Video Background Modeling Algorithm of Low Complexity Based on the Minimum Second Derivative
| Autor: | Anlun Zhang, Haiwu Zhao, Guozhong Wang, Guowei Teng |
|---|---|
| Rok vydání: | 2018 |
| Předmět: | |
| Zdroj: | Communications in Computer and Information Science ISBN: 9789811081071 IFTC |
| DOI: | 10.1007/978-981-10-8108-8_5 |
| Popis: | The coding of scene videos such as surveillance videos, conference videos, is becoming a hot spot of research in recent years. The key technology of this kind of video coding is to create one or more background images as a long-term reference frame in the process of encoding accurately and efficiently. This paper proposes a video background modeling algorithm of low complexity based on the minimum second derivative. Firstly, estimating the wave characteristics of the function according to its second derivative; after that, getting the stability of every pixel by using second-order difference to fit the second derivate of pixels in the time domain; finally, extracting the steadiest value of every pixel during the training period in the basis of threshold value, then take it as the corresponding background model value. The experiment results indicate that compared with AVS2, it saves 9.83% on BD-rate and improves 0.37 dB on BD-PSNR, compared with the background modeling algorithm of AVS2-S, this algorithm not only effectively improved the problem of foreground pollution, but also reduces the algorithm complexity. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|