MovementBasedSegmenter

MovementBasedSegmenter uses a convolutional neural network to classify objects. MovementBasedSegmenter can detect (i.e locate and classify) multiple objects at a time in the specified watcher shape.
Example usage:
1
import lampix from '@lampix/core';
2
​
3
const watcher = {
4
  name: 'MovementBasedSegmenter',
5
  shape: {
6
    type: 'rectangle',
7
    data: {
8
      posX: 0,
9
      posY: 0,
10
      width: window.innerWidth,
11
      height: window.innerHeight
12
    }
13
  }
14
  params: {
15
    neural_network_name: 'fruits',
16
    filter_circle: { min_radius: 50, max_radius: 150, min_area_ratio: 0.7 },
17
    filter_area: { min_ratio: 3000, max_ratio: 70000 },
18
    filter_thresh: 55
19
  }
20
}
21
​
22
// Remember: .watchers.add always returns an array of registered watchers
23
// of the same length as the number of arguments passed to it
24
lampix.watchers.add(watcher)
25
  .then((listOfWatchers) => console.log(listOfWatchers[0]));
Copied!
See standard watchers for more information MBS.

NeuralNetworkClassifier: Buttons

Counter App

Last modified 3yr ago

Copy link