<-References        Go to ToC        AI Modules->

1. Technical Specification 2. Reference Software 3. Conformance Testing 4. Performance Assessment

1. Technical Specifications

Technical Specification: Object and Scene Descriptors (MPAI-OSD) V1.5 assumes that implementations will be based on Technical Specification: AI Framework (MPAI-AIF) V3.0 enabling dynamic configuration, initialisation, and control of AI Modules (AIM), including Composite AIMs, in a standard AI Framework (AIF).

MPAI-OSD V1.5 specifies no AI Workflow. The Television Media Analysis AI Workflow (OSD-TMA) of MPAI-OSD V1.4 is specified in this version as a Composite AIM, Television Media Analysis (OSD-TMA), whose metadata is in TelevisionMediaAnalysis.json.

2. Reference Software

As a rule, MPAI provides Reference Software implementing the AI Modules released with the BSD-3-Clause licence and the following disclaimers:

  1. The purpose of the Reference Software is to demonstrate a working Implementation of an AIM, not to provide a ready-to-use product.
  2. MPAI disclaims the suitability of the Software for any other purposes than those of the MPAI-OSD Standard, and does not guarantee that it offers the best performance and that it is secure.
  3. Users shall verify that they have the right to use any third-party software required by this Reference Software, e.g., by accepting the licences from third-party repositories.

2. Conformance Testing

An implementation of an AI Workflow conforms with MPAI-OSD if it accepts as input and produces as output Data and/or Data Objects (Data of a Data Type and its Qualifier) conforming with those specified by MPAI-HMC.

The Conformance of an instance of a Data is to be expressed by a sentence like “Data validates against the Data Type Schema”. This means that:

  • Any Data Sub-Type is as indicated in the Qualifier.
  • The Data Format is indicated by the Qualifier.
  • Any File and/or Stream have the Formats indicated by the Qualifier.
  • Any Attribute of the Data is of the type or validates against the Schema specified in the Qualifier.

The method to Test the Conformance of a Data or Data Object instance is specified in the Data Types chapter.

3. Performance Assessment

Performance is a multidimensional entity because it can have various connotations. Therefore, the Performance Assessment Specification should provide methods to measure how well an AIW performs its function, using a metric that depends on the nature of the function, such as:

  1. Quality: the Performance of a Television Media Analysis AIW can measure how well an AIM identifies the humans in a scene.
  2. Bias: Performance of a Television Media Analysis AIW can measure the quality of face identification in dependence of the types of humans involved.
  3. Legal compliance: the Performance of an AIW can measure the compliance of the AIW to a regulation, e.g., the European AI Act.
  4. Ethical compliance: the Performance Assessment of an AIW can measure the compliance of an AIW to a target ethical standard.

The current MPAI-OSD) V1.5 Standard does not provide AIW Performance Assessment methods.

<-References        Go to ToC        AI Modules->