Obrada i analiza satelitskih video snimaka
Ključne reči:
Daljinska detekcija, satelitsko osmatranje, video signal, praćenje pokretnih objekata
Apstrakt
U radu je razmatrana analiza i obrada video snimaka Zemljine površine načinjenih sa senzorima slike postavljenim na satelitskim platfromama. Korišćene su video sekvence sa Jilin-1 satelita na kojima postoji značajna dinamika scene u vidu pokretnih objekata kao što su vozila, brodovi i avioni. Na primeru takvih snimaka analizirane su mogućnosti modela za praćenje pokretnih objekata koji se oslanjaju na arhitekturu sijamskih neuronskih mreža. Isti model za praćenje objekata kvalitativno je testiran, bez prethodnog prilagođavanja, i na lokalnim video sekvencama načinjenim sa dronom i ručnim kamerama.
Reference
[1] Zhao, Q., Yu, L., Du, Z., Peng, D., Hao, P., Zhang, Y., Gong, P. (2022). An overview of the applications of Earth observation satellite data: impacts and future trends. Remote Sensing, 14(8), 1863.
[2] Zhang, Z, Wang, C., J., & Xu, Y. (2022). Object Tracking based on satellite videos: A literature review. Remote Sensing, 14(15), 3674.
[3] Chen R, Ferreira G, Li X. Detecting Moving Vehicles from Satellite-Based Videos by Tracklet Feature Classification. Remote Sensing. 2023; 15(1):34.
[4] H. G, T. Blaschke, D. Marceau and A. Bouchard, A comparison of three image object methods for the multiscale analysis of landscape structure., International Journal of Photogrammetry and Remote Sensing, vol. 57, pp. 327-345, 2003.
[5] Li, Y., Jiao, L., Huang, Z., Zhang, X., Zhang, R., Song, X., & Li, L. (2022). Deep learning-based object tracking in satellite videos: A comprehensive survey with a new dataset. IEEE Geoscience and Remote Sensing Magazine, 10(4), 181-212.
[6] Zhang, Z., & Peng, H. (2019). Deeper and wider Siamese networks for real-time visual tracking. CVPR (pp. 4591-4600).
[7] xdai-dlgvv/SV248S, opensource satellite video datasets for object tracking: https://github.com/xdai-dlgvv/SV248S
[8] SiamDW/siamese_tracking: https://github.com/researchmm/SiamDW/tree/master/siamese_tracking
[2] Zhang, Z, Wang, C., J., & Xu, Y. (2022). Object Tracking based on satellite videos: A literature review. Remote Sensing, 14(15), 3674.
[3] Chen R, Ferreira G, Li X. Detecting Moving Vehicles from Satellite-Based Videos by Tracklet Feature Classification. Remote Sensing. 2023; 15(1):34.
[4] H. G, T. Blaschke, D. Marceau and A. Bouchard, A comparison of three image object methods for the multiscale analysis of landscape structure., International Journal of Photogrammetry and Remote Sensing, vol. 57, pp. 327-345, 2003.
[5] Li, Y., Jiao, L., Huang, Z., Zhang, X., Zhang, R., Song, X., & Li, L. (2022). Deep learning-based object tracking in satellite videos: A comprehensive survey with a new dataset. IEEE Geoscience and Remote Sensing Magazine, 10(4), 181-212.
[6] Zhang, Z., & Peng, H. (2019). Deeper and wider Siamese networks for real-time visual tracking. CVPR (pp. 4591-4600).
[7] xdai-dlgvv/SV248S, opensource satellite video datasets for object tracking: https://github.com/xdai-dlgvv/SV248S
[8] SiamDW/siamese_tracking: https://github.com/researchmm/SiamDW/tree/master/siamese_tracking
Objavljeno
2024-06-06
Sekcija
Elektrotehničko i računarsko inženjerstvo
