|
Automatic vehicle identification from Google Earth satellite images based on single shot deep learning neural networks for object detection
|
Mostafa Kabolizadeh *   , Mohammad Abbasi |
|
|
|
Abstract: (4357 Views) |
Road and urban transport network facilitate our daily life for optimal routing. In the road network, traffic management is one of the main challenges of managers. In this regard, the first step is to estimate the density of cars at the level of the urban road network. Estimating the number of cars or the level of occupancy of cars in the whole city, taking into account less time and cost, is only possible with satellite images. In this regard, in this research, satellite images with high spatial resolution available and downloadable from the Google Earth system have been used. To identify the position of the cars, the single shot deep learning method with RetinaNet architecture and based on residual neural networks with the number of layers 18, 34 and 50 have been used. For the training data, the position of the cars is marked with bounding boxes and then satellite images with dimensions of 128 x 128 pixels and 64 pixels pitch are cut. Of the total training data, 80% have been used for training and 20% for validation. The models were trained in 50 epochs and with an average accuracy of 0.7. Satellite images containing more than 15000 cars was used to evaluate the trained models. The parameter of the possibility of overlapping of the non-maximum suppression method was applied equal 25%. The final result shows that the use of the proposed model in the identification of cars has a good accuracy. The RetinaNet detector model based on the residual deep learning network with 50 layers has performed best in terms of average accuracy with 0.87, precision with 0.7, recall with 0.99 and F1-score with 0.82. The main challenge of the proposed models is in areas with high car density, which reduces the possibility of accurately detecting the number of cars due to the size of the ground sampling distance of satellite images, but it estimates the occupancy level better.
|
Article number: 2 |
| Keywords: deep learning, satellite images, RetinaNet, residual neural networks, Google Earth |
|
|
Full-Text [PDF 1238 kb]
(1350 Downloads)
|
Type of Study: Research |
Subject:
Photo&RS
Received: 2022/10/29 | Accepted: 2023/12/31
|
|
|
|
|
|
|
| References |
1. Benjdira, B., Khursheed, T., Koubaa, A., Ammar, A. and Ouni, K. (2018) "Car Detection using Unmanned Aerial Vehicles: Comparison between Faster R-CNN and YOLOv3." arXiv preprint arXiv:1812.10968. [ DOI:10.1109/UVS.2019.8658300] 2. Duarte, D., Nex, F., Kerle, N. and Vosselman, G. (2018) "Satellite Image Classification of Building Damages using Airborne and Satellite Image Samples in a Deep Learning Approach." Remote Sensing and Spatial Information Sciences, Riva del Garda, Italy, 4-7, Volume IV-2, PP. 89-96. [ DOI:10.5194/isprs-annals-IV-2-89-2018] 3. Audebert, N., Le Saux, B. and Lef'evre, S. (2017) "Segment-beforedetect: Vehicle detection and classification through semantic segmentation of aerial images." Remote Sens., vol. 9, no. 4, PP. 368. [ DOI:10.3390/rs9040368] 4. Yu, Y., Gu, T., Guan, H., Li, D. and S. Jin, (2019) "Vehicle detection from high-resolution remote sensing imagery using convolutional capsule networks." IEEE Geosci. Remote Sens. Lett., vol. 16, no. 12, PP. 1894-1898. [ DOI:10.1109/LGRS.2019.2912582] 5. Mattyus, G., Wang, S., Fidler, S. and Urtasun, R. (2015) "Enhancing roads maps by parsing aerial images around the world." In Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 7-13 December 2015; PP. 1689-1697. [ DOI:10.1109/ICCV.2015.197] 6. Chen, G., Wang, H., Chen, K., Li, Z., Song, Z., Liu, Y., Chen, W. and Knoll, A. (2020) "A survey of the four pillars for small object detection: Multiscale representation, contextual information, super-resolution, and region proposal." IEEE Transactions on Systems, Man, and Cybernetics: Systems. 7. Girshick, R., Donahue, J., Darrell, T., Malik, J. and Malik, J. (2014) "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation." In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 23-28; PP. 580-587. [ DOI:10.1109/CVPR.2014.81] 8. Ren, S., He, K., Girshick, R.B. and Sun, J. (2015) "Faster R-CNN: towards real-time object detection with region proposal networks." corr abs/1506.01497, arXiv preprint arXiv:1506.01497. 9. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, Y. and Berg, A. C. (2016) "SSD: Single shot multibox detector." in European conference on computer vision. Springer, PP. 21-37. [ DOI:10.1007/978-3-319-46448-0_2] 10. Redmon, S., Divvala, R., Girshick, A. and Farhadi, A. (2016) "You only look once: Unified, real-time object detection," in Proceedings of the IEEE conference on computer vision and pattern recognition, PP. 779-788. [ DOI:10.1109/CVPR.2016.91] 11. Lin, T.Y., Goyal, P., Girshick, R., He, K. and Doll'ar, P. (2017) "Focal loss for dense object detection," in Proceedings of the IEEE international conference on computer vision, PP. 2980-2988. [ DOI:10.1109/ICCV.2017.324] 12. Yang, M.Y., Liao, W., LI, X. and Rosenhahn, B. (2018) "Deep learning for vehicle detection in aerial images." In: Proceedings of the IEEE International Conference on Image Processing (ICIP). PP. 3079-3083. [ DOI:10.1109/ICIP.2018.8451454] 13. Douillard, A. (2020) "Detecting Cars from Aerial Imagery for the NATO Innovation Challenge." Available online: https://arthurdouillard.com/post/nato-challenge/. 14. Stuparu, D.G., Ciobanu, R.I. and Dobre, C. (2020) "Vehicle Detection in Overhead Satellite Images Using a One-Stage Object Detection Model." Sensors, 20, 6485. [ DOI:10.3390/s20226485] 15. Van Etten, A. (2019) "Satellite imagery multiscale rapid detection with windowed networks." In Proceedings of the 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa Village, HI, USA, 7-11, PP. 735-743. [ DOI:10.1109/WACV.2019.00083] 16. He, K., Zhang, X., Ren, S. and Sun, J. (2015) "Deep residual learning for image recognition." arXiv preprint arXiv:1512.03385, 2016. [ DOI:10.1109/CVPR.2016.90] 17. Lin, T.Y., Doll'ar, P., Girshick, R., He, K., Hariharan, B. and Belongie, S. (2017) "Feature pyramid networks for object detection." in Proceedings of the IEEE conference on computer vision and pattern recognition, PP. 2117-2125. [ DOI:10.1109/CVPR.2017.106] 18. Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll'ar P. and Zitnick, C.L. (2014) "Microsoft coco: Common objects in context", In European Conference on Computer Vision; Springer: Berlin/Heidelberg, Germany, pp. 740-755. [ DOI:10.1007/978-3-319-10602-1_48] 19. Ren, S., He, K., Girshick, R. and Sun, J. (2017) "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks." IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149. [ DOI:10.1109/TPAMI.2016.2577031] 20. Mansour, A., Hassan, A., Hussein, W. and Said, E. (2019) "Automated vehicle detection in satellite images using deep learning", 18th International Conference on Aerospace Sciences & Aviation Technology, 610(1):012027. doi:10.1088/1757-899X/610/1/012027 [ DOI:10.1088/1757-899X/610/1/012027] |
|
| Send email to the article author |
|
|
|
| Add your comments about this article |
|
|
|
|
Kabolizadeh M, Abbasi M. Automatic vehicle identification from Google Earth satellite images based on single shot deep learning neural networks for object detection. , JGST. 2023; 13 (2) : 2 URL: http://jgst.issgeac.ir/article-1-1120-en.html
|
