Comparative analysis of CNN-based smart pre‐trained models for object detection on DOTA

• Autorzy: Hashmi Hina , Dwivedi Rakesh Kumar , Kumar Anil

Identyfikatory

DOI

10.14313/JAMRIS/2‐2024/11

• Języki publikacji: EN

Abstrakty

EN

In this paper, we proposed a comparative research project on the classification of various objects in satellite images using some pre-trained models of CNN (VGG- 19, ResNet-50, Inception-V3, EfficientNet-B7) and R-CNN. In this research work, we have used the DOTA dataset, which combines data from 14 classes. We have imple- mented above-mentioned pre-trained models of CNN and R-CNN to achieve optimal results for accuracy as well as productivity in detection of various objects such as ships, tennis courts, swimming pools, vehicles, and harbors from remotely accessed images. In this study, a convolutional neural network (CNN) is used as the base model. For complex computations and for speeding up results, transfer learning is used. With the help of experimental analysis, we have discovered that R-CNN and Inception-V3 performed best out of the five pre-trained models

Słowa kluczowe

EN

remote sensing images; CNN; R-CNN; transfer learning; object detection

• Wydawca: Łukasiewicz Industrial Research Institute for Automation and Measurements PIAP
• Czasopismo: Journal of Automation Mobile Robotics and Intelligent Systems
• Rocznik: 2024
• Tom: Vol. 18, No. 2
• Strony: 31--45
• Opis fizyczny: Bibliogr. 41 poz., rys.

Twórcy

autor

Hashmi Hina

• College of Computing Sciences & Information Technology, Teerthanker Mahaveer University, Moradabad, 244001, India

autor

Dwivedi Rakesh Kumar

• College of Computing Sciences & Information Technology, Teerthanker Mahaveer University, Moradabad, 244001, India

autor

Kumar Anil

• Indian Institute of Remote Sensing (IIRS), Indian Space Research Organisation (ISRO), Dehradun, 248001, India

