1 / 19

Discovering Important People and Objects for Egocentric Video Summarization

Discovering Important People and Objects for Egocentric Video Summarization. Yong Jae Lee, Joydeep Ghosh , and Kristen Grauman University of Texas at Austin. Outline. Introduction Approach Results Conclusion. Introduction. Introduction.

lada
Download Presentation

Discovering Important People and Objects for Egocentric Video Summarization

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Discovering Important People and Objects for Egocentric Video Summarization Yong Jae Lee, JoydeepGhosh, and Kristen Grauman University of Texas at Austin

  2. Outline Introduction Approach Results Conclusion

  3. Introduction

  4. Introduction Focus on the most important objects and people with which the camera wearer interacts. Develop region cues indicative of high-level saliency feature in egocentric video Learn a regressor to predict the relative importance of any new region based on the cues.

  5. Approach Train a regression model to predict region importance Segment the video into temporal events Scoring each region ' s importance using the regressor Generate a storyboard summary of important people /objects important things are those with which the camera wearer has significant interaction. four main steps:

  6. Egocentric video data collection  We use the Looxcie wearable camera, which captures video at 15 fps at 320 x 480 resolution.   We collected 10 videos, each of 3-5 hours in length.

  7. Annotating important regions in training video

  8. Learning region importance in egocentric video  • Egocentric features • Interaction • Gaze • Frequency

  9. Learning region importance in egocentric video [19] D. Lowe. Distinctive Image Features from Scale-Invariant Keypoints.IJCV, 60(2), 2004. • Frequency feature • Matching regions • Matching points(DoG+SIFT)[19]

  10. Learning region importance in egocentric video [3] Constrained Parametric Min-Cutsfor Automatic Object Segmentation. In CVPR, 2010. [16]Key-Segments for Video ObjectSegmentation. In ICCV, 2011. [27]Rapid Object Detection using a Boosted Cascadeof Simple Features. In CVPR, 2001. • Object features • object-like appearance[3] • object-like motion[16] • likelihood of a person's face[27] • Region features • size、centroid • bounding box centroid、width、height

  11. Regressor to predict region importance learned parameters i’thfeature value For training: ; for testing: predict given Training a linear regression model with pair-wise interaction terms to predict a region r'simportance score:

  12. Segmenting the video into temporal events where

  13. Discovering an event’s key people and objects

  14. Results Evaluate on videos from all 4 users, total 17 hours.Train using data from 3 users and test on 1 video from remaining user.

  15. Important region prediction accuracy [3] Constrained Parametric Min-Cuts for Automatic Object Segmentation. In CVPR, 2010. [6]Category Independent Object Proposals. In ECCV, 2010. [28] Modeling Attention to Salient Proto-Objects. Neural Networks, 19:1395–1407, 2006.

  16. The highest learned weights

  17. User study results

  18. Application example

  19. Conclusion A novel approach to perform summarization for egocentric video. Focus on the most important objects and people that generate the " story " of vedio. Novel egocentric features to train a regressor that predicts important regions.

More Related