Abstract
In today’s era, the usage of videos has led to major contributions in the technological world. Be it CCTV footage captured in apartments and at traffic intersections or real-time recordings in the medical industry, videos help in discerning various patterns and uncovering hidden details, accounting for its extensive usage. Future frame prediction involves using the analysis of videos to predict what could happen next in the video. This is an emerging field of deep learning and computer vision whose advancement would provide large potential to enable faster decision making processes in areas like autonomous driving cars, anomaly detection, and aggression in people and falls in the elderly. Due to the proven effectiveness of deep learning in image processing, our goal is to develop a generative model capable of producing a future frame given a set of sequential frames as input. Generative adversarial networks (GANs) and autoencoders are the models used in implementing and achieving the target results. This paper presents the analysis and results of different proposed architectures that take multiple frames as input and aim to produce accurate future frames with the use of multiple efficiency measures. A structural similarity index (SSIM) score of 0.875 was obtained for the predicted frame.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Liu W, Luo W, Lian D, Gao S (2018) Future frame prediction for anomaly detection—a new baseline. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6536–6545
Johnson J, Alahi A, Li F-F (2016) Perceptual losses for real-time style transfer and super-resolution. In: European conference on computer vision. Springer, Cham, pp 694–711
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Ruder S (2016) An overview of gradient descent optimization algorithms. arXiv:1609.04747
Kwon Y-H, Park M-G (2019) Predicting future frames using retrospective cycle gan. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1811–1820
Geiger A, Lenz P, Stiller C, Urtasun R (2013) Vision meets robotics: the kitti dataset. Int J Robotic Res 32(11):1231–1237
Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, Cham, pp 234–241
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612
Isola P, Zhu J-Y, Zhou T, Efros AA (2017) Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1125–1134
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Itagi, S., Gowda, S., Udupa, T., Shylaja, S.S. (2022). Future Frame Prediction Using Deep Learning. In: Raje, R.R., Hussain, F., Kannan, R.J. (eds) Artificial Intelligence and Technologies. Lecture Notes in Electrical Engineering, vol 806. Springer, Singapore. https://doi.org/10.1007/978-981-16-6448-9_21
Download citation
DOI: https://doi.org/10.1007/978-981-16-6448-9_21
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6447-2
Online ISBN: 978-981-16-6448-9
eBook Packages: Computer ScienceComputer Science (R0)