For audiovisual applications, the ultimate criteria has been the human perception, assessed in well calibrated subjective testing, which become objective criteria if performed with the right methodology.
What needs to be done if the beneficiaries of the coding, transmission, retrieval, rendering are not human, but machines performing actions?
The scene is set in more details in this presentation:
Presentation Machine Perception criteria added to Human Perception criter...
What is your view, how do you address such a matter?
What would you recommend?
Any significant publications in that domain?
Perception is the process of acquiring, interpreting, selecting, and organizing sensory information. ... In AI, the study on perception is mostly focused on the reproduction of human perception, especially on the perception of aural and visual signals.
Machine perception is the capability of a computer system to interpret data in a manner that is similar to the way humans use their senses to relate to the world around them. The basic method that the computers take in and respond to their environment is through the attached hardware.
Relevante a pesquisa. Acredito que toda IA sobre a percepção deve ser focada na percepção humana audiovisual e princípios éticos.
- Badges
- Science topic
- Similar topics
- Automotive Engineering
- Machines