Abstract
In this paper, we propose a new lossy image compression technique suitable for computationally challenged platforms. Extensive development in moving platforms create need for encoding images in real time with less computational resources. Conventional compression algorithms have potential to address this problem. However, the reconstruction accuracy of conventional encoders does not match that of deep learning based compression algorithms. In this paper, we have utilized best of both worlds by proposing a new compression method which combines conventional and deep learning based methods to sustain real time transmission and as well good reconstruction quality. We have validated our algorithm across a varied set of test images from EPFL mini drone dataset and Stanford drone dataset. The proposed algorithm exhibits better rate-distortion performance than conventional method. More importantly, our algorithm gives real time performance which has been substantiated by displaying a dramatic improvement in speed as against state-of-the-art deep learning compression method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gupta, P., Srivastava, P., Bhardwaj, S., Bhateja, V.: A modified PSNR metric based on HVS for quality assessment of color images. In: IEEEXplore 2011 (2011)
Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multiscale structural similarity for image quality assessment. In: Conference on Signals, Systems and Computers, vol. 2, pp. 1398–1402 (2004)
Toderici, G., et al.: Full resolution image compression with recurrent neural networks. In: CVPR 2015 (2018)
Agustsson, E., Tschannen, M., Mentzer, F., Timofte, R., Gool, L.V.: Generative adversarial networks for extreme learned image compression, arXiv:1804.02958 (2018)
Theis, L., Shi, W., Cunningham, A., Huszar, F.: Lossy image compression with compressive autoencoders. In: International Conference on Learning Representations, ICLR-2017 (2017)
Agustsson, E., et al.: Soft-to-hard vector quantization for end-to-end learning compressible representations. In: ICLR-2017 (2017)
Li, M., Zuo, W., Gu, S., Zhao, D., Zhang, D.: Learning convolutional networks for content-weighted image compression, arXiv:1703.10553 (2017)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks, arXiv preprint 1511.06434 (2015)
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANS. In: Advances in NIPS 2016, pp. 2234–2242 (2016)
Mirza, M., Osindero, S.: Conditional generative adversarial Nets, arXiv:1411.1784 (2014)
Burt, P.J., Adelson, E.H.: The Laplacian pyramid as a compact image code. In: Readings in Computer Vision, pp. 671–679 (1987)
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks, arXiv prprint (2017)
Bonetto, M., Korshunov, P., Ramponi, G., Ebrahimi, T.: Privacy in mini-drone based video surveillance. In: Workshop on De-identification for Privacy Protection in Multimedia (2015)
Kingma, D.P., Adam, J.B.: A method for stochastic optimization, CoRR, abs/1412.6980 (2014)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in NIPS 2015 (2015)
Robicquet, A., Sadeghian, A., Alahi, A., Savarese, S.: Learning social etiquette: human “trajectory prediction in crowded scenes”. In: ECCV 2016 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Faheema, A.G.J., Lakshmi, A., Priyanka, S. (2020). Image Compression for Constrained Aerial Platforms: A Unified Framework of Laplacian and cGAN. In: Nain, N., Vipparthi, S., Raman, B. (eds) Computer Vision and Image Processing. CVIP 2019. Communications in Computer and Information Science, vol 1148. Springer, Singapore. https://doi.org/10.1007/978-981-15-4018-9_19
Download citation
DOI: https://doi.org/10.1007/978-981-15-4018-9_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-4017-2
Online ISBN: 978-981-15-4018-9
eBook Packages: Computer ScienceComputer Science (R0)