Showing posts with label visual search. Show all posts
Showing posts with label visual search. Show all posts

Wednesday, July 27, 2011

MPEG news: a report from the 97th meeting, Torino, Italy

The 97th MPEG meeting in Torino brought a few interesting news which I'd like to report here briefly. Of course, as usual, there is the official press release, however, I'd like to report on some interesting topics as follows:
  • MPEG Unified Speech and Audio Coding (USAC) reached FDIS status
  • Call for Proposals: Compact Descriptors for Visual Search (CDVS)
  • Call for Proposals: Internet Video Coding (IVC)
  • DIS on MPEG Dynamic Adaptive Streaming over HTTP (DASH)
MPEG Unified Speech and Audio Coding (USAC) reached FDIS status

ISO/IEC 23003-3 aka Unified Speech and Audio Coding (USAC) reached FDIS status and soon will be an International Standard. The FDIS itself won't be publicly available but the Unified Speech and Audio Coding Verification Test Report in September 2011 (most likely here). 

Call for Proposals: Compact Descriptors for Visual Search (CDVS)

I reported previously about that and here comes the final CfP including the evaluation framework.

MPEG is planning standardizing technologies that will enable efficient and interoperable design of visual search applications. In particular we are seeking technologies for visual content matching in images or video. Visual content matching includes matching of views of objects, landmarks, and printed documents that is robust to partial occlusions as well as changes in vantage point, camera parameters, and lighting conditions.

There are a number of component technologies that are useful for visual search, including format of visual descriptors, descriptor extraction process, as well as indexing, and matching algorithms. As a minimum, the format of descriptors as well as parts of their extraction process should be defined to ensure interoperability.

It is envisioned that a standard for compact descriptors will:
  • ensure interoperability of visual search applications and databases, 
  • enable high level of performance of implementations conformant to the standard,
  • simplify design of descriptor extraction and matching for visual search applications, 
  • enable hardware support for descriptor extraction and matching in mobile devices,
  • reduce load on wireless networks carrying visual search-related information.
It is envisioned that such standard will provide a complementary tool to the suite of existing MPEG standards, such as MPEG-7 Visual Descriptors. To build full visual search application this standard may be used jointly with other existing standards, such as MPEG Query Format, HTTP, XML, JPEG, JPSec, and JPSearch.

The Call for Proposals and the Evaluation Framework is publicly available. From a research perspective, it would be interesting to see how technologies submitted as an answer to the CfP compete with existing approaches and applications/services.

In this context, it is probably worth looking at IEEE Multimedia Jul.-Sep. 2011 issue which is dedicated to visual content: identification and search including an overview about this new MPEG standard.

Call for Proposals: Internet Video Coding (IVC)

I reported previously about that and the final CfP for Internet Video Coding Technologies is available here. The requirements reveal some interesting issues the call is about:
  • Real-time communications, video chat, video conferencing,
  • Mobile streaming, broadcast and communications,
  • Mobile devices and Internet connected embedded devices 
  • Internet broadcast streaming, downloads
  • Content sharing.
Requirements fall into the following major categories:
  • IPR requirements
  • Technical requirements
  • Implementation complexity requirements 
Clearly, this work item has an optimization towards IPR but others are not excluded. In particular,
It is anticipated that any patent declaration associated with the Baseline Profile of this standard will indicate that the patent owner is prepared to grant a free of charge license to an unrestricted number of applicants on a worldwide, non-discriminatory basis and under other reasonable terms and conditions to make, use, and sell implementations of the Baseline Profile of this standard in accordance with the ITU-T/ITU-R/ISO/IEC Common Patent Policy. 

MPEG Dynamic Adaptive Streaming over HTTP (MPEG-DASH)

For all DASH enthusiast, the latest - and probably almost final - version of DASH-related standards can be found here. Please note that DASH has been reorganized into MPEG-DASH referred to as ISO/IEC DIS 23009-1.2, Part 1: Media presentation description and segment formats. Additionally, you might be interested in the following draft:
  • ISO/IEC 14496-12:2008/DAM 3, Part 12: ISO base media file format, AMENDMENT 3: DASH support and RTP reception hint track processing
  • ISO/IEC FDIS 23001-7, Part 7: Common encryption format for ISO base media file format
All these DASH-related documents are publicly available here. In terms of implementation, the interested reader might check out the ITEC-DASH VLC-based implementation and GPAC (which provides basic support for DASH) respectively.

Further information you may find at the MPEG Web site, specifically under the hot news section and the press release. Working documents of any MPEG standard so far can be found here. If you want to join any of these activities, the list of Ad-hoc Groups (AhG) is available here (soon also here) including the information how to join their reflectors.

Friday, February 11, 2011

MPEG envisages royalty-free MPEG video coding standard

Daegu, KR – The 95th MPEG meeting was held in Daegu, Korea from the 24th to the 28th of January 2011.
--MPEG press release also available here.

Highlights of the 95th Meeting

MPEG anticipates March 2011 CfP for Type-1 Video Coding Standard
MPEG has been producing standards that provide industry with the best video compression technologies. In recognition of the growing importance that the Internet plays in the generation and consumption of video content, MPEG intends to develop a new video compression standard in line with the expected usage models of the Internet. The new standard is intended to achieve substantially better compression performance than that offered by MPEG-2 and possibly comparable to that offered by the AVC Baseline Profile. MPEG will issue a call for proposals on video compression technology at the end of its upcoming meeting in March 2011 that is expected to lead to a standard falling under ISO/IEC “Type-1 licensing”, i.e. intended to be “royalty free”.

