SBIR Phase I: Augmented Reality (AR) Web Commerce for Footware Retailers

小型企业创新研究(SBIR)第一阶段项目的更广泛影响/商业潜力是使鞋类零售商能够允许消费者在其电子商务网站上虚拟试穿产品。研究表明，对于超过66%的电子商务购物者来说，产品合身和外观是重要的参数。这一研究和开发工作为消费者提供了一种便利，可以很容易地通过现有的电子商务网站来实现。这项技术允许客户使用智能手机摄像头测量自己的脚码，而不需要应用程序。该项目开发并商业化了一种新型的增强现实(AR)电子商务平台，使零售商能够为客户提供独特的、身临其境的在线产品试穿购物体验，减少库存消耗，提供从现有电子商务网站到增强现实(AR)商务平台的无缝转换，为客户满意、提高销售额、减少回报和降低销售成本做出贡献。这个小型企业创新研究(SBIR)第一阶段项目将采用人工智能、机器学习、增强现实(AR)和3D建模解决方案来创建电子商务平台，将实体产品无缝转换为可在所有智能设备上运行的3D模型。成功的产品将在图像叠加方面提供高水平的性能和精度。解决方案必须确保AR模型以轻量级3D可视化和95%的准确率确保瞬间推理覆盖和跟踪流，以适应真实世界。如果成功，拟议的AR商务平台可能适用于包括零售和医疗行业在内的各种应用。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is to enable footwear retailers to allow consumers to virtually try-on products on their eCommerce websites. Research suggests product fit and look are important parameters for over 66% of eCommerce shoppers. This research and development effort provides a convenicence for consumers that is readily implemented by existing eCommerce site. The technology allow customers to measure their foot size using a smartphone camera without a need for an app. The project develops and commercializes a novel Augmented Reality (AR) eCommerce platform, enabling retailers to offer customers unique and immersive online product-try-on shopping experiences instantly, reduces inventory instory, provides seamless conversion of existing e-Commerce websites to AR-enabled commerce platforms contributing to satisfied customers, higher sales, reduced returns, and decreased cost per sale.This Small Business Innovation Research (SBIR) Phase I project will employ artificial intelligence, machine learning, augmented realiity (AR), and 3D modelling solutions to create eCommerce platforms that convert physical products into 3D models that work on all smart devices seamlessly. The successful product will provide high levels of performance and precision in the superimposition of images. Solution must ensure that the AR model ensures split second inference overlays and tracking streams with lightweight 3D visualizations and 95% accuracy to fit into the real world. If successful, the proposed AR Commerce platform may be applicable to a variety of applications including retail and medical industries.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.