透過電腦視覺與人工智慧創造物聯網新價值
•Transferir como PPTX, PDF•
3 gostaram•486 visualizações
目前幾乎所有的物聯網解決方案都是基於感測器(sensor)，然而現實生活中，有絕大部分的與使用者的互動是基於視覺與對話的。 Microsoft 的認知服務與人工智能解決方案，對於物聯網來說，就像是一個大腦，讓物聯網解決方案可以通過人工智能，達到更多的連接，從而創造價值。 這一個場次中，講師將使用Microsoft 的認知服務與人工智能解決方案與物聯網裝置結合，當感知器啟動時，搭配攝影機以及OpenCV 技術擷取環境畫面之後，使用Azure 上開發好的框架判斷目前的場景狀態，並且透過交談式機器人等方式，與使用者進行互動。
Recomendados
Mais conteúdo relacionado
Mais procurados
Mais procurados (20)
Semelhante a 透過電腦視覺與人工智慧創造物聯網新價值
Semelhante a 透過電腦視覺與人工智慧創造物聯網新價值 (20)
Mais de John Chang
Último
Último (20)
透過電腦視覺與人工智慧創造物聯網新價值
- 1. 利用電腦視覺與人工智慧 創造更多物聯網價值 John Chang ( 張書源 ) 資深軟體開發協理 john.chang@microsoft.com Azure 雲的萬物論
- 2. 物聯網架構
- 3. Custom Cloud Gateway Custom Cloud Gateway Field Gateway Device VPN/ExpressRoute OPC, HTTP, CoAP,… Custom Protocols Client SDK IoT Edge AMQP Management app Device registry/Management Monitoring Send commands Client SDK Management app Device registry/Management Monitoring Send commands Client SDK Cloud protocol gateway sample Cloud protocol gateway sample AMQP, MQTT, HTTPS Applications - Companion apps - Dashboards - Controllers - … CoAP, AllJoyn, OPC,… Device Device CoAP, AllJoyn, OPC, … Device Device Device IoT Hub Field Gateway
- 7. Custom Cloud Gateway Custom Cloud Gateway Field Gateway Device VPN/ExpressRoute OPC, HTTP, CoAP,… Custom Protocols Client SDK IoT Edge AMQP Management app Device registry/Management Monitoring Send commands Client SDK Management app Device registry/Management Monitoring Send commands Client SDK Cloud protocol gateway sample Cloud protocol gateway sample AMQP, MQTT, HTTPS Applications - Companion apps - Dashboards - Controllers - … CoAP, AllJoyn, OPC,… Device Device CoAP, AllJoyn, OPC, … Device Device Device IoT Hub Field Gateway Data + AI
- 8. 結合攝影機偵測環境狀態 降低傳感器誤判 降低傳感器數量 容易處理複雜的情境 深度學習讓影像辨識技術更成熟 OpenCV 可在 IoT Edge 篩選影像 Azure 認知服務支援影像分析 可與 Azure 其他服務結合
- 9. Sensor Sensor Sensor Sensor Sensor Blob Queue Azure FunctionOpenCV Computer Vision Rule Engine AzureIoT Device Bot SMS Text Phone Call
- 11. Demo 智慧物聯網範例
- 15. Vision
- 16. 200K celebrities
- 18. JSON: { "language": "en", "orientation": "Up", "regions": [ { "boundingBox": "41,77,918,440", "lines": [ { "boundingBox": "41,77,723,89", "words": [ { "boundingBox": "41,102,225,64", "text": "LIFE" }, { "boundingBox": "356,89,94,62", "text": "IS" }, { "boundingBox": "539,77,225,64", "text": "LIKE" } . . .
