Object category recognition with large training sets

大型训练集的物体类别识别

• 批准号: 36807-2011
• 负责人: Lowe, David
• 金额: $ 3.57万
• 依托单位: University of British Columbia
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2012
• 资助国家: 加拿大
• 起止时间: 2012-01-01 至 2013-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=513423
• 关键词: Object; category; recognition; large; training

An important long-term goal for the field of computer vision is to enable a computer to recognize broad categories of objects (for example bicycles, cows, or people) whenever they appear in images. While this seems effortless for a person, the current performance of computer vision systems remains far below that of human vision. The solution to this problem is important for numerous applications, such as automobile driver assistance, image search on the web, or aids to the visually impaired. We believe that a major reason for the limited performance of existing systems is that they use inadequate training data. This research will develop approaches for working with far larger training sets of images, such as tens of thousands of images per image category rather than the few hundred currently used. This will require new learning methods and fast algorithms for scaling up to large amounts of data. We will achieve other improvements in scalability by developing new approaches to feature selection, in which only a small subset of the best potential visual features are selected for each particular discrimination task. Our research group has already developed some widely used software for speeding up similar problems, such as the Fast Library for Approximate Nearest Neighbours (FLANN). We intend to build on our expertise in these areas to exploit large sets of diverse local features and scale training set sizes by at least two orders of magnitude over current capabilities. Preliminary experiments indicate that this will give a large improvement in the accuracy of recognition and enable many new applications of importance to society.

计算机视觉领域的一个重要的长期目标是使计算机能够在图像中出现广泛类别的对象(例如自行车、奶牛或人)时识别它们。虽然这对一个人来说似乎毫不费力，但目前计算机视觉系统的性能仍然远远低于人类视觉。这个问题的解决方案对于许多应用都很重要，例如汽车驾驶员辅助、网络图像搜索或视障人士辅助工具。我们认为，现有系统性能有限的一个主要原因是它们使用了不充分的训练数据。这项研究将开发处理更大的图像训练集的方法，例如每个图像类别有数万张图像，而不是目前使用的数百张。这将需要新的学习方法和快速算法来扩展到大量数据。我们将通过开发新的特征选择方法来实现可伸缩性的其他改进，在这种方法中，只为每个特定的辨别任务选择最好的潜在视觉特征的一小部分。我们的研究小组已经开发了一些广泛使用的软件来加快类似问题的速度，例如近似最近邻快速库(FLANN)。我们打算在这些领域的专业知识的基础上，利用大量不同的地方特征，并将训练集的规模扩大至少两个数量级，超过目前的能力。初步实验表明，这将大大提高识别的准确率，并使许多新的社会应用具有重要意义。