SkyDataNet: An object detection algorithm with 2D gaussian loss for UAV-based aerial images

Name: SkyDataNet: An object detection algorithm with 2D gaussian loss for UAV-based aerial images
Author: Ozer, S., Begen, Ali C., Ozkanoglu, M. A.

İsim	SkyDataNet: An object detection algorithm with 2D gaussian loss for UAV-based aerial images
Yazar	Ozer, S., Begen, Ali C., Ozkanoglu, M. A.
Basım Tarihi:	2024-01-01
Basım Yeri	- IEEE
Konu	2D gaussian heatmap, Single-stage detectors, UAV, Aerial imagery, Object detection
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	979-8-3503-5143-9
Kayıt Numarası	47f24443-7c40-4876-b2a9-07e66102be0f
Lokasyon	Computer Science
Tarih	2024-01-01
Notlar	TÜBİTAK
Örnek Metin	In 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.
DOI	10.1109/MIPR62202.2024.00011

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

SkyDataNet: An object detection algorithm with 2D gaussian loss for UAV-based aerial images

Yazar Ozer, S., Begen, Ali C., Ozkanoglu, M. A.

Basım Tarihi 2024-01-01

Basım Yeri - IEEE

Konu 2D gaussian heatmap, Single-stage detectors, UAV, Aerial imagery, Object detection

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 979-8-3503-5143-9

Kayıt Numarası 47f24443-7c40-4876-b2a9-07e66102be0f

Lokasyon Computer Science

Tarih 2024-01-01

Notlar TÜBİTAK

Örnek Metin In 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.

DOI 10.1109/MIPR62202.2024.00011