首页> 外文会议>SPIE Defense + Commercial Sensing Conference;Society of Photo-Optical Instrumentation Engineers >Generating synthetic imagery of complex scenes from ideal synthetic source imagery via MSERs on entropy imagery
【24h】

Generating synthetic imagery of complex scenes from ideal synthetic source imagery via MSERs on entropy imagery

机译:通过MSER在熵图像上从理想的合成源图像生成复杂场景的合成图像

获取原文

摘要

Synthetic imagery generation is not a new topic; however, it has reemerged as a major focus in recent years. Thisis in part due to the success achieved by modern machine learning methodologies, in particular, deep learning.One reason these technologies have succeeded is due to the wealth of available training data. A majority ofthe available data are of generic objects or scenes. However, there are numerous applications in which dataare neither readily available nor easily obtained in large quantities. In such scenarios, synthetic imagery is anappealing choice to address this shortcoming. While still faster than the performance of data collections, physics-based models tend to have computational complexity and require extensive computational time. This work seeksto investigate the use of reduced-order modeling (ROM) of relevant objects identied by a maximally stableextremal region (MSER) detector from the entropy image of simple ideal high-delity, physics-based syntheticimages. Specically, this work will utilize MSERs to identify pertinent objects to be placed within the simplescene via ROM to produce a more complex scene. This approach has the benet of rapidly increasing both thecomplexity of simple, ideal, high-delity, physics-based scenes and the amount of synthetic imagery generatedvia random or statistically-based placement of the objects throughout the scene.
机译:合成图像的生成不是一个新话题。然而,近年来它又重新成为主要焦点。这 部分原因是现代机器学习方法(尤其是深度学习)取得了成功。 这些技术成功的原因之一是由于大量可用的培训数据。大多数 可用数据来自通用对象或场景。但是,在许多应用程序中,数据 既不容易获得也不容易大量获得。在这种情况下,合成图像是一种 吸引人的选择来解决此缺点。尽管仍然比数据收集的性能要快,但是物理- 基于模型的模型往往具有计算复杂性,并且需要大量的计算时间。这项工作寻求 调查使用最大稳定度标识的相关对象的降阶建模(ROM)的使用 简单理想的高清晰度,基于物理的合成的熵图像中的极值区域(MSER)检测器 图片。具体来说,这项工作将利用MSER来识别要放置在简单对象中的相关对象 通过ROM生成更复杂的场景。这种方法的好处是可以迅速增加 简单,理想,高清晰度,基于物理的场景的复杂性以及生成的合成图像的数量 通过整个场景中对象的随机或基于统计的放置。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号