Automated video-to-text system

Details Automated video-to-text system Automated video-to-text system

2007-04-03

2010-11-16

ahmed, Samir A. (Department: 2624)

Image analysis

Image segmentation

Distinguishing text from other regions

C382S171000, C382S173000, C382S243000, C382S294000, C358S462000

Reexamination Certificate

active

07835578

ABSTRACT:
A method for transforming Video-To-Text is disclosed that automatically generates text descriptions of the content of a video. The present invention first segments an input video sequence according to predefined semantic classes using a Mixture-of-Experts blob segmentation algorithm. The resulting segmentation is coerced into a semantic concept graph and based on domain knowledge and a semantic concept hierarchy. Then, the initial semantic concept graph is summarized and pruned. Finally, according to the summarized semantic concept graph and its changes over time, text and/or speech descriptions are automatically generated using one of the three description schemes: key-frame, key-object and key-change descriptions.

REFERENCES:
patent: 2912674 (1959-11-01), Aiken
patent: 6931604 (2005-08-01), Lane
patent: 7065250 (2006-06-01), Lennon
patent: 7305618 (2007-12-01), Jasinschi
patent: 2004/0083092 (2004-04-01), Valles
patent: 2006/0165169 (2006-07-01), Ng et al.
patent: 2006/0242126 (2006-10-01), Fitzhugh
patent: 2007/0156842 (2007-07-01), Vermeulen et al.
Cheng et al., “Segmentation of Aerial Surveillance Video Using a Mixture of Experts,” Proc. of Digital Image Computing: Techniques and Applications (DICTA) Conference, Cairns, Australia, Dec. 2005.
Cheng et al., “Multiscale Bayseian Segmentation Using a Trainable Context Model,” IEEE Transactions on Image Processing, Apr. 2001, vol. 10, No. 4, pp. 511-525.
Comaniciu et al., “Robust Analysis of Feature Spaces: Color Image Segmentation,” in Proc. of IEEE Conf. on Computer Vision and Pattern. Recognition, San Juan, Puerto Rico, Jun. 1997, pp. 750-755.
Comaniciu et al., “Mean shift: a robust approach toward feature space analysis,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 24, No. 5, pp. 603-619, May 2002.
Zhao et al., “Real-Time Wide Area Multi-Camera Stereo Tracking,” CVPR (1) 2005: 976-983.
Tao et al., “Object Tracking with Bayesian Estimation of Dynamic Layer Representations,” IEEE Trans. Pattern Anal. Mach. Intell. 24(1): 75-89 (2002).

Affiliated with

Also associated with

Rating

Automated video-to-text system does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Automated video-to-text system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Automated video-to-text system will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4204311