLayout}={..._provideComponents(),...props.components};return MDXLayout?_jsx(MDXLayout,{...props,children:_jsx(_createMdxContent,{...props})}):_createMdxContent(props)}return{default:MDXContent};function _missingMdxReference(id,component){throw new Error(`Expected `+(component?`component`:`object`)+\" `\"+id+\"` to be defined: you likely forgot to import, pass, or provide it.\")}","frontmatter":{},"scope":{"config":{},"pageMetadata":{"description":"Train and deploy a gesture recognition model on ESP32 boards using Edge Impulse, covering data collection, model training, and on-device inference.","title":"Edge Impulse Gesture Recognition","sidebarTitle":"Edge Impulse","href":"/guides/ai/edge-impulse"}}},"mdxSourceWithNoJs":null},"mdxExtracts":{"tableOfContents":[{"title":"Edge Impulse Gesture Recognition","slug":"edge-impulse-gesture-recognition","depth":1,"children":[]},{"title":"How it Works? (The Simple Version)","slug":"how-it-works-the-simple-version","depth":2,"children":[]},{"title":"What You Need","slug":"what-you-need","depth":2,"children":[{"title":"Hardware Required","slug":"hardware-required","depth":3,"children":[]},{"title":"Software","slug":"software","depth":3,"children":[]}]},{"title":"Software Setup","slug":"software-setup","depth":2,"children":[{"title":"Step 1: Create a Project","slug":"step-1-create-a-project","depth":3,"children":[]},{"title":"Step 2: Connect Your Phone","slug":"step-2-connect-your-phone","depth":3,"children":[]},{"title":"Step 3: Collect Data","slug":"step-3-collect-data","depth":3,"children":[]},{"title":"Step 4: Design the Impulse","slug":"step-4-design-the-impulse","depth":3,"children":[]},{"title":"Step 5: Check Accuracy","slug":"step-5-check-accuracy","depth":3,"children":[]},{"title":"Step 6: Train the Model","slug":"step-6-train-the-model","depth":3,"children":[]},{"title":"Step 7: Export as Code","slug":"step-7-export-as-code","depth":3,"children":[]},{"title":"Step 8: Upload to ESP32","slug":"step-8-upload-to-esp32","depth":3,"children":[]},{"title":"Step 9: Test Your Gestures","slug":"step-9-test-your-gestures","depth":3,"children":[]}]}],"codeExamples":{}},"jsLinks":[],"subdomain":"pcbcupid-bae3761c","siteName":"PCB Cupid","title":"Edge Impulse Gesture Recognition - PCB Cupid","navMaps":{"firstHrefInVersion":{},"firstHrefInLanguage":{}},"lastModified":"2026-05-21T11:02:46.410Z","originalFileLocation":"guides/ai/edge-impulse.mdx"},"headHtml":"\u003cscript data-mint-head>(function(){var d=document.documentElement,p=null;if(!p){try{p=localStorage.getItem(\"isDarkMode\")}catch(e){}if(p==='true')p='dark';else if(p==='false')p='light';if(p!=='light'\u0026\u0026p!=='dark'\u0026\u0026p!=='system')p=\"system\"}var r=p==='system'?(matchMedia(\"(prefers-color-scheme: dark)\").matches?'dark':'light'):p;d.classList.remove(r==='dark'?'light':'dark');d.classList.add(r);d.setAttribute(\"data-theme-preference\",p)})();\u003c/script>\u003cmeta data-mint-head name=\"description\" content=\"Train and deploy a gesture recognition model on ESP32 boards using Edge Impulse, covering data collection, model training, and on-device inference.\">\u003cmeta data-mint-head name=\"application-name\" content=\"PCB Cupid\">\u003cmeta data-mint-head name=\"generator\" content=\"Mintlify\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/pcbcupid-bae3761c/TFd0Eu1csuxrLpjH/_generated/favicon/android-chrome-192x192.