MPEG moves toward a visual search standard by issuing Draft Call for Proposals
In its latest step toward creating a standard for efficient and interoperable designs of visual search applications, MPEG has issued a draft Call for Proposals at its 95th meeting. Like a barcode reader, but using regular images instead of barcodes, visual search enables the retrieval of related information from databases for tourists, simplified shopping, mobile augmented reality, and other applications.

Specifically, the call seeks technologies that deliver robust matching of images of objects, such as landmarks and text-based documents, that may be partially occluded or captured from various vantage points, and with different camera parameters, or lighting conditions. The underlying component technologies that are expected to be addressed by the standard include the format of the visual descriptors, and parts of the descriptor extraction process needed to ensure interoperability. Other component technologies, such as indexing and matching algorithms, may also be incorporated into the new standard.

Further details are outlined in the text of the call available at http://mpeg.chiariglione.org/hot_news.htm. The Final Call for Proposals will be issued at the 96th MPEG meeting in March 2011 with responses due in October 2011.

MPEG targets a new phase of 3D video coding standards
A Draft Call for Proposals on 3D Video Coding Technology has also been issued by MPEG at its 95th meeting. This call invites technology submissions providing efficient compression of 3D video and high quality view reconstruction that goes beyond the capabilities of existing standards. MPEG has already delivered 3D compression formats to the market, including MVC and frame-compatible stereoscopic formats, which are being deployed by industry for packaged media and broadcast services. However, the market needs are expected to evolve and new types of 3D displays and services will be offered. With this call, MPEG embarks on a new phase of 3D standardization that anticipates these future needs. The next-generation of 3D standards will define the 3D data format and associated compression technology to facilitate the generation of multiview output to enable both advanced stereoscopic display processing and improved support for auto-stereoscopic displays. Further details are outlined in MPEG's Vision on 3D Video (http://mpeg.chiariglione.org/visions/3dv/index.htm). The Final Call for Proposals will be issued at the 96th MPEG meeting in March 2011 with responses due in September 2011.

Amendment to MPEG-2 systems is finalized at 95th meeting
MPEG is continuously improving the popular MPEG-2 Transport Stream (TS) standard (ISO/IEC 13818-1), one of its most widely accepted standards for broadcast industries. At its 95th meeting, MPEG has finalized a new amendment to support recently developed video coding standards, Advanced Video Coding (AVC) and Multiview Video Coding (MVC), in MPEG-2 TS. This amendment extends the AVC video descriptor to signal the presence of a frame packing arrangement in an associated supplemental enhancement information message for the underlying AVC video stream component. The new amendment also adds signaling of an operating point descriptor of MVC which enables transmission systems to convey the relevant operating points that can be used by receiving devices.

In a related project, MPEG has also started a new amendment to signal stereoscopic video services carried in MPEG-2 TS. This amendment will support not only frame compatible video services but also service compatible video services which will allow implementation of backward compatible stereoscopic video services in HDTV systems.

MPEG hosts MPEG-V awareness event
At its 95th meeting, MPEG hosted the MPEG-V Awareness Event 2011, at which the full range of MPEG-V technologies, including several products and applications employing the standard, were showcased. These technologies cover applications for multi-sensorial user experience in the home environment, control of virtual worlds by real signals, motion capture systems and real-time avatar animation, multi-platform streaming for virtual worlds and mixed reality games. The workshop presentations are available at http://wg11.sc29.org/mpeg-v.


A hot standard moves fast
MPEG has approved the promotion of Dynamic Adaptive Streaming over HTTP (DASH) to Draft International Standard (DIS) status. The draft is available from the Hot News page of http://mpeg.chiariglione.org.

Responding to a Call – How to Contact MPEG
The text and details related to the Calls mentioned above (together with other current Calls) are in the Hot News section, http://www.chiariglione.org/mpeg/hot_news.htm. These documents include information on how to respond to the Calls.

Communicating the large and sometimes complex array of technologies that the MPEG Committee has developed is not a simple task. Experts, past and present, have contributed a series of tutorials and vision documents that explain each of these standards individually. The repository is growing with each meeting, but if something of interest cannot be found, do not hesitate to request it. You can start your MPEG adventure at: http://mpeg.chiariglione.org/technologies.htm.

Further Information

Future MPEG meetings are planned as follows:

  • No. 96, Geneva, CH, 21-25 March, 2011
  • No. 97, Torino, IT, 18-22 July, 2011
  • No. 98, Geneva, CH 28 November – 2 December, 2011
  • No. 99, San Jose, USA 6-10 February, 2012

For further information about MPEG, please contact:

Dr. Leonardo Chiariglione (Convener of MPEG, Italy)
Via Borgionera, 103
10040 Villar Dora (TO), Italy
Tel: +39 011 935 04 61
leonardo@chiariglione.org

This press release and other MPEG-related information can be found on the MPEG homepage:
http://mpeg.chiariglione.org/

The MPEG homepage also has links to other MPEG pages which are maintained by the MPEG subgroups. It also contains links to public documents that are freely available for download by those who are not MPEG members. Journalists that wish to receive MPEG Press Releases by email should contact Dr. Arianne T. Hinds at arianne.hinds@infoprint.com.