Mandira M. D.,
Kesanapalli Lakshmi Priyanka,
K. Vamshi Krishna,
- Student Department of Computer Science and Engineering, Rashtreeya Vidyalaya College of Engineering (RVCE), Bengaluru Karnataka India
- Student Department of Computer Science and Engineering, Rashtreeya Vidyalaya College of Engineering (RVCE), Bengaluru Karnataka India
- Associate Professor Department of Computer Science and Engineering, Rashtreeya Vidyalaya College of Engineering (RVCE), Bengaluru Karnataka India
Abstract
The development of the Multi U-Net engineering marks an essential headway in geospatial question location inside ethereal symbolism investigation. The altered U-Net addresses the complexities of multi-class division in assorted geospatial settings. Leveraging the inalienable growing and contracting pathways inside U-Net plans, the Multi U-Net exceeds expectations in capturing complicated spatial data, in this manner setting up a vigorous establishment for exact division. The extend envelops an advanced picture handling pipeline joining Min-Max scaling for information normalization and Patchify for fine-grained conservation of spatial subtle elements, optimizing profound learning show preparation. Assessment measurements just like the Jaccard coefficient give exact bits of knowledge into spatial coherence, and misfortune capacities amalgamating Central Misfortune and Dice Misfortune guides proficient show preparing. The results emphasize Multi U-Net’s adeptness in taking care of particular question categories, minimizing untrue positives and negatives, and illustrating versatility over different datasets. Changes in division assessment exactness imply its potential benefits over applications such as natural observing, calamity administration, and urban arranging. This investigate contributes essentially to the domain of geographic question recognizable proof by showing an arrangement with striking upgrades to demonstrate execution, inventive engineering, and mastery in multi-class division.
Keywords: Geospatial Object Detection, Semantic Segmentation, Multi-Unet, Satellite Imagery.
[This article belongs to Journal of Image Processing & Pattern Recognition Progress(joipprp)]
References
- Dabra A, Kumar V. Evaluating green cover and open spaces in informal settlements of Mumbai using deep learning. Neural Computing and Applications. 2023 Jun;35(16):11773-88.
- Giang TL, Dang KB, Le QT, Nguyen VG, Tong SS, Pham VM. U-Net convolutional networks for mining land cover classification based on high-resolution UAV imagery. Ieee Access. 2020 Oct 19;8:186257-73.
- Kilic E, Ozturk S. An accurate car counting in aerial images based on convolutional neural networks. Journal of Ambient Intelligence and Humanized Computing. 2023 Feb 1:1-10.
- Li C, Yang T, Zhu S, Chen C, Guan S. Density map guided object detection in aerial images. Inproceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops 2020 (pp. 190-191).
- Dalal AA, Shao Y, Alalimi A, Abdu A. Mask R-CNN for geospatial object detection. International Journal of Information Technology and Computer Science (IJITCS). 2020;12(5):63-72.
- Ardeshir S, Zamir AR, Torroella A, Shah M. GIS-assisted object detection and geospatial localization. InComputer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VI 13 2014 (pp. 602-617). Springer International Publishing.
- Yu D, Ji S. A new spatial-oriented object detection framework for remote sensing images. IEEE Transactions on Geoscience and Remote Sensing. 2021 Nov 10;60:1-6.
- V Vasanth, Darnesh DP, Arya Kumar Jena.GEOSPATIAL OBJECT DETECTION USING AERIAL IMAGERY, International Research Journal of Modernization in Engineering Technology and Science . 2024;6(1):860-864.
- Zhang Z, Wang C, Song J, Xu Y. Object tracking based on satellite videos: A literature review. Remote Sensing. 2022 Jul 31;14(15):3674.
- Shen Y, Liu D, Chen J, Wang Z, Wang Z, Zhang Q. On-board multi-class geospatial object detection based on convolutional neural network for High Resolution Remote Sensing Images. Remote Sensing. 2023 Aug 10;15(16):3963.
Journal of Image Processing & Pattern Recognition Progress
| Volume | 11 |
| Issue | 02 |
| Received | June 5, 2024 |
| Accepted | July 3, 2024 |
| Published | July 9, 2024 |