Ozkanoglu, Mehmet AkifBegen, Ali C.Ozer, Sedat2025-02-212025-02-212025-01-09https://hdl.handle.net/11693/116560Conference Name:2024 Ieee 7th Internatıonal Conference On Multımedıa Informatıon Processıng And Retrıeval, Mıpr 2024Date of Conference:AUG 07-09, 2024In this paper, we introduce a novel object detection algorithm based on the center-point detection. In our architecture, we introduce using two HourGlass architecture as the backbone, and we introduce using a new module to unify the predictions made after each backbone. Furthermore, since bounding boxes are in varying aspect ratios, as opposed to using a scalar Gaussian variance, we introduce using 2D variance in the Gaussian loss function to predict center-points in our network. We present the performance of our proposed improvements on three aerial datasets by comparing them to center-point based detection algorithms.EnglishObject detectionaerial imageryUAVsingle-stage detectors2D Gaussian heatmapConference Paper10.1109/MIPR62202.2024.00011979-8-3503-5142-22770-4319