Region-of-interest extraction for video telephony

摘要

The disclosure is directed to techniques for region-of-interest (ROI) processing for video telephony (VT) applications. According to the disclosed techniques, a recipient device defines ROI information for video information transmitted by a sender device, i.e., far-end video information. The recipient device transmits the ROI information to the sender device. Using the ROI information transmitted by the recipient device, the sender device applies preferential encoding to an ROI within a video scene. ROI extraction may be applied to process a user description of a region of interest (ROI) to generate information specifying the ROI based on the description. The user description may be textual, graphical, or speech-based. An extraction module applies appropriate processing to generated the ROI information from the user description. The extraction module may locally reside with a video communication device, or reside in a distinct intermediate server configured for ROI extraction.

主权项

1. A method comprising:
receiving, from a local user of a local device, a first description of a first region of interest (ROI) within near-end video that is to be encoded by the local device, wherein the first description defines the first ROI with respect to the near-end video to be encoded by the local device; receiving, from a remote user of a remote device, a second description of a second ROI within the near-end video that is to be encoded by the local device, wherein the second description defines the second ROI with respect to the near-end video to be encoded by the local device; determining processing resources of the local device; selecting either the first ROI or the second ROI based on the determined processing resources of the local device; generating information specifying the selected ROI in the near-end video based on the corresponding description of the selected ROI; encoding the near-end video on the local device based on the information specifying the selected ROI to enhance image quality of the selected ROI relative to non-ROI areas of the near-end video; and transmitting the encoded near-end video and the information specifying the selected ROI from the local device to the remote device.