- 21. "faceRectangle": {"width": 193, "height": 193, "left": 326, "top": 204} “scores": { "anger": 5.182241e-8, "contempt": 0.0000242813, "disgust": 5.621025e-7, "fear": 0.00115027453, "happiness": 1.06114619e-8, "neutral": 0.003540177, "sadness": 9.30888746e-7, "surprise": 0.9952837}
- 23. "faceRectangle": {"width": 193, "height": 193, "left": 326, "top": 204} … "attributes": { "age": 42, "gender": "male", "headPose": { "roll": "8.2", "yaw": "-37.8", "pitch": "0.0" }}
- 27. Demo 使用 Custom Vision Service 建立智能物聯 網方案
Notas do Editor
- https://kaboompics.com/photo/1780/dogs-behind-metal-bars https://kaboompics.com/page/license-and-faq
- https://kaboompics.com/photo/1780/dogs-behind-metal-bars https://kaboompics.com/page/license-and-faq
- Summary Millions of people worldwide have embraced Uber as a new means of reliable transportation and flexible income. To safeguard against fraud and enhance both driver and rider peace of mind, Uber uses the Face API, part of Microsoft Cognitive Services, to help ensure the driver using the app matches the account on file. The extra verification step is fast, works on all smartphones and in dim light, and scales to more than 1 million driver-partners. By using the Face API, Uber saved months of development work, time it could devote to tailoring the user experience. Challenge Uber sends photos of drivers to riders as soon as their ride is on the way, but occasionally the Uber driver who shows up doesn’t look like the person in the photo that the rider receives. Uber wanted to make sure that the person it had screened and approved was the person behind the wheel. Solution Uber decided to use photo-matching to verify drivers when they signed in to the Uber app. Drivers would periodically take and submit a selfie to verify their identity. Uber used the Microsoft Cognitive Services Face API to build its Real-Time ID Check feature. The Face API supported the ability to compare photos in varying pose, focus, and lighting conditions. Benefits Three-week development time and rapid time-to-market with new driver authentication step Amazing performance, which provides quick authentication without slowing down drivers Very high photo-matching accuracy Scalable to support up to 1 million users https://customers.microsoft.com/en-US/story/uber
- Why choose these APIs? They work, and it’s easy. Easy: The APIs are easy to implement because of the simple REST calls. Being REST APIs, there’s a common way to implement and you can get started with all of them for free simply by going to one place, one website, www.microsoft.com/cognitive. (You don’t have to hunt around to different places.) Flexible: We’ve got a breadth of intelligence and knowledge APIs so developers will be able to find what intelligence feature they need; and importantly, they all work on whatever language, framework, or platform developers choose. So, devs can integrated into their apps—iOS, Android, Windows—using their own tools they know and love (such as python or node.js, etc.). Tested: Tap into an ever-growing collection of powerful AI algorithms developed by experts. Developers can trust the quality and expertise build into each API by experts in their field from Microsoft’s Research organization, Bing, and Azure machine learning and these capabilities are used across many Microsoft first party products such as Cortana, Bing and Skype.
- Do you need an API that gives you actionable information about images used in your app? The Computer Vision API gives you the tools to understand the contents of any image. Create tags identifying objects, beings, or actions present in the image, and then craft coherent sentences to describe it. Whether you want to execute better image search, or you want to create an assistive app for the visually impaired, the Computer Vision API helps get the job done.
- How are you feeling? Can your app tell? With the Emotion API, you can build an app that recognizes emotions according to facial expressions—giving you the capability to provide an amazing, personalized experience. Using facial expressions, this cloud-based API can detect happiness, neutrality, sadness, contempt, anger, disgust, fear, and surprise. The AI understands these emotions based on universal facial expressions, and it functions cross-culturally, so your app will work around the world.
- Detect human faces and compare similar ones, organize people into groups according to visual similarity, and identify previously tagged people in images.
- Intelligent video processing produces stable video output, detects motion, creates intelligent thumbnails, and detects and tracks faces.
- Do you need an API that gives you actionable information about images used in your app? The Computer Vision API gives you the tools to understand the contents of any image. Create tags identifying objects, beings, or actions present in the image, and then craft coherent sentences to describe it. Whether you want to execute better image search, or you want to create an assistive app for the visually impaired, the Computer Vision API helps get the job done.
- Animation set to loop (replace /Build walk in ?) BOT Framework provides everything you need to build and connect intelligent BOTs that interact naturally wherever your users are talking, from text/sms to Skype, Slack, Office 365 mail, Facebook Messenger, Kik and other popular services. BOT Framework consists of three main components: BOT Connector, BOT Builder, and BOT Directory