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"apple-touch-icon\" type=\"image/png\" sizes=\"180x180\" href=\"/mintlify-assets/_mintlify/favicons/pcbcupid-bae3761c/TFd0Eu1csuxrLpjH/_generated/favicon/apple-touch-icon.png\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/pcbcupid-bae3761c/TFd0Eu1csuxrLpjH/_generated/favicon/favicon-16x16.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/pcbcupid-bae3761c/TFd0Eu1csuxrLpjH/_generated/favicon/favicon-32x32.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/pcbcupid-bae3761c/TFd0Eu1csuxrLpjH/_generated/favicon/favicon.ico\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/pcbcupid-bae3761c/TFd0Eu1csuxrLpjH/_generated/favicon-dark/android-chrome-192x192.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/pcbcupid-bae3761c/TFd0Eu1csuxrLpjH/_generated/favicon-dark/favicon-16x16.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/pcbcupid-bae3761c/TFd0Eu1csuxrLpjH/_generated/favicon-dark/favicon-32x32.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/pcbcupid-bae3761c/TFd0Eu1csuxrLpjH/_generated/favicon-dark/favicon.ico\" media=\"(prefers-color-scheme: dark)\">\u003cmeta data-mint-head property=\"og:title\" content=\"Edge Impulse Gesture Recognition - PCB Cupid\">\u003cmeta data-mint-head property=\"og:description\" content=\"Train and deploy a gesture recognition model on ESP32 boards using Edge Impulse, covering data collection, model training, and on-device inference.\">\u003cmeta data-mint-head property=\"og:site_name\" content=\"PCB Cupid\">\u003cmeta data-mint-head property=\"og:url\" content=\"https://learn.pcbcupid.com/guides/ai/edge-impulse\">\u003cmeta data-mint-head property=\"og:type\" content=\"website\">\u003cmeta data-mint-head property=\"og:image\" content=\"https://pcbcupid-bae3761c.mintlify.site/_mintlify/api/og/v2?division=AI\u0026amp;title=Edge+Impulse+Gesture+Recognition\u0026amp;description=Train+and+deploy+a+gesture+recognition+model+on+ESP32+boards+using+Edge+Impulse%2C+covering+data+collection%2C+model+training%2C+and+on-device+inference.\u0026amp;theme=2c7e3818cca0f9e7f4434aa9\u0026amp;signature=dbcbccfefaa7a3888692d721b27acd0f9cecbf7326fdd4026dd96558759c350a\">\u003cmeta data-mint-head property=\"og:image:width\" content=\"1200\">\u003cmeta data-mint-head property=\"og:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"twitter:card\" content=\"summary_large_image\">\u003cmeta data-mint-head name=\"twitter:title\" content=\"Edge Impulse Gesture Recognition - PCB Cupid\">\u003cmeta data-mint-head name=\"twitter:description\" content=\"Train and deploy a gesture recognition model on ESP32 boards using Edge Impulse, covering data collection, model training, and on-device inference.\">\u003cmeta data-mint-head name=\"twitter:image\" content=\"https://pcbcupid-bae3761c.mintlify.site/_mintlify/api/og/v2?division=AI\u0026amp;title=Edge+Impulse+Gesture+Recognition\u0026amp;description=Train+and+deploy+a+gesture+recognition+model+on+ESP32+boards+using+Edge+Impulse%2C+covering+data+collection%2C+model+training%2C+and+on-device+inference.\u0026amp;theme=2c7e3818cca0f9e7f4434aa9\u0026amp;signature=dbcbccfefaa7a3888692d721b27acd0f9cecbf7326fdd4026dd96558759c350a\">\u003cmeta data-mint-head name=\"twitter:image:width\" content=\"1200\">\u003cmeta data-mint-head name=\"twitter:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"msapplication-config\" content=\"/mintlify-assets/_mintlify/favicons/pcbcupid-bae3761c/TFd0Eu1csuxrLpjH/_generated/favicon/browserconfig.xml\">\u003cmeta data-mint-head name=\"apple-mobile-web-app-title\" content=\"PCB Cupid\">\u003cmeta data-mint-head name=\"msapplication-TileColor\" content=\"#0D9373\">\u003clink data-mint-head