Bibliografia

• [1] M. Sharp, R. Ak, and T. Hedberg. “A survey of the advancing use and development of machine learning in smart manufacturing.” Journal of Manufacturing Systems, 48, 2018, 170–179. doi: 10.1016/j.jmsy.2018.02.004.
• [2] A. D. Preez, G. A. Oosthuizen. “Machine learning in cutting processes as enabler for smart sustainable manufacturing.” Procedia Manufacturing, 33, 2019, 810–817. doi: 10.1016/j.promfg.2019.04.102.
• [3] H. Hashmi, R. K. Dwivedi, A. Kumar, “Identifcation of Objects using AI & ML Approaches: State-of-the-Art,” 2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART), 2021, pp. 1–5, doi: 10.1109/SMART52563.2021.9676273.
• [4] H. Kumar, S. A. Hashmi, Khan and S. Kazim Naqvi, “SSE: A Smart Framework for Live Video Streaming based Alerting System,” 2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART), 2021, pp. 193–197, doi: 10.1109/SMART52563.2021. 9675306.
• [5] K. He, X. Zhang, S. Ren, J. Sun, “Deepresidual learning for image recognition,” in: CVPR, 2016.
• [6] R. Girshick, J. Donahue, T. Darrell, J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” in: CVPR, 2014.
• [7] M. Tan, Q. V. Le, “EfϐicientNet: Rethinking Model Scaling for Convolutional Neural Networks.” Proc. Mach. Learn. Res. 97, 2019, 6105–6114.
• [8] Pan, S. J., and Yang, Q. “A Survey on Transfer Learning.” IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, 2010, 1345–1359. doi: 10.1109/tkde.2009.191.
• [9] X. Sun et al., “Multi-type Microbial Relation Extraction by Transfer Learning,” 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Houston, TX, USA, 2021, pp. 266–269, doi: 10.1109/BIBM52615. 2021.9669738.
• [10] X. Wang, S. Liu and C. Zhou, “Classification of Knee Osteoarthritis Based on Transfer Learning Model and Magnetic Resonance Images,” 2022 International Conference on Machine Learning, Control, and Robotics (MLCR), Suzhou, China, 2022, pp. 67–71, doi: 10.1109/MLCR57210.2022.00021.
• [11] Z. Xia, J. Liu, X. Chen, X. Li, and P. Chen, “Airplane Object Detection in Satellite Images Based on Attention Mechanism and Multi-scale Feature Fusion,” 2022 4th International Conference on Robotics and Computer Vision (ICRCV), Wuhan, China, 2022, pp. 142–147, doi: 10.1109/ICRCV55858.2022.9953228.
• [12] C. B. Chittineni, “Edge and Line Detection in Multidimensional Noisy Imagery Data,” in IEEE ransactions on Geoscience and Remote Sensing, vol. GE-21, no. 2, pp. 163–174, April 1983, doi: 10.1109/TGRS.1983.350485.
• [13] S. Rong and B. Bhanu, “Modeling clutter and context for target detection in infrared images,” Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1996, pp. 106–113, doi: 10.1109/CVPR.1996.517061.
• [14] J. Ng and Shaogang Gong, “Multi-view face detection and pose estimation using a composite support vector machine across the view sphere,” Proceedings International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems. In Conjunction with ICCV’99 (Cat. No.PR00378), 1999, pp. 14–21, doi: 10.1109/RATFG.1999.799218.
• [15] P. Garnesson, G. Giraudon, and P. Montesinos, “An image analysis, application for aerial imagery interpretation,” [1990] Proceedings. 10th International Conference on Pattern Recognition, Atlantic City, NJ, USA, 1990, pp. 210–212, vol. 1, doi: 10.1109/ICPR.1990.118094.
• [16] Hsuan Ren and Chein-I Chang, “A computer-aided detection and classification method for concealed targets in hyperspectral imagery,” IGARSS ’98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat.No.98CH36174), 1998, pp. 1016–1018, vol. 2, doi: 10.1109/IGARSS.1998.699658.
• [17] J. A. Shufelt, “Performance evaluation and analysis of monocular building extraction from aerialimagery,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 4, pp.311–326, April 1999, doi: 10.1109/34.761262.
• [18] J. G. Shanks and B. V. Shetler, “Confronting clouds: detection, remediation and simulation approaches for hyperspectral remote sensing systems,” Proceedings 29th Applied Imagery Pattern Recognition Workshop, 2000, pp. 25–31, doi: 10.1109/AIPRW.2000.953599.
• [19] T. L. Haithcoat, W. Song, and J. D. Hipple, “Building footprint extraction and 3-D reconstruction from LIDAR data,” IEEE/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas (Cat. No.01EX482), 2001, pp. 74–78, doi: 10.1109/DFUA.2001.985730.
• [20] Keping Chen and R. Blong, “Extracting building features from high resolution aerial imagery for natural hazards risk assessment,” IEEE International Geoscience and Remote Sensing Symposium, 2002, pp. 2039–2041, vol. 4, doi: 10.1109/IGARSS.2002.1026437.
• [21] J. Secord and A. Zakhor, “Tree Detection in Urban Regions Using Aerial Lidar and Image Data,” in IEEE Geoscience and Remote Sensing Letters, vol. 4, no. 2, April 2007, pp. 196–200, doi:10.1109/LGRS.2006.888107.
