Method and system for fast detecting static stacking letters in online video stream

Abstract

The invention relates to an image and video processing method and system, in particular to a method and system for rapidly detecting static superimposed text in an online video stream. The static superimposed text detection method utilizes inter-frame correlation information and wavelet domain modeling and other methods, which can effectively remove moving text and background areas, and retain the static superimposed text area. The method can realize the rapid detection of the static superimposed text position in the online video stream. At the same time, an online video stream retrieval system is constructed based on the static superimposed text detection method. In this system, different parameter families are used for fast text detection on each user terminal, and the results are converted into text streams through the OCR control. After each user terminal transmits the text stream to the centralized retrieval server for integration, a multi-time granular retrieval function for each channel and a content-based quick browsing function for each channel can be provided. The present invention can realize the functions of synchronous analysis, indexing, retrieval and browsing of multiple online video streams with multiple qualities without infringing copyright, and does not need to establish special servers for various video streams.

Description

technical field [0001] The invention relates to an image and video processing method and system, in particular to a method and system for quickly detecting static superimposed text in online video streams. Background technique [0002] In the past 10 years, the rapid rise of network media technology has greatly expanded the ways and means for people to receive information. Among the many network media technologies, the development of online video streaming technology is the most eye-catching. In a sense, online video streaming can be understood as a broadcast channel on the Internet. Such as the famous PPLive video broadcasting system, there are hundreds of channels broadcasting at any moment. In order to find out the channel that the user is interested in among the thousands of Internet broadcasting channels, the user urgently needs an effective means to quickly browse and retrieve the content of the channel's current program. However, the current search methods based on ...

AI Technical Summary

Problems solved by technology

[0005] 2. Real-time issues

However, the existing text detection algorithms often require a lot of calculations, making the detection speed far lower than the normal playback speed of the video stream. Using this method to detect text on the online video stream will cause a large number of missed detections, thus Unable to provide a complete program content description

[0006] 3. The number of channels

However, due to the large number and high variability of online video streams, it is impossible to use the method of establishing a separate analysis server for each online video stream for analysis

[0007] 4. Video quality problem

However, in order to achieve real-time indexing of online video streams, a text detection algorithm that can quickly detect static text areas is required. Therefore, the above-mentioned analysis method using complex calculations cannot be directly applied to text detection of online video streams, so that it cannot be used for online video streams. Provide a full text description

[0009] From the above analysis, it can be seen that due to the special nature of online video stream analysis, it is difficult to directly use the existing analysis and retrieval technology for video files.

Images