butterflydetector
Current state-of-the-art object detectors have achieved high performance when applied to images captured by standard front facing cameras. When applied to high-resolution aerial images captured from a drone or UAV stand-point, they fail to generalize to the wide range of objects' scales. In order to address this limitation, we propose an object detection method called Butterfly Detector that is tailored to detect objects in aerial images. We extend the concept of fields and introduce butterfly fields, a type of composite field that describes the spatial information of output features as well as the scale of the detected object. To overcome occlusion and viewing angle variations that can hinder the localization process, we employ a voting mechanism between related butterfly vectors pointing to the object center. We evaluate our Butterfly Detector on two publicly available UAV datasets (UAVDT and VisDrone2019) and show that it outperforms previous state-of-the-art methods while remaining real-time.
Python
Library
Description
Current state-of-the-art object detectors have achieved high performance when applied to images captured by standard front facing cameras. When applied to high-resolution aerial images captured from a drone or UAV stand-point, they fail to generalize to the wide range of objects' scales. In order to address this limitation, we propose an object detection method called Butterfly Detector that is tailored to detect objects in aerial images. We extend the concept of fields and introduce butterfly fields, a type of composite field that describes the spatial information of output features as well as the scale of the detected object. To overcome occlusion and viewing angle variations that can hinder the localization process, we employ a voting mechanism between related butterfly vectors pointing to the object center. We evaluate our Butterfly Detector on two publicly available UAV datasets (UAVDT and VisDrone2019) and show that it outperforms previous state-of-the-art methods while remaining real-time.
Date Created
2020-03-20T00:00:00.000Z
Date Updated
2023-04-20T00:00:00.000Z
Feature List
Citation DOI
https://doi.org/10.1016/j.trc.2023.104181
Application Category
Related Images
Programming languages
Accessible for free
No
Producers
Persons and Organizations are temporally plot on the same table. This will be divided in two tables.
Maintainers
