<-AI Workflows      Go to ToC       Data Types->

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

1. Technical Specifications

Table 1 provides the links to the specifications and the JSON syntax of all AIMs specified by Technical Specification: Object and Scene Description (MPAI-OSD) V1.2. All previously specified MPAI-OSD AI-Modules are superseded by those specified by V1.2 but may still be used by explicitly signaling their version. AI Modules in bold are Composite.

Table 1 – Specifications and JSON syntax of AIMs used by MPAI-OSD V1.2

AIMs Name and Specification JSON AIMs Name and Specification JSON
OSD-AVA Audio-Visual Alignment X OSD-VBD Visual Basic Scene Description X
OSD-ABS Audio-Visual Basic Scene Description X OSD-VCD Visual Change Detection X
OSD-AVE Audio-Visual Event Description X OSD-VDI Visual Direction Identification X
OSD-SDX Audio-Visual Scene Demultiplexing X OSD-VII Visual Instance Identification X
OSD-AVS Audio-Visual Scene Description X OSD-VOE Visual Object Extraction X
OSD-SMX Audio-Visual Scene Multiplexing X OSD-VOI Visual Object Identification X
OSD-DVI Direct Visual Identification X OSD-VSD Visual Scene Description X
OSD-TVS Television Splitting X

2. Conformance Testing

An implementation of an AI Module Conforms with this Technical Specification if its input and output Data and/or Data Objects Conform with the Data or Data Objects specified in this Technical Specification. Note that Data Object is defined as the combination of Data of a certain Data Type and its Qualifier.

The Conformance of a Data instance  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.

#3. 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 provide a working Implementation of an AIM, not 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.

Note that at this stage only part of the MPAI-OSD AIMs have a Reference Software Implementation.

4. 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: Performance Assessment measures how well an AIM performs its function, using a metric that depends on the nature of the function, e.g., how well a Visual Change Detection (VCD) AIM can detect the change of a visual scene.
  2. Bias: Performance Assessment measures the preference given by an AIM to certain elements, using a metric that depends on a bias related to certain attributes of the AIM. For instance, a Visual Instance Identification (VII) AIM tends to have a higher correct identification of visual objects that have a certain shape.
  3. Legal compliance: Performance Assessment measures how well an AIM performs its function, using a metric that assesses its accordance with a certain legal standard.
  4. Ethical compliance: the Performance Assessment of an AIM can measure the compliance of an AIM to a target ethical standard.

The current MPAI-PAF V1.3 does not provide AIM Performance Assessment methods.

<-AI Workflows      Go to ToC       Data Types->