A real-time SC2S-based open-set recognition in remote sensing imagery
Tóm tắt
Accuracy and computational time are two crucial parameters influencing the efficacy of classification algorithms for remote sensing applications. Machine learning algorithms are known for achieving notable success for several classification problems in various domains, including remote sensing. However, they are well-recognized and considered accurate and efficient for closed-set recognition (CSR) but may provide suboptimal and erroneous results for open-set recognition (OSR) tasks. Many practical image-driven and computer vision applications have open-set and dynamic scenarios with unknown data where classification algorithms have not yet achieved significant prediction performance. This paper presents a group of class-aware (CA) classification algorithms based on a supervised cascaded classifier system (SC2S), called CA-SC2S, which is accurate for OSR and CSR tasks. We evaluate the prediction accuracy of the proposed methods against the state-of-the-art methods in a multiclass setting using multiple image classification scenarios of OSR and CSR. The test case scenarios use six multispectral and hyperspectral datasets from different sensing platforms. And to assess the computational performance of the methods, we designed various field-programmable gate array (FPGA) architectures of the proposed methods. We evaluated their real-time performance on a low-cost, low-power Artix-7 35 T FPGA.
Tài liệu tham khảo
Scheirer, W.J., Jain, L.P., Boult, T.E.: Probability models for open set recognition. IEEE Trans. Pattern Anal. Mach. Intell. 36(11), 2317–2324 (2014). https://doi.org/10.1109/TPAMI.2014.2321392
Ghamisi, P., Plaza, J., Chen, Y., Li, J., Plaza, A.J.: Advanced spectral classifiers for hyperspectral images: a review. IEEE Geosci. Remote Sens. Mag. 5(1), 8–32 (2017). https://doi.org/10.1109/MGRS.2016.2616418
Khan, M.J., Khan, H.S., Yousaf, A., Khurshid, K., Abbas, A.: modern trends in hyperspectral image analysis: a review. IEEE Access 6, 14118–14129 (2018). https://doi.org/10.1109/ACCESS.2018.2812999
Gyaneshwar, D., Nidamanuri, R.R.: Low-complexity reconfigurable computing based online one-class classification using high-resolution hyperspectral imagery. In: 2021 IEEE International India Geoscience and Remote Sensing Symposium (InGARSS), pp. 33–36. IEEE
Gyaneshwar, D., Nidamanuri, R.R.: A novel supervised cascaded classifier system (SC2S) for robust remote sensing image classification. IEEE Geosci. Remote Sens. Lett. 18(3), 421–425 (2021). https://doi.org/10.1109/LGRS.2020.2980186
Tessier, R., Pocek, K., DeHon, A.: Reconfigurable computing architectures. Proc. IEEE 103(3), 332–354 (2015)
Gyaneshwar, D., Nidamanuri, R.R.: A real-time FPGA accelerated stream processing for hyperspectral image classification. Geocarto Int. 37(1), 52–69 (2022). https://doi.org/10.1080/10106049.2020.1713231
Júnior, P.R.M., et al.: Nearest neighbors distance ratio open-set classifier. Mach. Learn. 106(3), 359–386 (2017)
Farfan-Escobedo, J.D., Enciso-Rodas, L., Vargas-Muñoz, J.E.: Towards accurate building recognition using convolutional neural networks. In: 2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON), Cusco, Peru, pp. 1–4 (2017)
Homenda, W., Jastrzebska, A.: Global, local and embedded architectures for multiclass classification with foreign elements rejection: An overview. In: 2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR), pp. 89–94. https://doi.org/10.1109/SOCPAR.2015.7492789. (2015)
Schölkopf, B., Williamson, R.C., Smola, A.J., Shawe-Taylor, J., Platt, J.C.: Support vector method for novelty detection. In: Thirteenth Annual Neural Information Processing Systems Conference (NIPS 1999), pp. 582–588. MIT Press
Hu, W., Huang, Y., Wei, L., Zhang, F., Li, H.: Deep convolutional neural networks for hyperspectral image classification. J. Sens. (2015). https://doi.org/10.1155/2015/258619
Xilinx User Guide: Vivado Design Suite User Guide: Model-Based DSP Design using System Generator, UG897, v2016.1 ed. (2016)
Zhang, L.: System generator model-based FPGA design optimization and hardware co-simulation for Lorenz chaotic generator. In: 2017 2nd Asia-Pacific Conference on Intelligent Robot Systems (ACIRS), Wuhan, China, pp. 170–174 (2017)
SpaceNet on Amazon Web Services (AWS). "Datasets," The SpaceNet Catalog. https://spacenet.ai/datasets/. Accessed 18 Aug. 2020
Kemker, R., Salvaggio, C., Kanan, C.: Algorithms for semantic segmentation of multispectral remote sensing imagery using deep learning. ISPRS J. Photogramm. Remote. Sens. 145, 60–77 (2018)
Yokoya, N., Iwasaki, A.: Airborne hyperspectral data over Chikusei. Space Appl. Lab., Univ. Tokyo, Tokyo, Japan, Tech. Rep. SAL-2016–05–27 (2016)
Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. (TIST) 2(3), 27 (2011)