Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Detecting and removing visual distractors for video aesthetic enhancement

Zhang, Fang-Lue, Wu, Xian, Li, Rui-Long, Wang, Jue, Zheng, Zhao-Heng and Hu, Shi-Min 2018. Detecting and removing visual distractors for video aesthetic enhancement. IEEE Transactions on Multimedia 20 (8) , pp. 1987-1999. 10.1109/TMM.2018.2790163

[img]
Preview
PDF - Accepted Post-Print Version
Download (10MB) | Preview

Abstract

Personal videos often contain visual distractors, which are objects that are accidentally captured that can distract viewers from focusing on the main subjects. We propose a method to automatically detect and localize these distractors through learning from a manually labeled dataset. To achieve spatially and temporally coherent detection, we propose extracting features at the Temporal-Superpixel (TSP) level using a traditional SVM-based learning framework. We also experiment with end-to-end learning using Convolutional Neural Networks (CNNs), which achieves slightly higher performance than other methods. The classification result is further refined in a post-processing step based on graph-cut optimization. Experimental results show that our method achieves an accuracy of 81% and a recall of 86%. We demonstrate several ways of removing the detected distractors to improve the video quality, including video hole filling; video frame replacement; and camera path re-planning. The user study results show that our method can significantly improve the aesthetic quality of videos.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
ISSN: 1520-9210
Date of First Compliant Deposit: 25 December 2017
Date of Acceptance: 12 December 2017
Last Modified: 07 Nov 2019 10:09
URI: http://orca.cf.ac.uk/id/eprint/107790

Citation Data

Cited 3 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item