Abstract
The homography matrix plays a vital role in robotics and computer vision applications, but mainstream estimators are usually customized for specific problems and are sensitive to image quality. In response to this situation, a reinforced agent is proposed to improve image quality by sequentially reconstructing the exposure. First, the gamma correction theory is employed to design a nonlinear exposure adjustment function so that the agent’s action is not bound to additional hardware or software. Then, the agent is designed as consisting of a metric network and a Q network that are trained under the reinforcement learning framework. When a black-box nondifferentiable homography estimator is given, the metric network can map the image into its corresponding embedding space, and the Q network can further determine an exposure value to produce pleasing images for it. Comprehensive experiments are conducted on homography samples generated from the public aerial DOTASet. After reconstructing the exposure of the original input, all selected estimators can obtain more accurate results. It also reveals that visually satisfactory images may not always be the best choice for homography estimation.









Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Ma J, Jiang X, Fan A, et al. (2020) Image matching from handcrafted to deep features: a survey. Int J Comput Vis, 1–57
Kamranian Z, Sadeghian H, Nilchi ARN, et al. (2021) Fast, yet robust end-to-end camera pose estimation for robotic applications. Appl Intell 51(6):3581–3599
Meng L, Zhou J, Liu S, et al. (2021) Investigation and evaluation of algorithms for unmanned aerial vehicle multispectral image registration. Int J Appl Earth Observ Geoinform 102:102403
Wolpert DH, Macready WG (1997) No free lunch theorems for optimization. IEEE Trans Evol Comput 1(1):67–82
Qiu S, Liu Q, Zhou S, et al. (2019) Review of artificial intelligence adversarial attack and defense technologies. Appl Sci 9(5):909
Wang H-n, Liu N, Zhang Y-y, et al. (2020) Deep reinforcement learning: a survey. Frontiers of Information Technology & Electronic Engineering, 1–19
Le N, Rathour VS, Yamazaki K, et al. (2021) Deep reinforcement learning in computer vision: a comprehensive survey. Artif Intell, 1–87
Wang Z, Zhang J, Lin M, et al. (2020) Learning a reinforced agent for flexible exposure bracketing selection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 1820–1828
Yang H, Wang B, Vesdapunt N, et al. (2018) Personalized exposure control using adaptive metering and reinforcement learning. IEEE Trans Visual Comput Graph 25(10):2953–2968
Kosugi S, Yamasaki T (2020) Unpaired image enhancement featuring reinforcement-learning-controlled image editing software. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 11296–11303
Zhang R, Guo L, Huang S, et al. (2021) Rellie: deep reinforcement learning for customized low-light image enhancement. In: Proceedings of the 29th ACM international conference on multimedia, pp 2429–2437
Yu R, Liu W, Zhang Y, et al. (2018) Deepexposure: learning to expose photos with asynchronously reinforced adversarial learning. In: Proceedings of the 32nd international conference on neural information processing systems, pp 2153–2163
Sajjadi MS, Scholkopf B, Hirsch M (2017) Enhancenet: single image super-resolution through automated texture synthesis. In: Proceedings of the IEEE international conference on computer vision, pp 4491–4500
Talebi H, Milanfar P (2021) Learning to resize images for computer vision tasks. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 497–506
Onzon E, Mannan F, Heide F (2021) Neural auto-exposure for high-dynamic range object detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 7710–7720
Haris M, Shakhnarovich G, Ukita N (2021) Task-driven super resolution: object detection in low-resolution images. In: International conference on neural information processing, pp 387–395
Zhang Z, Forster C, Scaramuzza D (2017) Active exposure control for robust visual odometry in hdr environments. In: 2017 IEEE International conference on robotics and automation, pp 3894–3901
Tomasi J, Wagstaff B, Waslander SL, et al. (2021) Learned camera gain and exposure control for improved visual feature detection and matching. IEEE Robot Autom Lett 6(2):2028–2035
Mehta I, Tang M, Barfoot TD (2020) Gradient-based auto-exposure control applied to a self-driving car. In: 2020 17th conference on computer and robot vision, pp 166–173
Krishna Gottipati S, Pathak Y, Nuttall R, et al. (2020) Maximum reward formulation in reinforcement learning. In: Proceedings of the international conference on learning representations
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60 (2):91–110
Bay H, Tuytelaars T, Van Gool L (2006) Surf: speeded up robust features. In: European conference on computer vision, pp 404–417
Rublee E, Rabaud V, Konolige K, et al. (2011) Orb: an efficient alternative to sift or surf. In: 2011 International conference on computer vision, pp 2564–2571
Baker S, Matthews I (2004) Lucas-kanade 20 years on: a unifying framework. Int J Comput Vis 56(3):221–255
DeTone D, Malisiewicz T, Rabinovich A (2019) Method and system for performing convolutional image transformation estimation. Google Patents. US Patent 10,489,708
