DyViR: dynamic virtual reality dataset for aerial threat object detection

DyViR: dynamic virtual reality dataset for aerial threat object detection
复制标题

DyViR:用于空中威胁物体检测的动态虚拟现实数据集

DOI:
10.1117/12.2663417
复制
发表时间:
2023
期刊:
and Applications
影响因子:
--
通讯作者:
Bouaynaya, Nidhal
Bouaynaya, Nidhal
中科院分区:
--
文献类型:
--
作者:
Williams, Garrett;Lecakes, George;Almon, Amanda;Koutsoubis, Nikolas;Naddeo, Kyle;Kiel, Thom;Ditzler, Gregory;Bouaynaya, Nidhal

文献摘要

参考文献

相似文献

无人作战飞行器(即无人机)正在改变现代地缘政治舞台的监视、安全和冲突格局。各种技术和解决方案可以帮助跟踪无人机;每种技术在无人机尺寸和探测范围方面都有不同的优点和局限性。机器学习 (ML) 可以自动实时检测和跟踪无人机,同时取代人类水平的准确性并提供增强的态势感知。不幸的是,机器学习的力量取决于数据的质量和数量。在无人机检测任务场景中,有限的数据集提供了有限的环境变化、视角、视角距离和无人机类型。我们开发了一款名为 DyViR 的可定制软件工具,可生成大型合成视频数据集,用于训练空中威胁物体检测的机器学习算法。这些数据集包含用户指定的动态模拟生物群落(即北极、沙漠和森林)内空中物体的视频和音频渲染。用户可以在时间轴上改变环境,从而在综合生成的数据集中改变无人机飞行模式和天气条件等行为。 DyViR 支持额外的控制,例如运动模糊、抗锯齿和全动态移动摄像机,以跨多个视角生成图像。每个空中物体的分类(无人机或飞机)和边界框数据会自动导出到逗号分隔值 (CSV) 文件和视频,以形成合成数据集。我们通过在这些合成数据集上训练实时 YOLOv7-tiny 模型来展示 DyViR 的价值。与未使用 DyViR 的对象检测模型相比,对象检测模型的性能提高了 60.4%。这一结果提出了合成数据集的用例,以克服空中威胁物体检测的现实世界训练数据的缺乏。
Unmanned combat aerial vehicles (i.e., drones), are changing the modern geopolitical stage’s surveillance, security, and conflict landscape. Various technologies and solutions can help track drones; each technology has different advantages and limitations concerning drone size and detection range. Machine learning (ML) can automatically detect and track drones in real-time while superseding human-level accuracy and providing enhanced situational awareness. Unfortunately, ML’s power depends on the data’s quality and quantity. In the drone detection task scenario, limited datasets provide limited environmental variation, view angle, view distance, and drone type. We developed a customizable software tool called DyViR that generates large synthetic video datasets for training machine learning algorithms in aerial threat object detection. These datasets contain video and audio renderings of aerial objects within user-specified dynamic simulated biomes (i.e., arctic, desert, and forest). Users can alter the environment on a timeline allowing changes to behaviors such as drone flight patterns and weather conditions across a synthetically generated dataset. DyViR supports additional controls such as motion blur, anti-aliasing, and fully dynamic moving cameras to produce imagery across multiple viewing angles. Each aerial object’s classification (drone or airplane) and bounding box data automatically exports to a comma-separated-value (CSV) file and a video to form a synthetic dataset. We demonstrate the value of DyViR by training a real-time YOLOv7-tiny model on these synthetic datasets. The performance of the object detection model improved by 60.4% over its counterpart not using DyViR. This result suggests a use-case of synthetic datasets to surmount the lack of real-world training data for aerial threat object detection.
用于实时动画的基于物理的区域照明模型
DOI: 10.1007/978-3-319-46418-3_7
发表时间: 2016
影响因子: 8.9
作者:
M. Olejnik;D. Szajerman;P. Napieralski
通讯作者: P. Napieralski
DOI: --
发表时间: 2019-01
期刊: --
影响因子: --
作者:
A. Burkov
通讯作者: A. Burkov
利用卷积神经网络实现可见光和热成像无人机监控
DOI: 10.1017/atsip.2018.30
发表时间: 2018
影响因子: 3.2
作者:
Yeon;Yueru Chen;Jongmoo Choi;C.
通讯作者: C.
具有时间一致性的增强现实非真实感渲染框架
DOI: 10.1109/ismar.2012.6402552
发表时间: 2012
期刊: 2012 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)
影响因子: --
作者:
Jiajian Chen;Greg Turk;B. MacIntyre
通讯作者: B. MacIntyre
自动将电子表格转换为机器学习数据格式
DOI: 10.1007/978-3-030-01768-2_30
发表时间: 2018
影响因子: --
作者:
Gust Verbruggen;L. D. Raedt
通讯作者: L. D. Raedt