Video Violence Detection using Optical Flow-Based Feature Selection and Violence Guard FrIFrO Inception V3 Algorithm

Full Length Article

•

Video Violence Detection using Optical Flow-Based Feature Selection and Violence Guard FrIFrO Inception V3 Algorithm

DOI

format_quote Cite this article

View PDF open_in_new

Abstract

Violence in recent years pose a biggest threat to the society which need to be addressed in all means. Video based Violence detection is very tough to be detected when the person or things in motion. This cutting-edge, video violence detection system uses the most advanced Violence Guard Freeze-In Freeze-Out Inception V3(VGFrIFrOI3) deep learning model in conjunction with optical flow-based characteristics. The Mosaicking process done in the pre-processing step improvises the algorithm performance through the process of space search minimization. By using a wide range of video clips that depict both violent and non-violent situations, Modern security and crime prevention techniques are more important than ever in light of the growing worries around violence in the world. The necessity of this research is underscored by statistical analysis, which shows that crimes related to violence cause almost 1.3 million lives globally each year. Through the application of recent development in computer vision and neural network algorithms, this Proposed method provides a proactive way to protect public areas and greatly improve safety worldwide.

Keywords

Violence Detection Optical Flow Deep Learning Convolutional Neural Networks InceptionV3 Mosaicking.

References

1. Jahandad, Sam SM, Kamardin K, Amir Sjarif NN, Mohamed N. Offline Signature Verification using Deep Learning Convolutional Neural Network (CNN) Architectures GoogLeNet Inception-v1 and Inception-v3. Procedia Comput Sci 2019; 161: 475–483.

2. Demir A, Yilmaz F, Kose O. Early detection of skin cancer using deep learning architectures: resnet-101 and inception-v3. 2019 Medical Technologies Congress (TIPTEKNO), IEEE 2019, 1–4.

3. Chollet F. Xception: Deep Learning with Depthwise Separable Convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE 2017, 1800–1807.

4. Emmanuel A, Tio DC. Face shape classification using Inception v3. .

5. Rahman MM, Amin Biswas A, Rajbongshi A, Majumder A, Realty C. Recognition of Local Birds of Bangladesh using MobileNet and Inception-v3. 2020.

6. Aneja N, Aneja S. Transfer Learning using CNN for Handwritten Devanagari Character Recognition. 2019;

7. Peixoto B, Lavi B, Bestagini P, Dias Z, Rocha A. MULTIMODAL VIOLENCE DETECTION IN VIDEOS. .

8. Carreira J, Zisserman A. Quo Vadis, action recognition? A new model and the kinetics dataset. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Institute of Electrical and Electronics Engineers Inc. 2017, 4724–4733.

9. Hassner T, Itcher Y, Kliper-Gross O. Violent flows: Real-time detection of violent crowd behavior. 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, IEEE 2012, 1–6.

10.Akti S, Tataroglu GA, Ekenel HK. Vision-based Fight Detection from Surveillance Cameras. 2019 Ninth International Conference on Image Processing Theory, Tools and Applications (IPTA), IEEE 2019, 1–6.

11.Ilg E, Mayer N, Saikia T, Keuper M, Dosovitskiy A, Brox T. FlowNet 2.0: Evolution of optical flow estimation with deep networks. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Institute of Electrical and Electronics Engineers Inc. 2017, 1647–1655.

12.Li J, Jiang X, Sun T, Xu K. Efficient Violence Detection Using 3D Convolutional Neural Networks. 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), IEEE 2019, 1–8.

13.Bermejo Nievas E, Deniz Suarez O, Bueno García G, Sukthankar R. Violence Detection in Video Using Computer Vision Techniques. In: 2011: 332–339.

14.Buskus K, Vaiciukynas E, Medelyte S, Siaulys A. Exploring the necessity of mosaicking for underwater imagery semantic segmentation using deep learning. J WSCG (Plzen) 2022; 30.

15.Mansour S, Ben Jabra S, Zagrouba E. A Robust Deep Learning-Based Video Watermarking Using Mosaic Generation. Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, SCITEPRESS - Science and Technology Publications 2023, 668–675.

Cite This Article

Choose your preferred format

format_quote

. "Video Violence Detection using Optical Flow-Based Feature Selection and Violence Guard FrIFrO Inception V3 Algorithm." Fusion: Practice and Applications, vol. , no. , , pp. . DOI:

(). Video Violence Detection using Optical Flow-Based Feature Selection and Violence Guard FrIFrO Inception V3 Algorithm. Fusion: Practice and Applications, (), . DOI:

. "Video Violence Detection using Optical Flow-Based Feature Selection and Violence Guard FrIFrO Inception V3 Algorithm." Fusion: Practice and Applications , no. (): . DOI:

() 'Video Violence Detection using Optical Flow-Based Feature Selection and Violence Guard FrIFrO Inception V3 Algorithm', Fusion: Practice and Applications, (), pp. . DOI:

. Video Violence Detection using Optical Flow-Based Feature Selection and Violence Guard FrIFrO Inception V3 Algorithm. Fusion: Practice and Applications. ;():. DOI:

, "Video Violence Detection using Optical Flow-Based Feature Selection and Violence Guard FrIFrO Inception V3 Algorithm," Fusion: Practice and Applications, vol. , no. , pp. , . DOI:

Digital Archive Ready