Oriented object detection: edge models vs. cloud architectures
DOI:
https://doi.org/10.17979/ja-cea.2026.47.13834Palabras clave:
Aprendizaje autom´atico, Procesamiento de im´agenes, Robots a´ereos, Percepci´on y sensado, Sistemas embebidos de control, UAVsResumen
La detección de objetos en imágenes aéreas capturadas por drones requiere modelos capaces de localizar objetos con orientaciones arbitrarias y, al mismo tiempo, funcionar bajo las limitaciones de cómputo propias del procesamiento a bordo. Este trabajo evalúa once modelos de detección de objetos orientados de las familias YOLO-OBB, RTMDet, RoI Transformer y Strip R-CNN. La comparación considera tanto la precisión de detección como métricas relevantes para su uso en escenarios reales, como velocidad de procesamiento, tamaño del modelo y coste computacional. La evaluación se realiza sobre parches solapados del dataset DOTA v1.0. Los modelos se comparan mediante mAP y F1-Score ponderado usando umbrales de confianza seleccionados en el subconjunto de calibración. Los resultados muestran que los modelos de mayor capacidad, como YOLOv11x-OBB y RTMDet-l, son los candidatos m´as adecuados para inferencia en la nube, mientras que las variantes YOLO nano y RTMDet-tiny ofrecen distintos compromisos para el procesamiento en el borde.
Referencias
Cai, X., Lai, Q., Wang, Y., Wang, W., Sun, Z., Yao, Y., 2024. Poly kernel inception network for remote sensing detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 27706–27716.
Ding, J., Xue, N., Long, Y., Xia, G.-S., Lu, Q., 2019. Learning RoI transformer for oriented object detection in aerial images. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 2849–2858.
Ding, J., Xue, N., Xia, G.-S., Bai, X., Yang, W., Yang, M. Y., Belongie, S., Luo, J., Datcu, M., Pelillo, M., et al., 2021. Object detection in aerial images: A large-scale benchmark and challenges. IEEE transactions on pattern analysis and machine intelligence 44 (11), 7778–7796.
Gill, S. S., Golec, M., Hu, J., Xu, M., Du, J., Wu, H., Walia, G. K., Murugesan, S. S., Ali, B., Kumar, M., et al., 2025. Edge AI: A taxonomy, systematic review and future directions. Cluster Computing 28 (1), 18.
Li, Y., Hou, Q., Zheng, Z., Cheng, M.-M., Yang, J., Li, X., 2023. Large selective kernel network for remote sensing object detection. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 16794–16805.
Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll´ar, P., 2017. Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision. pp. 2980–2988.
Lyu, C., Zhang, W., Huang, H., Zhou, Y., Wang, Y., Liu, Y., Zhang, S., Chen, K., 2022. RTMDet: An empirical study of designing real-time object detectors. arXiv preprint arXiv:2212.07784.
NVIDIA, 2026. NVIDIA TensorRT Documentation. https://docs.nvidia.com/deeplearning/tensorrt/latest/index.html, accessed: 2026-05-30.
Redmon, J., Divvala, S., Girshick, R., 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.
Reilly, V., Idrees, H., Shah, M., 2010. Detection and tracking of large number of targets in wide area surveillance. In: European conference on computer vision. Springer, pp. 186–199.
Ren, S., He, K., Girshick, R., Sun, J., 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28.
Sadgrove, E. J., Falzon, G., Miron, D., Lamb, D. W., 2018. Real-time object detection in agricultural/remote environments using the multiple-expert colour feature extreme learning machine (MEC-ELM). Computers in Industry 98, 183–191.
Tang, G., Ni, J., Zhao, Y., Gu, Y., Cao,W., 2023. A survey of object detection for uavs based on deep learning. Remote Sensing 16 (1), 149. Ultralytics, 2026. Ultralytics documentation. https://docs.ultralytics.com/, accessed: 2026-05-30.
Xia, G.-S., Bai, X., Ding, J., Zhu, Z., Belongie, S., Luo, J., Datcu, M., Pelillo, M., Zhang, L., 2018. DOTA: A large-scale dataset for object detection in aerial images. In: Proceedings of the IEEE conference on computer visión and pattern recognition. pp. 3974–3983.
Xu, Y., Fu, M., Wang, Q., Wang, Y., Chen, K., Xia, G.-S., Bai, X., 2020. Gliding vertex on the horizontal bounding box for multi-oriented object detection. IEEE transactions on pattern analysis and machine intelligence 43 (4), 1452–1459.
Yuan, X., Zheng, Z., Li, Y., Liu, X., Liu, L., Li, X., Hou, Q., Cheng, M.-M., 2026. Strip R-CNN: Large strip convolution for remote sensing object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 40. pp. 12259–12267.
Yuan, Y., Gao, S., Zhang, Z.,Wang,W., Xu, Z., Liu, Z., 2024. Edge-cloud collaborative UAV object detection: Edge-embedded lightweight algorithm design and task offloading using fuzzy neural network. IEEE Transactions on Cloud Computing 12 (1), 306–318.
Zhou, Y., Yang, X., Zhang, G., Wang, J., Liu, Y., Hou, L., Jiang, X., Liu, X., Yan, J., Lyu, C., et al., 2022. MMRotate: A rotated object detection benchmark using pytorch. In: Proceedings of the 30th ACM international conference on multimedia. pp. 7331–7334.
Zhu, H., Chen, X., Dai, W., Fu, K., Ye, Q., Jiao, J., 2015. Orientation robust object detection in aerial images using deep convolutional neural network. In: 2015 IEEE international conference on image processing (ICIP). IEEE, pp. 3735–3739.
Zhu, P., Wen, L., Bian, X., Ling, H., Hu, Q., 2018. Vision meets drones: A challenge. arXiv preprint arXiv:1804.07437.
Descargas
Publicado
Número
Sección
Licencia
Derechos de autor 2026 Eri Pérez Corral, Enrique Alegre Gutiérrez, Christopher Gaul, Milad Mirjalili, Waqar Tanveer
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
