# Shot Boundary Detection Based on Global Features and the Target Features

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Related Works

#### 2.1. RGB Color Histogram Features

#### 2.2. Gaussian Mixture Model

#### 2.3. SIFT Features

- Scale-space detection is performed to initially determine the key point location and scale;
- The 3-dimensional quadratic function is pseudomatched to accurately determine the position and scale of the key points, removing the key points with low contrast and the unstable edge response points;
- The gradient orientation distribution properties of the key neighborhood pixels are used to specify the orientation parameters for each key;$$m(x,y)=\sqrt{(L(x+1,y)-L(x-1),y){)}^{2}+{(L(x,y+1)-L(x,y-1))}^{2}}$$$$\theta (x,y)=\alpha \mathrm{tan}2(\frac{L(x,y+1)-L(x,y-1)}{L(x+1,y)-L(x-1,y)})$$The above formula refers to the modular value and direction formula of the gradient at $(x,y)$, respectively. At this time, the key detection is completed, and the scale used by $L$ is each key point;
- Generate the SIFT feature vectors.

## 3. Fusion Feature Algorithm

#### 3.1. Multi-Step Comparison Scheme

#### 3.2. Cut Detection

#### 3.3. Gradual Detection

## 4. Results and Discussion

#### 4.1. Experimental Results and the Comparison

#### 4.2. Discussion

## 5. Conclusions

- In our method, by extracting the RGB color histogram global features of video frames and the scale-invariant feature transform (SIFT) target features. It can not only compensate for the misdetection of shot boundary detection caused by extracting only the global features while ignoring the detailed features but also compensate for the misdetection of shot boundary detection caused by extracting only the local features while ignoring the global changes.
- We combined the Gaussian Mixed Model (GMM) algorithm to the field of shot boundary detection and then extracted the scale-invariant feature transform (SIFT) features and further improved the misdetection situation caused by ignoring the attention to the target features.

## Author Contributions

## Funding

## Data Availability Statement

## Conflicts of Interest

## References

- Shanshan, L. Improved Algorithm for Shot Mutation Detection Based on SIFT Feature Points; Wuhan Polytechnic University: Wuhan, China, 2019. [Google Scholar]
- Chakraborty, S.; Singh, A.; Thounaojam, D.M.J. A novel bifold-stage shot boundary detection algorithm: Invariant to motion and illumination. Vis. Comput.
**2021**, 38, 445–456. [Google Scholar] [CrossRef] - Xu, W.; Xu, L. Shot Boundary Detection Algorithm Based on Clustering. Comput. Eng.
**2010**, 36, 230–237. [Google Scholar] - Xi, C. A Shot Boundary Detection Algorithm of MPEG-2 Video Sequence Based on Chi-Square Detection and Macroblocktype Statistics; Shanghai Jiao Tong University: Shanghai, China, 2009; pp. 1–70. [Google Scholar]
- Gygli, M. Ridiculously Fast Shot Boundary Detection with Fully Convolutional Networks. In Proceedings of the 2018 International Conference on Content-Baesd Multimedia Indexing, CBMI2018, La Rochelle, France, 4–6 September 2018; pp. 1–4. [Google Scholar] [CrossRef]
- Souek, T.; Loko, J. TransNet V2: An effective deep network architecture for fast shot transition detection. arXiv
**2020**, arXiv:2008.04838. [Google Scholar] - Raja Suguna, M.; Kalaivani, A.; Anusuya, S. The Detection of Video Shot Transitions Based on Primary Segments Using the Adaptive Threshold of Colour-Based Histogram Differences and Candidate Segments Using the SURF Feature Descriptor. Symmetry
**2022**, 14, 2041. [Google Scholar] [CrossRef] - Li, J.; Shao, C.F.; Yang, L.Y. Pedestrian detection based on improved Gaussian mixture model. Jilin Daxue Xuebao (Gongxueban)/J. Jilin Univ. (Engine-Ering Technol. Ed.)
**2011**, 41, 41–45. [Google Scholar] - Kekre, H.B.; Sonawane, K. Comparative study of color histogram based bins approach in RGB, XYZ, Kekre’s LXY and L′X′Y′ color spaces. In Proceedings of the International Conference on Circuits, San Francisco, CA, USA, 22–24 October 2014; IEEE: Piscatvie, NJ, USA, 2014. [Google Scholar]
- Lihua, T.; Mi, Z.; Chen, L. Key frame extraction algorithm based on feature of moving target. Appl. Res. Comput.
**2019**, 10, 3138–3186. [Google Scholar] - Kailiang, G.; Tuanfa, Q.; Yuebo, C.; Kan, C. Detection of moving objects using pixel classification based on Gaussian mixture model. J. Nan Jing Univ. (Nat. Sci.)
**2011**, 47, 195–200. [Google Scholar] - Hannane, R.; Elboushaki, A.; Afdelk, K.; Naghabhushan, P.; Javed, M. An efficient method for video shot boundary detection and key frame extraction using SIFT-point distribution histogram. Int. J. Multimed. Info-Rmation Retr.
**2016**, 5, 89–104. [Google Scholar] [CrossRef] - Zonggui, C.; Xiaojun, D.; Lingrong, Z.; Yingjun, Z. Application of Improved SIFT Algorithm in Medical Image Registration. Comput. Technol. Dev.
**2022**, 32, 71–75. [Google Scholar] - Xuelong, H.; Yingcheng, T.; Zhenghua, Z. Video object matching based on sift algorithm. In Proceedings of the Conference Neural on Networks and Signal Processing, Nanjing, China, 7–11 June 2008; IEEE: Piscatvie, NJ, USA, 2008; pp. 412–415. [Google Scholar]
- Cai, C.; Lam, K.M.; Tan, Z. Shot Boundary Detection Based on a Multi-Step, Comparison Scheme. In Proceedings of the TRECVID 2005, Gaithersburg, MD, USA, 14–15 November 2005. Experiments in The Hong Kong Polytechnic University. [Google Scholar]
- Meitei, T.D.; Thongam, K.; Manglem, S.K.; Roy, S. A genetic algorithm and fuzzy logic approach for video shot boundary detection. Comput. Intell. Neurosci.
**2016**, 2016, 8469428. [Google Scholar] - Apostolidis, E.; Mezaris, V. Fast shot segmentation combining global and local visual descriptors. In Proceedings of the IEEE International Conferenceon Acoustics, Florence, Italy, 4–9 May 2014; IEEE: Piscatvie, NJ, USA, 2014; pp. 6583–6587. [Google Scholar]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |

© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Li, Q.; Chen, X.; Wang, B.; Liu, J.; Zhang, G.; Feng, B. Shot Boundary Detection Based on Global Features and the Target Features. *Symmetry* **2023**, *15*, 565.
https://doi.org/10.3390/sym15030565

**AMA Style**

Li Q, Chen X, Wang B, Liu J, Zhang G, Feng B. Shot Boundary Detection Based on Global Features and the Target Features. *Symmetry*. 2023; 15(3):565.
https://doi.org/10.3390/sym15030565

**Chicago/Turabian Style**

Li, Qiuling, Xiao Chen, Bingbing Wang, Jing Liu, Guofeng Zhang, and Bin Feng. 2023. "Shot Boundary Detection Based on Global Features and the Target Features" *Symmetry* 15, no. 3: 565.
https://doi.org/10.3390/sym15030565