RI: Small: Performance Prediction and Validation for Object Recognition

RI：小型：对象识别的性能预测和验证

• 批准号: 0915270
• 负责人: Bir Bhanu
• 金额: $ 10万
• 依托单位: University of California-Riverside
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2009
• 资助国家: 美国
• 起止时间: 2009-10-01 至 2013-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0915270&HistoricalAwards=false
• 关键词: RI; Small; Performance; Prediction; Validation

This project brings together an interdisciplinary collaboration between Engineering and Statistics for developing the science for automated object recognition. Object recognition technology is pervasive in a broad range of applications, such as safety and law enforcement, defense and security, autonomous navigation, industrial manufacturing, business process and e-commerce. The proposed transformative research provides a foundational framework for predicting the performance of object recognition algorithms based on probabilities and structural characteristics of the models and data. In contrast to previous work, the proposed research considers not only the data distortion factors but also the model similarity. The performance is explicitly modeled as a function of data distortion factors (feature uncertainty, occlusion and clutter) and model factors (similarity) so that one can ultimately characterize the probability distribution of performance rather than the empirical results on a specific dataset. The research will focus in three areas: 1) Developing the Bayesian formulation of performance prediction and bounds on performance. 2) Analyzing the effects of all of the assumptions made in the performance prediction approach; evaluating the effects of mathematical tractability, complexity and the gain in performance and validating different assumptions based on real data. 3) Generating results of the approach for practical applications. The development of scientific theory, prediction and computational models for recognition will result in the development of systematic approaches to the design of recognition systems that can reliably achieve predictable results in complex real-world, and contribute towards the science of computer-based object recognition.

该项目汇集了工程和统计学之间的跨学科合作，以开发自动对象识别的科学。对象识别技术在广泛的应用中普遍存在，例如安全和执法，国防和安全，自动导航，工业制造，业务流程和电子商务。拟议的变革性研究提供了一个基本框架，用于根据模型和数据的概率和结构特征来预测对象识别算法的性能。与以前的工作相反，拟议的研究不仅考虑了数据失真因素，还考虑了模型相似性。该性能是明确建模的，是数据失真因子（特征不确定性，阻塞和混乱）和模型因子（相似性）的函数，以便最终可以表征性能的概率分布，而不是特定数据集中的经验结果。 该研究将重点放在三个领域：1）制定贝叶斯对性能预测和绩效界限的表述。 2）分析性能预测方法中所有假设的影响；评估数学障碍性，复杂性和性能增长的影响，并基于实际数据验证不同的假设。 3）为实用应用产生方法的结果。识别识别的科学理论，预测和计算模型的发展将导致发展系统的识别系统设计方法，这些方法可以可靠地在复杂的现实世界中可靠地实现可预测的结果，并为基于计算机的对象识别的科学做出了贡献。