期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 17, 期 4, 页码 2357-2364出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2020.3001147
关键词
Geometry-supervised pose network (GSPN); monocular camera; retail shelf pose dataset (RSPD); shelf pose estimation; smart retail industry
类别
资金
- National Natural Science Foundation of China [61866016, TII-20-0107]
The article discusses the impact of image quality on final analysis results in the smart retail industry and proposes a novel geometry-supervised pose network to estimate shelf poses. Additionally, a new retail shelf pose dataset (RSPD) is introduced, along with a complete 3-D shelf posture for training end-to-end networks. Experimental results show that the proposed GSPN achieves state-of-the-art performance on RSPD.
In the smart retail industry, the quality of image collection is known to heavily affect the final analysis results (like accuracy) of applications, such as commodity detection, identification, and stitching. In practice, images captured manually by a monocular camera like mobile phone contain many low-quality images caused by an irregular shoot step. After image collection, filtering out low-quality images is a key step to mitigate the aforementioned impacts. One of the most effective solutions is to filter images with huge off-angles in 3-D through the shelf pose estimation algorithm. However, most of the existing camera pose estimation algorithms are designed for natural scenes and are difficult to realize in the structured real target scenes (like shelf scenes). Meanwhile, due to the lack of shelf pose dataset in academia and industry, there is still no approach designed for the shelf pose estimation in the smart retail scenario. In this article, we try to regress the complete shelf pose within a single end-to-end network and propose a novel geometry-supervised pose network (GSPN), which supervises the shelf pose estimation by learning the intrinsically geometric properties of shelves. Furthermore, we introduce the first retail shelf pose dataset (RSPD), including 28 876 images selected from three different shelf categories and being annotated carefully, as well as a complete 3-D shelf posture. The whole networks can be trained end to end with the shelf images and well-annotated ground truth. Experiments result of five strategies show that GSPN achieves the state-of-the-art performance on RSPD.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据