Image search for simulator content creation

万维网包含数百亿张图片，个人和工业收藏的图片数量是这个数字的5倍。这些基于图像的资源的潜在经济价值是巨大的，但很大程度上尚未开发，因为我们没有实际的方法来恢复我们需要的图像。该项目将开发图像搜索技术，使澳大利亚工业能够利用这些重要资源。各种各样可能的应用可能包括搜索感兴趣对象的监控视频，无人驾驶车辆的基于视觉的引导，了解其环境的智能手机和智能家居系统，以及可以检测损坏的库存跟踪系统。

The World Wide Web contains tens of billions of images, with personal and industrial collections stretching to may times that number. The potential economic value of these image-based resources is enormous, but largely untapped as we have no practical way of recovering the images we need. This project will develop image search technologies which will allow Australian industry to exploit these important resources. Some of the wide variety of possible applications might include the searching of surveillance video for objects of interest, vision-based guidance of unmanned vehicles, smart-phone and smart-home systems which understand their environments, and stock tracking systems which can detect spoilage.