• [22] D. Chaudhuri and A. Samal, “An Automatic Bridge Detection Technique for Multispectral Images,”in IEEE Transactions on Geoscience and Remote Sensing, vol. 46, no. 9, Sept. 2008, pp. 2720–2727, doi: 10.1109/TGRS.2008.923631.
• [23] C. S. Grant, T. K. Moon, J. H. Gunther, M. R. Stites and G. P. Williams, “Detection of Amorphously Shaped Objects Using Spatial Information Detection Enhancement (SIDE),” in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 5, no. 2, April 2012, pp. 478–487, doi: 10.1109/JSTARS.2012.2186284.
• [24] M. I. Elbakary and K. M. Iftekharuddin, “Shadow Detection of Man-Made Buildings in High-Resolution Panchromatic Satellite Images,” in IEEE Transactions on Geoscience and Remote Sensing, vol. 52, no. 9, Sept. 2014, pp. 5374–5386, doi: 10.1109/TGRS.2013.2288500.
• [25] Sevo and A. Avramović, “Convolutional Neural Network Based Automatic Object Detection on Aerial Images,” in IEEE Geoscience and Remote Sensing Letters, vol. 13, no. 5, May 2016, pp. 740–744, doi: 10.1109/LGRS.2016.2542358.
• [26] D. Yu, H. Guo, Q. Xu, J. Lu, C. Zhao, and Y. Lin, “Hierarchical Attention and Bilinear Fusion for Remote Sensing Image Scene Classification,” in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, 2020, pp. 6372–6383, doi: 10.1109/JSTARS.2020.3030257.
• [27] Y. Yu, T. Gu, H. Guan, D. Li and S. Jin, “Vehicle Detection from High-Resolution Remote Sensing Imagery Using Convolutional Capsule Networks,” in IEEE Geoscience and Remote Sensing Letters, vol. 16, no. 12, Dec. 2019, pp. 1894–1898, doi: 10.1109/LGRS.2019.2912582.
• [28] B. Vasu and A. Savakis, “Resilience and Plasticity of Deep Network Interpretations for Aerial Imagery,” in IEEE Access, vol. 8, 2020, pp. 127491–127506, doi: 10.1109/ACCESS.2020. 3008323.
• [29] X. Sun et al., “Multi-type Microbial Relation Extraction by Transfer Learning,” 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Houston, TX, USA, 2021, pp. 266–269, doi: 10.1109/BIBM52615. 2021.9669738.
• [30] B. Huang, X. Chen, Y. Sun, and W. He, “Multi-agent cooperative strategy learning method based on transfer Learning,” 2022 13th Asian Control Conference (ASCC), Jeju, Korea, Republic of, 2022, pp. 1095–1100, doi: 10.23919/ASCC56756.2022.9828357.
• [31] Zou and Q. Zhang, “eyeSay: Make Eyes Speak for ALS Patients with Deep Transfer Learning-Empowered Wearable,” 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Mexico, 2021, pp. 377–381, doi: 10.1109/EMBC46164.2021.9629874.
• [32] M. Thoreau and F. Wilson, “SaRNet: A Dataset for Deep Learning Assisted Search and Rescue with Satellite Imagery,” 2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA), Zagreb, Croatia, 2021, pp. 204–208, doi: 10.1109/ISPA52656.2021.9552103.
• [33] N. Dey, Y. D. Zhang, V. Rajinikanth, R. Pugalenthi, and N. S. M. Raja, “Customized VGG19 architecture for pneumonia detection in chest X-rays.” Pattern Recognition Letters, vol. 143, 2021, 67–74.
• [34] A. Bagaskara, M. Suryanegara, “Evaluation of VGG-16 and VGG-19 Deep Learning Architecture for Classifying Dementia People.” In 2021 4th International Conference of Computer and Informatics Engineering (IC2IE) (pp. 1–4). IEEE.
• [35] S. Mascarenhas, M. Agarwal, “A comparison between VGG16, VGG19 and ResNet50 architecture frameworks for Image Classification In 2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON) (vol. 1, pp. 96–99).IEEE.
• [36] B. Koonce, B. Koonce, B. “ResNet 50. Convolutional Neural Networks with Swift for Tensor-flow: Image Recognition and Dataset Categorization,” 2021, pp. 63–72.
• [37] M. G. D. Dionson, P. B. El Jireh, “Inception-V3 architecture in dermatoglyphics-based temperament classiϐication.” Philippine Social Science Journal, vol. 3, no. 2, 2020, pp. 173–174.
• [38] L. P. Kothala, L. P., and Guntur, S. R. (2022, December). Segmentation of Intracranial Hemorrhage through an EfficientNetB7-based UNET model. In 2022 International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON) (pp. 1–5). IEEE.
• [39] M. K. Islam, C. Kaushal, M. A. Amin, “Smart Home-Healthcare For Skin Lesions Classification With Iot Based Data Collection Device.” Kushtia, Bangladesh: Islamic University, 2021.
• [40] Y. W. Chao, S. Vijayanarasimhan, B. Seybold, D. A. Ross, J. Deng, R. Sukthankar, R. (2018). “Rethinking the faster r-cnn architecture for temporal action localization.” In Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. pp. 1130–1139.
• [41] P. Bharati, A. Pramanik, “Deep learning techniques—R-CNN to mask R-CNN: a survey.” Computational Intelligence in Pattern Recognition: Proceedings of CIPR,2020, pp. 657–668.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).