Boosting Aerial Object Detection Performance via Virtual Reality Data and Multi-Object Training-猫眼课题宝

DOI：

10.1109/ijcnn54540.2023.10191223

发表时间：

2023-06

期刊：

2023 International Joint Conference on Neural Networks (IJCNN)

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Nikolas Koutsoubis;Kyle Naddeo;Garrett Williams;George D. Lecakes;G. Ditzler;N. Bouaynaya;Thomas Kiel-Thomas

深度神经网络（DNN）架构，如R-CNN和YOLO，在对象检测任务中，在时间和准确性方面都表现出令人印象深刻的性能。然而，从数据和算法的角度来看，探测小型空中物体仍然具有挑战性。收集和注释视频以检测小型空中物体是一项耗时的任务，并且在向数据库添加新类别的物体时会很快成为负担。此外，目前DNN的目标函数并不是专门为较小的对象设计的。为了解决这些挑战，我们提出了一个虚拟现实（VR）数据集的空中物体检测，它可以生成大量的小物体的空中数据。通过将VR数据与真实数据相结合，我们能够提高空中目标检测的性能。我们还引入了一个从归一化Wasserstein距离导出的成本函数来代替YOLO的Intersection-over-Union损失。实验结果表明，VR数据集和归一化Wasserstein距离提高了最先进的目标检测方法在检测小型空中目标方面的性能。我们的源代码可在https://github.com/naddeok96/yolov7_mavrc上公开获取

Deep neural network (DNN) architectures, such as R-CNN and YOLO, have demonstrated impressive performance in object detection tasks with respect to both time and accuracy. However, detecting small aerial objects remains challenging from both a data and algorithmic perspective. Collecting and annotating videos to detect small aerial objects is a time-consuming task and can quickly become a burden when new classes of objects are added to a database. In addition, the current objective functions for DNNs are not specifically designed for smaller objects. To address these challenges, we propose a virtual reality (VR) dataset for aerial object detection, which can generate large volumes of small-object aerial data. By combining VR data with real-world data, we are able to improve the performance of aerial object detection. We also introduce a cost function derived from the normalized Wasserstein distance to replace the Intersection-over-Union loss for YOLO. Experimental results demonstrate that the VR dataset and normalized Wasserstein distance improve the performance of state-of-the-art object detection methods in detecting small aerial objects. Our source code is publicly available at https://github.com/naddeok96/yolov7_mavrc

Boosting Aerial Object Detection Performance via Virtual Reality Data and Multi-Object Training

文献摘要

相似文献