Merge pull request #175286 from jfilcik/patch-4

Drafting scenario focused update to the Spatial Analysis intro

Author: Court72

articles/cognitive-services/Computer-vision/intro-to-spatial-analysis-public-preview.md

@@ -15,7 +15,7 @@ ms.custom: contperf-fy22q2
 
 # What is Spatial Analysis?
 
-Spatial Analysis is an AI service that helps organizations maximize the value of their physical spaces by understanding people's movements and presence within a given area. It allows you to ingest video from CCTV or surveillance cameras, extract insights from the video streams, and generate events to be used by other systems. With input from a camera stream, the service can do things like count the number of people entering a space or measure compliance with face mask and social distancing guidelines.
+You can use Computer Vision Spatial Analysis to ingest streaming video from cameras, extract insights, and generate events to be used by other systems. The service detects the presence and movements of people in video. It can do things like count the number of people entering a space or measure compliance with face mask and social distancing guidelines. By processing video streams from physical spaces, you are able to learn how people use them and maximize the space's value to your organization. 
 
 <!--This documentation contains the following types of articles:
 * The [quickstarts](./quickstarts-sdk/analyze-image-client-library.md) are step-by-step instructions that let you make calls to the service and get results in a short period of time. 
@@ -24,26 +24,34 @@ Spatial Analysis is an AI service that helps organizations maximize the value of
 * The [tutorials](./tutorials/storage-lab-tutorial.md) are longer guides that show you how to use this service as a component in broader business solutions.-->
 
 ## What it does
+Spatial Analysis ingests video then detects people in the video. After people are detected, the system tracks the people as they move around over time then generates events as people interact with regions of interest. All operations give insights from a single camera's field of view. 
 
-The core operations of Spatial Analysis are built on a system that ingests video, detects people in the video, tracks the people as they move around over time, and generates events as people interact with regions of interest.
+### People counting
+This operation counts the number of people in a specific zone over time using the PersonCount operation. It generates an independent count for each frame processed without attempting to track people across frames. This operation can be used to estimate the number of people in a space or generate an alert when a person appears.
 
-## Spatial Analysis features
+![Spatial Analysis counts the number of people in the cameras field of view](https://user-images.githubusercontent.com/11428131/139924111-58637f2e-f2f6-42d8-8812-ab42fece92b4.gif)
 
-| Feature | Definition |
-|------|------------|
-| **People Detection** | This component answers the question, "Where are the people in this image?" It finds people in an image and passes bounding box coordinates indicating the location of each person to the **People Tracking** component. |
-| **People Tracking** | This component connects the people detections over time as people move around in front of a camera. It uses temporal logic about how people typically move and basic information about the overall appearance of the people. It does not track people across multiple cameras. If a person exits the field of view for longer than approximately one minute and then reenters the view, the system will perceive them as a new person. People Tracking does not uniquely identify individuals across cameras. It does not use facial recognition or gait tracking. |
-| **Face Mask Detection** | This component detects the location of a person's face in the camera's field of view and identifies the presence of a face mask. The AI operation scans images from video; where a face is detected the service provides a bounding box around the face. Using object detection capabilities, it identifies the presence of face masks within the bounding box. Face Mask detection does not involve distinguishing one face from another face, predicting or classifying facial attributes or doing face recognition. |
-| **Region of Interest** | This component is a user-defined zone or line in the input video frame. When a person interacts with this region on the video, the system generates an event. For example, for the **PersonCrossingLine** operation, a line is defined in the video frame. When a person crosses that line, an event is generated. |
-| **Event** | An event is the primary output of Spatial Analysis. Each operation raises a specific event either periodically (like once per minute) or whenever a specific trigger occurs. The event includes information about what occurred in the input video but does not include any images or video. For example, the **PeopleCount** operation can raise an event containing the updated count every time the count of people changes (trigger) or once every minute (periodically). |
+### Entrance Counting
+This feature monitors how long people stay in an area or when they enter through a doorway. This monitoring can be done using the PersonCrossingPolygon or PersonCrossingLine operations. In retail scenarios, these operations can be used to measure wait times for a checkout line or engagement at a display. Also, these operations could measure foot traffic in a lobby or a specific floor in other commercial building scenarios.
+
+![Spatial Analysis measures dwelltime in checkout queue](https://user-images.githubusercontent.com/11428131/137016574-0d180d9b-fb9a-42a9-94b7-fbc0dbc18560.gif)
+
+### Social distancing and facemask detection 
+This feature analyzes how well people follow social distancing requirements in a space. Using the PersonDistance operation, the system automatically calibrates itself as people walk around in the space. Then it identifies when people violate a specific distance threshold (6 ft. or 10 ft.).
+
+![Spatial Analysis visualizes social distance violation events showing lines between people showing the distance](https://user-images.githubusercontent.com/11428131/139924062-b5e10c0f-3cf8-4ff1-bb58-478571c022d7.gif)
+
+Spatial Analysis can also be configured to detect if a person is wearing a protective face covering such as a mask. A mask classifier can be enabled for the PersonCount, PersonCrossingLine, and PersonCrossingPolygon operations by configuring the `ENABLE_FACE_MASK_CLASSIFIER` parameter.
+
+![Spatial Analysis classifies whether people have facemasks in an elevator](https://user-images.githubusercontent.com/11428131/137015842-ce524f52-3ac4-4e42-9067-25d19b395803.png)
 
 ## Get started
 
 Follow the [quickstart](spatial-analysis-container.md) to set up the Spatial Analysis container and begin analyzing video.
 
 ## Responsible use of Spatial Analysis technology
 
-To learn how to use Spatial Analysis technology responsibly, see the [transparency note](/legal/cognitive-services/computer-vision/transparency-note-spatial-analysis?context=%2fazure%2fcognitive-services%2fComputer-vision%2fcontext%2fcontext). Microsoft's transparency notes are intended to help you understand how our AI technology works, the choices system owners can make that influence system performance and behavior, and the importance of thinking about the whole system, including the technology, the people, and the environment.
+To learn how to use Spatial Analysis technology responsibly, see the [transparency note](/legal/cognitive-services/computer-vision/transparency-note-spatial-analysis?context=%2fazure%2fcognitive-services%2fComputer-vision%2fcontext%2fcontext). Microsoft's transparency notes help you understand how our AI technology works and the choices system owners can make that influence system performance and behavior. They focus on the importance of thinking about the whole system including the technology, people, and environment.
 
 ## Next steps