rel=\"canonical\" href=\"https://learn.pcbcupid.com/guides/ai/edge-impulse\">\u003clink data-mint-head rel=\"alternate\" type=\"application/xml\" href=\"/sitemap.xml\">\u003clink data-mint-head rel=\"alternate\" type=\"text/markdown\" href=\"/guides/ai/edge-impulse.md\">\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@graph\":[{\"@type\":\"Organization\",\"@id\":\"https://learn.pcbcupid.com/#organization\",\"name\":\"PCB Cupid\",\"url\":\"https://learn.pcbcupid.com\"},{\"@type\":\"WebSite\",\"@id\":\"https://learn.pcbcupid.com#website\",\"name\":\"PCB Cupid\",\"url\":\"https://learn.pcbcupid.com\",\"publisher\":{\"@id\":\"https://learn.pcbcupid.com/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https://learn.pcbcupid.com/guides/ai/edge-impulse#webpage\",\"url\":\"https://learn.pcbcupid.com/guides/ai/edge-impulse\",\"name\":\"Edge Impulse Gesture Recognition\",\"description\":\"Train and deploy a gesture recognition model on ESP32 boards using Edge Impulse, covering data collection, model training, and on-device inference.\",\"dateModified\":\"2026-05-21T11:02:46.410Z\",\"isPartOf\":{\"@id\":\"https://learn.pcbcupid.com#website\"},\"breadcrumb\":{\"@id\":\"https://learn.pcbcupid.com/guides/ai/edge-impulse#breadcrumb\"}},{\"@type\":\"BreadcrumbList\",\"@id\":\"https://learn.pcbcupid.com/guides/ai/edge-impulse#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"AI\",\"item\":\"https://learn.pcbcupid.com/guides/ai/esp32-c3-voice-chatbot\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Edge Impulse Gesture Recognition\",\"item\":\"https://learn.pcbcupid.com/guides/ai/edge-impulse\"}]},{\"@type\":[\"Article\",\"TechArticle\"],\"@id\":\"https://learn.pcbcupid.com/guides/ai/edge-impulse#article\",\"headline\":\"Edge Impulse Gesture Recognition\",\"name\":\"Edge Impulse Gesture Recognition\",\"description\":\"Train and deploy a gesture recognition model on ESP32 boards using Edge Impulse, covering data collection, model training, and on-device inference.\",\"url\":\"https://learn.pcbcupid.com/guides/ai/edge-impulse\",\"mainEntityOfPage\":{\"@id\":\"https://learn.pcbcupid.com/guides/ai/edge-impulse#webpage\"},\"dateModified\":\"2026-05-21T11:02:46.410Z\",\"publisher\":{\"@id\":\"https://learn.pcbcupid.com/#organization\"},\"isPartOf\":{\"@id\":\"https://learn.pcbcupid.com#website\"}}]}\u003c/script>\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@type\":\"WebSite\",\"name\":\"PCB Cupid\",\"publisher\":{\"@type\":\"Organization\",\"name\":\"PCB Cupid\"},\"provider\":{\"@type\":\"Organization\",\"name\":\"Mintlify\",\"url\":\"https://mintlify.com\"}}\u003c/script>","agentPointerHref":"/guides/ai/edge-impulse.md","siteName":"PCB Cupid","nav":{"global":null,"tabs":[{"tab":"Documentation","pages":[{"title":"Documentation","href":""}]},{"tab":"Examples","pages":[{"group":"Basic","pages":[{"title":"Blink LED","sidebarTitle":"Blink LED","href":"/guides/arduino-ide-blink-led"},{"title":"Analog Input and Output","sidebarTitle":"Reading Analog Input","href":"/guides/reading-analoginput"},{"title":"Battery Voltage Measurement","sidebarTitle":"Battery Measurement","href":"/guides/battery-measurement"},{"title":"I2C Scanner","sidebarTitle":"I2C Scanner","href":"/guides/i2c-scan-test"},{"title":"BH1750 Adafruit Sensor","sidebarTitle":"BH1750 Sensor","href":"/guides/bh1750adafruit-compatibility"},{"title":"Parallel LCD Display","sidebarTitle":"Parallel LCD","href":"/guides/lcd"},{"title":"I2C LCD Display","sidebarTitle":"I2C LCD","href":"/guides/lcd-i2c"},{"title":"Rotary Encoder with Glyph ESP32-C6","sidebarTitle":"Rotary