<-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 ) V1.2 assumes that implementations will be based on Technical Specification: AI Framework (MPAI-AIF) V2.1 enabling dynamic configuration, initialisation, and control of AI Workflows (AIW) composed of interconnected AI Modules (AIM) in a standard AI Framework (AIF).

Table 1 displays the AIW specified by MPAI-OSD V1.1. Click the AIW to access its dedicated page, which includes a its functions, reference model, I/O Data, Functions of AIMs, I/O Data of AIMs, and a table providing links to the AIW-related AIW, AIMs, and JSON metadata.

Table 1 – AIWs of MPAI-OSD V2.0

Name and Specification JSON
OSD-TMA Television Media Analysis X

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 AIW, 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

As Performance is a multidimensional entity because of it various possible connotations, 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 V1.2 Standard does not provide AIW Performance Assessment methods.

<-References      Go to ToC       AI Modules->