Khyle Aaron Goneda Montebon
ABSTRACT
Since time immemorial, violence has been a problem that the world has been facing. The rise of technology has presented an opportunity to help in this matter. Violence detection solutions have been created for this cause. The problem with existing solutions is that they are not appropriate for settings in a developing country. Factors such as the place, objects seen, people involved, among others, are different from those models who are trained with datasets from developed countries, which might prove ineffective for developing countries. That is why the researchers aim to create a Generative Adversarial Networks Model trained with data that are location-specific to the country of Philippines. In this study, the researchers will gauge the effects and impact that resolution brings in the training of the GAN Model, named V.GAN, to help with improving its performance and implementation.
- [1] 6Wresearch. 2020. Philippines Video Surveillance Market (2020-2026). https://www.6wresearch.com/industry-report/philippines-video-surveillance-market-2020-2026Google Scholar
- [2] Al-Maamoon R. Abdali and Rana F. Al-Tuma. 2019. Robust Real-Time Violence Detection in Video Using CNN And LSTM., 104–108 pages. https://doi.org/10.1109/SCCS.2019.8852616Google Scholar
- [3] AIMultiple. 2021. Data Annotation: What it is & why does it matter?https://research.aimultiple.com/data-annotation/Google Scholar
- [4] Francis Baek, Somin Park, and Hyoungkwan Kim. 2019. Data Augmentation Using Adversarial Training for Construction-Equipment Classification. (2019). https://doi.org/10.48550/arXiv.1911.11916Google Scholar
- [5] David Choqueluque-Roman and Guillermo Camara-Chavez. 2022. Weakly Supervised Violence Detection in Surveillance Video. Sensors 22 (06 2022), 4502. https://doi.org/10.3390/s22124502Google Scholar
- [6] COE. n.d. Physical violence. https://www.coe.int/en/web/gender-matters/physical-violenceGoogle Scholar
- [7] Antonia Creswell, Tom White, Vincent Dumoulin, Kai Arulkumaran, Biswa Sengupta, and Anil A. Bharath. 2018. Generative Adversarial Networks: An Overview. IEEE Signal Processing Magazine 35 (01 2018), 53–65. https://doi.org/10.1109/msp.2017.2765202Google Scholar
- [8] FFMPEG. n.d. ffmpeg Documentation. https://ffmpeg.org/ffmpeg.htmlGoogle Scholar
- [9] Sumit Gupta. 2019. High Accuracy & Faster Deep Learning with High Resolution Images & Large Models. https://sumitgup.medium.com/deep-learning-with-high-resolution-images-large-models-44bfd90482a8Google Scholar
- [10] Enrique Bermejo Nievas, Oscar Deniz Suarez, Gloria Bueno Garcia, and Rahul Sukthankar. 2011. Violence Detection in Video Using Computer Vision Techniques. (2011).Google Scholar
- [11] Aravind Ramalingam. 2021. How to Pick the Optimal Image Size for Training Convolution Neural Network?https://medium.com/analytics-vidhya/how-to-pick-the-optimal-image-size-for-training-convolution-neural-network-65702b880f05Google Scholar
- [12] Muhammad Ramzan, Adnan Abid, Hikmat Ullah Khan, Shahid Mahmood Awan, Amina Ismail, Muzamil Ahmed, Mahwish Ilyas, and Ahsan Mahmood. 2019. A Review on State-of-the-Art Violence Detection Techniques. IEEE Access 7 (2019), 107560–107575. https://doi.org/10.1109/access.2019.2932114Google ScholarCross Ref
- [13] Mohamed Mostafa Soliman, Mohamed Hussein Kamal, Mina Abd El-Massih Nashed, Youssef Mohamed Mostafa, Bassel Safwat Chawky, and Dina Khattab. 2019. Violence Recognition from Videos using Deep Learning Techniques., 80–85 pages. https://doi.org/10.1109/ICICIS46948.2019.9014714Google Scholar
- [14] Noah Sulman, Thomas Sanocki, Dmitry Goldgof, and Rangachar Kasturi. 2008. How effective is human video surveillance performance?2008 19th International Conference on Pattern Recognition (12 2008). https://doi.org/10.1109/icpr.2008.4761655Google Scholar
- [15] Laura Mazzuca Toops. 2022. State of the Market: Video Surveillance | SDM Magazine. https://www.sdmmag.com/articles/100416-state-of-the-market-video-surveillanceGoogle Scholar
- [16] Andrew Roth Stephanie Kirchgaessner in Washington, Daniel Boffey in Brussels, Oliver Holmes in Jerusalem, and Helen Davidson in Sydney. 2020. Growth in surveillance may be hard to scale back after pandemic, experts say. The Guardian (04 2020). https://www.theguardian.com/world/2020/apr/14/growth-in-surveillance-may-be-hard-to-scale-back-after-coronavirus-pandemic-experts-sayGoogle Scholar
- [17] Tao Zhang, Zhijie Yang, Wenjing Jia, Baoqing Yang, Jie Yang, and Xiangjian He. 2015. A new method for violence detection in surveillance scenes. Multimedia Tools and Applications 75 (05 2015), 7327–7349. https://doi.org/10.1007/s11042-015-2648-8Google ScholarDigital Library
Index Terms
- The Impact of Image Resolution in the training of Generative Adversarial Networks for Violence Detection
Recommendations
Generative adversarial network based synthetic data training model for lightweight convolutional neural networks
AbstractInadequate training data is a significant challenge for deep learning techniques, particularly in applications where data is difficult to get, and publicly available datasets are uncommon owing to ethical and privacy concerns. Various approaches, ...
Auto-encoder generative adversarial networks
Generative Adversarial Networks have demonstrated potential on a variety of generative tasks, although they are regarded as unstable and sometimes they miss modes. We propose Auto-encoder Generative Adversarial Networks - a convolutional neural network ...
CapsuleGAN: Generative Adversarial Capsule Network
Computer Vision – ECCV 2018 WorkshopsAbstractWe present Generative Adversarial Capsule Network (CapsuleGAN), a framework that uses capsule networks (CapsNets) instead of the standard convolutional neural networks (CNNs) as discriminators within the generative adversarial network (GAN) ...
Comments