Encoder","href":"/guides/rotor-encoder-with-glyph-c6"},{"title":"Servo Motor Control with Glyph C6","sidebarTitle":"Servo Motor","href":"/guides/servo-motor-with-glyph-c6"},{"title":"Stepper Motor","sidebarTitle":"Stepper Motor","href":"/guides/stepper-motor-with-drv8833"},{"title":"OpenWeatherMap REST API","sidebarTitle":"REST API Weather","href":"/guides/temperature-monitoring-using-glyph"},{"title":"OLED Display Test","sidebarTitle":"OLED Display","href":"/guides/display-test"},{"title":"REST API Weather on SH1106 OLED","sidebarTitle":"REST API Weather with OLED","href":"/guides/temperaturemonitoring-glyph+sh1106oled"},{"title":"DHT Sensor One-Wire Communication","sidebarTitle":"DHT Sensor One-Wire","href":"/guides/dht-onewire-communication"},{"title":"Unipolar Stepper Motor (28BYJ-48)","sidebarTitle":"Unipolar Stepper Motor","href":"/guides/unipolar-stepper-motor"}]},{"group":"Kits","pages":[{"title":"Beginner Kit with GLYPH-C6","sidebarTitle":"Beginner Kit","href":"/guides/kits/beginner-kit"},{"title":"GLYPH Voice Kit","sidebarTitle":"GLYPH Voice Kit","href":"/guides/kits/glyph-voice"},{"title":"GLYPH MIDI Controller Kit","sidebarTitle":"GLYPH MIDI Controller","href":"/guides/kits/glyph-midi-controller"},{"title":"GLYPH Tank Kit","sidebarTitle":"GLYPH Tank Kit","href":"/guides/kits/glyph-tank"}]},{"group":"AI","pages":[{"title":"ESP32-C3 Voice Chatbot","sidebarTitle":"Voice Chatbot","href":"/guides/ai/esp32-c3-voice-chatbot"},{"description":"Build the Z-Claw robotic gripper that uses on-device AI and computer vision on ESP32 to detect, classify, and pick up objects autonomously.","title":"Z-Claw AI","sidebarTitle":"Z-Claw AI","href":"/guides/ai/z-claw"},{"title":"Edge Impulse Gesture Recognition","sidebarTitle":"Edge Impulse","href":"/guides/ai/edge-impulse"}]},{"group":"Basic Sensors","pages":[{"description":"Connect the HC-SR04 ultrasonic distance sensor to the Glyph ESP32-C6 board, send a trigger pulse, and measure distance using the echo response.","title":"HC-SR04 Ultrasonic Sensor","sidebarTitle":"Ultrasonic Sensor","href":"/guides/basic-sensors/ultrasonic-sensor"},{"title":"Flame Sensor Test","sidebarTitle":"Flame Sensor","href":"/guides/basic-sensors/flame-sensor"},{"title":"IR Sensor","sidebarTitle":"IR Sensor","href":"/guides/basic-sensors/infrared-sensor"},{"title":"LDR Light Sensor","sidebarTitle":"LDR Light Sensor","href":"/guides/basic-sensors/ldr"},{"title":"MQ2 Gas Sensor","sidebarTitle":"MQ2 Gas Sensor","href":"/guides/basic-sensors/mq2-sensor"},{"title":"Touch Sensor (TTP223)","sidebarTitle":"Touch Sensor","href":"/guides/basic-sensors/touch-sensor"}]},{"group":"Bluetooth","pages":[{"title":"BLE Server Demo","sidebarTitle":"BLE Server","href":"/guides/bluetooth/bluetoothglyph"}]},{"group":"WiFi","pages":[{"title":"Control a Dual Relay over Wi-Fi","sidebarTitle":"Wi-Fi Dual Relay","href":"/guides/wifi/local-webserver-to-control-relay"},{"title":"Create a Wi-Fi Access Point on Glyph","sidebarTitle":"Wi-Fi Access Point","href":"/guides/wifi/wifiaccess-point"}]},{"group":"Zigbee","pages":[{"title":"Arduino Zigbee Blink: C6 to H2","sidebarTitle":"Zigbee Blink","href":"/guides/zigbee/arduino-zigbee-blink"}]}]},{"tab":"PCB Design","pages":[{"title":"PCB Design","href":"/pcb-design/design/kicad/introduction-on-kicad"}]}]},"basePath":"","title":"Edge Impulse Gesture Recognition - PCB Cupid","deploymentId":"dpl_HhUetB7eHHDAmK9T1Teip38TgFx9","buildId":"dpl_HhUetB7eHHDAmK9T1Teip38TgFx9","dynamics":["a74be98ba7"],"chunks":["zoom-image-lightbox-DQG3o8Eu.js","lightbox-handle-r17bVUz3.js"]}