Abstract
The state of the art in collaborative human-machine geographic region digitization yields 80% automation in vertex placement when digitizing land-water boundaries in small remotely sensed persistent image sets. However, these techniques have difficulty scaling to large datasets due to \(O(\log N)\) complexity of instance-based learning and concept drift, or sudden shifts in environmental context. We report the performance of the human-machine team on a 50-image dataset of a littoral region targeting the highly dynamic nearshore region, which is the region of breaking waves and swash. As we have observed that both computational performance and precision are lacking, we define and apply several novel optimization techniques built specifically for the human-machine team. The best performing optimization technique, which is named compositional interface schemata, utilizes the novel concept of providing an objective function based on the machine teammate’s performance in automation rather than an objective function based on the underlying classifier’s pixel classification accuracy. Results show that all proposed optimization methods, including simply clearing the learner of instances each period, perform at least 3% points better than an unoptimized approach. The best performing optimizer yields a vertex placement accuracy of 74% compared to the non-optimized accuracy of 65%. Additionally, we present an online heuristic that attempts to dynamically choose the best optimization method, which yields 77% vertex placement accuracy.
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
Notes
- 1.
We choose to use the term digitization, which emphasizes the manual process of digitizing features of interest from imagery. The term segmentation, which is also appropriate, mainly emphasizes processes for automatically performing digitization. Computer science literature typically uses the term “segmentation” while physical science literature typically uses the term “digitization”.
References
Aha, D.W., Bankert, R.L.: A comparative evaluation of sequential feature selection algorithms. In: Fisher, D., Lenz, HJ. (eds.) Learning from Data. Lecture Notes in Statistics, vol. 112. Springer, New York, NY (1996). https://doi.org/10.1007/978-1-4612-2404-4_19
Alekseev, A., Bobe, A.: Gabornet: Gabor filters with learnable parameters in deep convolutional neural network. In: 2019 International Conference on Engineering and Telecommunication (EnT), pp. 1–4. IEEE (2019)
Elhamifar, E., Sapiro, G., Yang, A., Sasrty, S.S.: A convex optimization framework for active learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 209–216 (2013)
Gabor, D.: Theory of communication. part 1: The analysis of information. J. Inst. Electr. Eng. Part III: Radio Commun. Eng. 93(26), 429–441 (1946)
Gama, J., Žliobaitė, I., Bifet, A., Pechenizkiy, M., Bouchachia, A.: A survey on concept drift adaptation. ACM Comput. Surv. (CSUR) 46(4), 1–37 (2014)
Hastie, T., Tibshirani, R., Friedman, J.: The elements of statistical learning: data mining, inference, and prediction, chap. 7, pp. 241–245. Springer Science & Business Media (2009)
Holman, R.: Nearshore processes. Rev. Geophys. 33(S2), 1237–1247 (1995)
Holman, R.A., Stanley, J.: The history and technical capabilities of argus. Coastal Eng. 54(6–7), 477–491 (2007)
Hossain, M.D., Chen, D.: Segmentation for object-based image analysis (OBIA): a review of algorithms and challenges from remote sensing perspective. ISPRS J. Photogrammetry Remote Sens. 150, 115–134 (2019)
Keller, J.M., Gray, M.R., Givens, J.A.: A fuzzy k-nearest neighbor algorithm. IEEE Trans. Syst. Man Cybern. 4, 580–585 (1985)
Kirby, S., Hurford, J.R.: The emergence of linguistic structure: an overview of the iterated learning model. In: Cangelosi, A., Parisi, D. (eds.) Simulating the Evolution of Language. Springer, London (2002). https://doi.org/10.1007/978-1-4471-0663-0_6
Kotaridis, I., Lazaridou, M.: Remote sensing image segmentation advances: a meta-analysis. ISPRS J. Photogrammetry Remote Sens. 173, 309–322 (2021). https://doi.org/10.1016/j.isprsjprs.2021.01.020, https://www.sciencedirect.com/science/article/pii/S0924271621000265
Meshgini, S., Aghagolzadeh, A., Seyedarabi, H.: Face recognition using gabor filter bank, kernel principle component analysis and support vector machine. Int. J. Comput. Theor. Eng. 4(5), 767 (2012)
Michael, C.J., Dennis, S.M., Maryan, C., Irving, S., Palmsten, M.L.: A general framework for human-machine digitization of geographic regions from remotely sensed imagery. In: Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, SIGSPATIAL 2019, pp. 259–268 (2019)
Nargesian, F., Samulowitz, H., Khurana, U., Khalil, E.B., Turaga, D.S.: Learning feature engineering for classification. In: Ijcai, vol. 17, pp. 2529–2535 (2017)
Nelder, J.A., Mead, R.: A simplex method for function optimization. Comput. J. 7, 308–313 (1965)
Palmsten, M.L., Brodie, K.L.: The coastal imaging research network (CIRN). Remote Sens. 14(3), 453 (2022)
Probst, P., Bischl, B., Boulesteix, A.L.: Tunability: importance of hyperparameters of machine learning algorithms. arXiv preprint arXiv:1802.09596 (2018)
Wilder, B., Horvitz, E., Kamar, E.: Learning to complement humans. arXiv preprint arXiv:2005.00582 (2020)
Witkin, A.P.: Scale-space filtering. In: Readings in Computer Vision, pp. 329–332. Elsevier (1987)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dennis, S.M., Michael, C.J. (2023). Optimization of a Human-Machine Team for Geographic Region Digitization. In: Mori, H., Asahi, Y. (eds) Human Interface and the Management of Information. HCII 2023. Lecture Notes in Computer Science, vol 14016. Springer, Cham. https://doi.org/10.1007/978-3-031-35129-7_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-35129-7_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35128-0
Online ISBN: 978-3-031-35129-7
eBook Packages: Computer ScienceComputer Science (R0)