<p style="text-align:center;"><span style="color:hsl(0,0%,100%);font-family:&quot;Segoe UI&quot;, &quot;Segoe UI Web (West European)&quot;, -apple-system, BlinkMacSystemFont, Roboto, &quot;Helvetica Neue&quot;, sans-serif;"><strong>Black Friday Special: Save Up to 35% on Wizart Solutions!</strong></span></p>

thumbnail_404.png

404.png

Oops! There is a mess in your room...

c5f592_bdd304d02a014cf6b41fbdde6ceae5ca_mv2_eae36ae89c.png

Localize and classify objects contained in an image in a single API request.

medium_Image (83).png

small_Image (83).png

thumbnail_Image (83).png

Image (83).png

<span class="brand-color">What is</span> object detection?

Object detection is a subfield of computer vision that involves detecting and identifying objects in an image. The goal of object detection is to accurately locate and classify objects of interest in an image, and it has a wide range of applications.

small_Image (84).png

thumbnail_Image (84).png

Image (84).png

<span class="brand-color">Why</span> use object detection?

The Object Detection API can help you identify the corners and edges of surfaces and obtain their dimensions.

small_Image (85).png

thumbnail_Image (85).png

Image (85).png

How does the localization of the object coordinate work?

Wizart Vision Detection API can return data in two different forms, and they are normally used for different needs.
<br><br>
A bounding box is a rectangular area that is drawn around an object to indicate its spatial location. It is a fundamental tool used in object detection and localization tasks, which enables you to determine the position of an object and, optionally, count the number of objects belonging to a particular class.  
<br><br>
However, for certain tasks, such as wall or floor detection, it is better to use a method based on key points. With this method, the software still localizes the object by connecting points and obtaining a frame around the detected object. But since the resulting border is not rectangular, it is possible to describe more complex shapes, take perspective into account, and determine more accurate values for the object coordinates. Furthermore, this method allows for the determination of coordinates for the invisible parts of the object that may be overlapped by other objects in the scene. Here is an example of what this method <span class="brand-color">looks like</span>:

medium_image 58 (1).png

small_image 58 (1).png

thumbnail_image 58 (1).png

image 58 (1).png

As you can see, some floor coordinates are hidden and overlapped with the sofa and the door.
And here is an example of the <span class="brand-color">API response</span>:

<div class="raw-html-embed"><div class="vision-api__code_example">
   <style>
       .vision-api__code_example {
           background-color: #eee;
           border-radius: 3px;
           font-family: courier, monospace;
           padding: 0 3px;
           height: 400px;
           overflow-y: scroll;
       }
   </style>
   <pre>       <code>
[
   {
       "wall_id": 0,
       "points": [
           [
               0.0,
               -0.32415005564689636
           ],
           [
               0.49296873807907104,
               0.1488862782716751
           ],
           [
               0.0,
               -0.32415005564689636
           ],
           [
               0.49296873807907104,
               0.14888626337051392
           ]
       ],
       "cx": 18.169554471969604,
       "cy": 29.29260683227396
   },
   {
       "wall_id": 1,
       "points": [
           [
               0.49296873807907104,
               0.1488862782716751
           ],
           [
               0.918749988079071,
               0.03399765491485596
           ],
           [
               0.49296873807907104,
               0.14888626337051392
           ],
           [
               0.918749988079071,
               0.03399762511253357
           ]
       ],
       "cx": 88.99655342102051,
       "cy": 33.05871209952924
   },
   {
       "wall_id": 2,
       "points": [
           [
               0.918749988079071,
               0.03399765491485596
           ],
           [
               1.0,
               -0.43728017807006836
           ],
           [
               0.918749988079071,
               0.03399762511253357
           ],
           [
               1.0,
               -0.43728017807006836
           ]
       ],
       "cx": 95.99307060241699,
       "cy": 33.63378419686035
   }
]
       </code>
   </pre>
</div></div><p><br>&nbsp;</p>

thumbnail_Image (86).png

Image (86).png

If you're involved in interior design, construction, or renovation, one of the essential tasks is to calculate the surface area of the interior space, particularly the walls, floor, and ceiling.

left

How to Calculate<br> the Amount of Material<br> Needed via Vision API

thumbnail_Image (87).png

Image (87).png

Vision API is a tool that can truly revolutionize the way manufacturers and retailers overall of the home improvement industry sell their products. This software solution has almost unlimited possibilities for product visualization, including products for the window treatment market.

Wizart Vision API for Roman Shades Visualization

thumbnail_Image (88).png

Image (88).png

How to Build Door Visualizer Using Vision API

Learn more about Vision API technology
With our bespole home improvement industry tools

Segmentation API splits indoor images into surfaces and creates a segmentation mask of the surfaces found in the scene.

thumbnail_Image.png

Image.png

Indoor Scene Semantic Segmentation

Get knowledge about 3D space with reconstruction API

3D Room Layout Reconstruction

Analysis API gives us an estimated camera position and its features. It also detects the type of room being visualized.

How to Calculate the Amount of Material Needed via Vision API

Wizart Vision API for Roman Shades Visualization

How to Build Door Visualizer Using Vision API

How to Calculate
the Amount of Material
Needed via Vision API