Skip to main content

MovingAverage

Calculate Moving Avg of Detection Count.

This module provides a pipeline element to calculate the moving avg of the detection count measured across a certain pre-defined window. There is an optional argument to specify the moving average window.

Examples:

REST API:

WIP

Configuration File:

short-from : moving-average, moving-average:<i-wndw>

Moving Avg with default:

source:
- address: https://youtu.be/jY86pXeTOLw
- type: youtube
pipeline:
- person-detection-nano:a:0.3:0.3
- moving-average

Moving Avg with window specified:

source:
- address: https://youtu.be/jY86pXeTOLw
- type: youtube
pipeline:
- person-detection-nano:a:0.3:0.3
- moving-average:10

MovingAverage Objects​

class MovingAverage(Element)

Calculate Moving Avg of Detection Count.

This element calculates moving avg of the detection count measured across a certain pre-defined window.

Attributes:

  • name str - The name of the element.
  • wndw int - The moving average window.

Examples:

Default:

ele = MovingAverage()
ele = MovingAverage(10)

extract_params​

@staticmethod
def extract_params(model_params)

Extract the parameters for this element.

Arguments:

  • model_params List[str] - The parameters for this element.

Returns:

  • wndw int - The moving average window.

Raises:

  • ExtractParameterException - If the parameters are not valid.

Examples:

params = MovingAverage.extract_params(["10"])
ele = MovingAverage(*params)

process​

def process(meta)

Process the bounding boxes.

This is the main function for this element. It will calculate moving avg of the detection count measured across a certain pre-defined window.

Arguments:

  • meta dict - The metadata to process.

Returns:

  • meta dict - The processed metadata.

Examples:

ele = MovingAverage()
meta = ele.process(meta)