Modelplace.AI is an app store for OpenCV compatible AI models

OpenCV open-source computer vision library is used in a wide variety of projects and products, and last year, the community also launched the OpenCV AI Kit (OAK) Myriad X-based hardware solution for computer vision.

However there’s a learning curve to use the library, especially in combination with artificial intelligence models, and it can be challenging and time-consuming to newcomers. So in order to broaden the reach of the solution, OpenCV has now introduced Modelplace.AI, an app store/marketplace for AI models working with the OpenCV library.

The AI model marketplace is a store and try-before-you-buy service for artificial intelligence models, many of which are certified to work with the OpenCV AI Kit.

There are currently over 40 models for detection (e.g. person, pedestrian…), classification, segmentation (e.g. extraction of objects from a scene), pose estimation, people counting, text detection, tracking, and more. Right now all models are free, but developers will be able to add premium models as well to get paid for their work.

The model can be tried directly from your browser, and for example, after signing up to the website, I could upload a photo to try out the “Iris landmark detector pipeline”. The page also shows the results in code form:

-[
 -{
  -"bbox": {
   "x1": 157,
   "y1": 219,
   "x2": 285,
   "y2": 347,
   "score": 1,
   "class_name": "Eye"
  },
  -"keypoints": [
   -{
    "x": 221,
    "y": 277
  },
   -{
    "x": 234,
    "y": 276
  },
  -{
   "x": 220,
   "y": 266
  },
  -{
   "x": 209,
   "y": 279
  },
  -{
   "x": 222,
   "y": 289
  }
...

-"bbox": {

"x1": 157,

"y1": 219,

"x2": 285,

"y2": 347,

"score": 1,

"class_name": "Eye"

-"keypoints": [

"x": 221,

"y": 277

"x": 234,

"y": 276

"x": 220,

"y": 266

"x": 209,

"y": 279

"x": 222,

"y": 289

}

...

If you click on “Original Model” it will take you to the project page, for example, https://github.com/PINTO0309/PINTO_model_zoo/tree/main/049_iris_landmark.

Clicking on “Get Model” would allow you to use the model in the cloud, but some models are not available that way, notably our Iris detector sample. If we try the Tiny YOLO v4 model there are more instructions, and it can be tested both in OAK, your computer, or the cloud, just check for the logo for compatible models.

Jean-Luc Aufranc (CNXSoft)

Jean-Luc started CNX Software in 2010 as a part-time endeavor, before quitting his job as a software engineering manager, and starting to write daily news, and reviews full time later in 2011.