New approach to video search utilizes “visual crawling” to find video the same way a casual Web surfer would.
Burlingame, CA-based Truveo has announced the debut of its video search engine. The privately held startup says on its web site that its technology will be an improvement over existing video search products.
Video search has been around for a while, with Yahoo, AOL, and Google all making inroads into indexing video content. Truveo describes how it can do a better job with finding and indexing videos online:
The insight was simple: web video that remains invisible to standard crawlers can be easily identified by a casual web surfer. We felt that if we could build a crawler that could identify the visual characteristics of a typical web application in the same way that a person could, then it would be possible to find and index all of the web video that other crawlers miss. We call this new approach “visual crawling.”
Truveo formed in January 2004, and has been indexing videos and any associated metadata available for them. If that metadata, such as closed-captioning or other info, isn’t available, the crawler tries to “examine the context of the surrounding web application.” The search engine also indexes video feeds that conform to RSS 2.0 or Media RSS enclosures.
The company’s site notes that they will be offering advertising on its site and on partner web sites. Those ads will range from text to full video options; currently, Truveo displays Google ads on its result pages. Also, sites with more than 10,000 video queries per day are eligible to license Truveo’s API, and use that to create custom applications driven by Truveo’s search.
David Utter is a staff writer for Murdok covering technology and business. Email him here.
