Description:
This subtopic focuses on information technology innovations that enhance the acquisition, processing, interpretation and use of images or video. This includes both innovations in human perception and use of images or video, and innovations in machine vision (e.g., improved algorithms or hardware). The terms "image" and "video" should be interpreted in their broadest sense – image or video simply refers to static or time-varying data (respectively) that are representative of certain properties of the subject and that may be acquired optically or via ultrasound, X-ray, MRI, PET, or any other observational measurement technique.
Applications are many and varied, ranging from cell-phone based 3D modeling to medical image processing for improved diagnostic accuracy and enhancements for robotic manufacturing systems. Deployment platforms may range from mobile devices (cell phones and tablets) to industrial settings (manufacturing plants).
Examples of relevant technical fields include (but are not limited to): automated image/video indexing and retrieval; object recognition; facial recognition; recognition of human actions and behavior (e.g., in video surveillance applications); automated video categorization; video summarization; generation and manipulation of 3D models; image/video enhancement; image/video feature extraction and identification; pattern recognition.
Many innovations in image and video processing rely on underlying methods developed more broadly in the field of artificial intelligence. Innovations employing artificial intelligence technologies should be submitted to this subtopic if they are primarily aimed at image or video based applications.