Nguyen T, Chen SW, Shivakumar SS, et al. (2018) Unsupervised deep homography: a fast and robust homography estimation model. IEEE Robot Autom Lett 3(3):2346–2353
Zhang J, Wang C, Liu S, et al. (2020) Content-aware unsupervised deep homography estimation. In: European conference on computer vision, pp 653–669
Lin T-Y, Maire M, Belongie S, et al. (2014) Microsoft coco: common objects in context. In: European conference on computer vision, pp 740–755
Le H, Liu F, Zhang S, et al. (2020) Deep homography estimation for dynamic scenes. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 7652–7661
Ye N, Wang C, Fan H, et al. (2021) Motion basis learning for unsupervised deep homography estimation with subspace projection. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 13117–13125
Mi Y, Zheng K, Wang S (2020) Homography estimation along short videos by recurrent convolutional regression network. Math Found Comput 3(2):125
Erlik Nowruzi F, Laganiere R, Japkowicz N (2017) Homography estimation from image pairs with hierarchical convolutional networks. In: Proceedings of the IEEE international conference on computer vision workshops, pp 913–920
Zhou Q, Li X (2019) Stn-homography: direct estimation of homography parameters for image pairs. Appl Sci 9(23):5187
Zeng R, Denman S, Sridharan S, et al. (2018) Rethinking planar homography estimation using perspective fields. In: Asian conference on computer vision, pp 571–586
VidalMata RG, Banerjee S, RichardWebster B, et al. (2020) Bridging the gap between computational photography and visual recognition. IEEE Trans Pattern Anal Mach Intell 43(12):4272–4290
Xie Z-F, Guo Y-C, Zhang S-H, et al. (2018) Multi-exposure motion estimation based on deep convolutional networks. J Comput Sci Technol 33(3):487–501
Stevens SS (1957) On the psychophysical law. Psychol Rev 64(3):153
Li D, Tian Y (2018) Survey and experimental study on metric learning methods. Neur Netw 105:447–462
He K, Zhang X, Ren S, et al. (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Hoffer E, Ailon N (2015) Deep metric learning using triplet network. In: International workshop on similarity-based pattern recognition, pp 84–92
Van Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI conference on artificial intelligence, vol 30
Chen X, He K (2021) Exploring simple siamese representation learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 15750–15758
Kharismawati DE, Akbarpour HA, Aktar R, et al. (2020) Cornet: unsupervised deep homography estimation for agricultural aerial imagery. In: European conference on computer vision, pp 400–417
Xia G-S, Bai X, Ding J, et al. (2018) Dota: a large-scale dataset for object detection in aerial images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3974–3983
Wang C, Wang X, Bai X, et al. (2019) Self-supervised deep homography estimation with invertibility constraints. Pattern Recogn Lett 128:355–360
Gharbi M, Chen J, Barron JT, et al. (2017) Deep bilateral learning for real-time image enhancement. ACM Trans Graph 36(4):1–12
Wei C, Wang W, Yang W, et al. (2018) Deep retinex decomposition for low-light enhancement. In: Proceedings of the British machine vision conference, pp 451–463
Zeng H, Cai J, Li L, et al. (2020) Learning image-adaptive 3d lookup tables for high performance photo enhancement in real-time. IEEE Transactions on Pattern Analysis and Machine Intelligence
Wang R, Zhang Q, Fu C-W, et al. (2019) Underexposed photo enhancement using deep illumination estimation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 6849–6857
Moran S, Marza P, McDonagh S, et al. (2020) Deeplpf: deep local parametric filters for image enhancement. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 12826–12835
Ren K, Zheng T, Qin Z, et al. (2020) Adversarial attacks and defenses in deep learning. Engineering 6(3):346–360
Funding
This work was supported by National Natural Science Foundation of China (91938301)
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design.
Corresponding authors
Ethics declarations
Ethics approval and consent to participate
The authors confirm that all experimental protocols were approved by the Institute of Software Chinese Academy of Sciences. The methods were carried out in accordance with the relevant guidelines and regulations, and informed consent has been obtained from all authors.
The consent to participate has been obtained from all authors.
Consent for Publication
The consent for publication has been obtained from all authors.
Conflict of Interests
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Additional information
Data availability
All data and materials in this article support the published claims and comply with field standards.
Code availability
All software application and custom code in this article support the published claims and comply with field standards.
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Lin, Y., Wu, F. & Zhao, J. Reinforcement learning-based image exposure reconstruction for homography estimation. Appl Intell 53, 15442–15458 (2023). https://doi.org/10.1007/s10489-022-04287-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-04287-5