Smart City Gnosys

Smart city article details

Title Lightweight Uav Image Segmentation Model Design With Edge Feature Aggregation
ID_Doc 35283
Authors Yang F.; Jia L.; Purwanto E.; Smith J.; Man K.L.; Yue Y.
Year 2023
Published 2023 International Conference on Platform Technology and Service, PlatCon 2023 - Proceedings
DOI http://dx.doi.org/10.1109/PlatCon60102.2023.10255196
Abstract Nowadays, Unmanned Aerial Vehicles (UAVs) tend to become an attractable platform for smart city applications, especially for environmental sensing tasks. UAV downwards view image segmentation can extract meaningful information, but the challenge lies in segmenting small-size objects. This paper proposed a reasonable method where edge features were aggregated to enhance the performance of segmentation results, together with a suitable re-weighting method to alleviate the imbalance of interested object class distribution. The effectiveness of the designed network architecture was proven by experimental results that around a 2-4% increase of IoU for aimed small-size classes was achieved. Additionally, the proposed model remains in a lightweight structure. © 2023 IEEE.
Author Keywords Edge feature; Imbalanced classes; Lightweight model; Semantic segmentation; UAV image


Similar Articles


Id Similarity Authors Title Published
59303 View0.876Yi S.; Liu X.; Li J.; Chen L.Uavformer: A Composite Transformer Network For Urban Scene Segmentation Of Uav ImagesPattern Recognition, 133 (2023)
14461 View0.863Gupta B.B.; Gaurav A.; Chui K.T.; Arya V.; Wu J.Cloud-Based Image Segmentation Approach For Internet Of Drones (Iod)IEEE INFOCOM 2024 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2024 (2024)
2329 View0.852Yang W.; He Q.; Li Z.A Lightweight Multidimensional Feature Network For Small Object Detection On UavsPattern Analysis and Applications, 28, 1 (2025)