Near-Duplicate Video Cleansing Method Based on Locality Sensitive Hashing and the Sorted Neighborhood Method
- 191 Downloads
With the wide utilization of intelligent video surveillance technology, increasing amounts of near-duplicate video has been generated, which seriously affects the data quality of the video data set. Cleaning this dirty data automatically from the video data set has become an important issue that needs to be urgently resolved. In this chapter, a near-duplicate video cleansing method based on locality sensitive hashing (LSH) and the sorted neighborhood method (SNM) is presented in an attempt to solve the above problem. First, the speeded-up robust feature is extracted from the video and then the sorted candidate set is built by using LSH; on this basis, the near-duplicate videos are cleaned by using the SNM. Finally, the simulation experiments are implemented to show that the presented method in this chapter is effective, which can be used to clean near-duplicate videos automatically and improve video data quality.
KeywordsData quality Dirty data Video cleansing Near-duplicate video LSH SNM
This work was supported in part by the Shannxi Provincial Department of Education special scientific research project (No.16JK1505).
- 1.Wang, W., & Zhang, L. (2013). Application and research of security data mining techniques in coal mine mobile video monitoring system (in Chinese). Coal Technology, 9, 101–103.Google Scholar
- 10.Rahm, E., & Do, H. H. (2000). Data cleaning: Problems and current approach. IEEE Data Engineering Bulletin, 23(4), 3–13.Google Scholar
- 14.Liu, S., Zhu, M., & Zheng, Q. (2010). A detection method for near duplicate video clips based on content similarity (in Chinese). Journal of University of Science and Technology of China, 40(11), 1130–1135.Google Scholar
- 15.Wang, H., & Liu, X. (2012). Near-duplicate web video detection based on locality sensitive hashing (in Chinese). Application Research of Computers, 29(5), 1954–1958.Google Scholar
- 16.Liu, D., & Zhu, M. (2013). A fast algorithm for near-duplicate video detection (in Chinese). Journal of Chinese Computer Systems, 34(6), 1400–1406.Google Scholar
- 17.Liu, D., & Zhu, M. (2015). A computationally efficient algorithm for large scale near-duplicate video detection. In International Conference on Multimedia Modeling (MMM 2015) (pp. 481–490). Basel: Springer.Google Scholar