Oriented R-CNN With Disentangled Representations for Product Packaging Detection
Object detection is a vital task in the field of computer vision for various applications such as face detection, autonomous driving and industrial production. In recent years, with the rise of deep neural networks, there has been significant progress in improving object detection accuracy. However,...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Photonics Journal |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10648834/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591177202794496 |
|---|---|
| author | Jiangyi Pan Jianjun Yang Yinhao Liu Yijie Lv |
| author_facet | Jiangyi Pan Jianjun Yang Yinhao Liu Yijie Lv |
| author_sort | Jiangyi Pan |
| collection | DOAJ |
| description | Object detection is a vital task in the field of computer vision for various applications such as face detection, autonomous driving and industrial production. In recent years, with the rise of deep neural networks, there has been significant progress in improving object detection accuracy. However, despite the state-of-the-art methods being tested on public datasets, there still remains a considerable gap when applied to real-world scenarios. This is because there are many unknown types of damaged samples in industrial object detection, the scale of the types varies greatly and the position changes are complex. Many previous works focus on rotating object detection and improve it, but this paper mainly combines the prior knowledge in remote sensing and industrial scenes, and the research is more general. To fill the shortage of wrapper datasets, we established a Carton Packing Tape (CPT) Dataset with a large scale of images only containing cartons. Specifically, we first collect a large number of images of packaged cartons from the real packaging production line and provide detection boxes for them by manual labeling. We have observed that the contextual clues required for different object detection tasks exhibit inconsistency. Furthermore, targets in varying backgrounds necessitate different receptive fields, which can be dynamically adjusted using different convolutional kernels. The features naturally attended to by these receptive fields of different scales should possess a unified representation disentanglement. Based on these insights, we propose a pioneering object detection method tailored for industrial environments, termed as oriented R-CNN with disentangled representations (ORDR). The experimental results indicate that our proposed method outperforms better than some of the state-of-the-art detection techniques available. |
| format | Article |
| id | doaj-art-92e475e4550541189e3b9c0b9fca2dea |
| institution | Kabale University |
| issn | 1943-0655 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Photonics Journal |
| spelling | doaj-art-92e475e4550541189e3b9c0b9fca2dea2025-01-23T00:00:11ZengIEEEIEEE Photonics Journal1943-06552024-01-0116511110.1109/JPHOT.2024.345029510648834Oriented R-CNN With Disentangled Representations for Product Packaging DetectionJiangyi Pan0https://orcid.org/0009-0004-8812-8312Jianjun Yang1Yinhao Liu2Yijie Lv3https://orcid.org/0000-0003-4702-2533Meizhou Cigarette Factory, China Tobacco Guangdong Industrial Company, Ltd., Meizhou, ChinaInner Mongolia Kunming Cigarette Co., Ltd., Hohhot, ChinaInstitute of Artificial Intelligence, Xiamen University, Xiamen, ChinaSchool of Computer Science and Technology, Shandong University of Technology, Zibo, ChinaObject detection is a vital task in the field of computer vision for various applications such as face detection, autonomous driving and industrial production. In recent years, with the rise of deep neural networks, there has been significant progress in improving object detection accuracy. However, despite the state-of-the-art methods being tested on public datasets, there still remains a considerable gap when applied to real-world scenarios. This is because there are many unknown types of damaged samples in industrial object detection, the scale of the types varies greatly and the position changes are complex. Many previous works focus on rotating object detection and improve it, but this paper mainly combines the prior knowledge in remote sensing and industrial scenes, and the research is more general. To fill the shortage of wrapper datasets, we established a Carton Packing Tape (CPT) Dataset with a large scale of images only containing cartons. Specifically, we first collect a large number of images of packaged cartons from the real packaging production line and provide detection boxes for them by manual labeling. We have observed that the contextual clues required for different object detection tasks exhibit inconsistency. Furthermore, targets in varying backgrounds necessitate different receptive fields, which can be dynamically adjusted using different convolutional kernels. The features naturally attended to by these receptive fields of different scales should possess a unified representation disentanglement. Based on these insights, we propose a pioneering object detection method tailored for industrial environments, termed as oriented R-CNN with disentangled representations (ORDR). The experimental results indicate that our proposed method outperforms better than some of the state-of-the-art detection techniques available.https://ieeexplore.ieee.org/document/10648834/Deep learningobject detectionproduct packagingrepresentation disentanglement |
| spellingShingle | Jiangyi Pan Jianjun Yang Yinhao Liu Yijie Lv Oriented R-CNN With Disentangled Representations for Product Packaging Detection IEEE Photonics Journal Deep learning object detection product packaging representation disentanglement |
| title | Oriented R-CNN With Disentangled Representations for Product Packaging Detection |
| title_full | Oriented R-CNN With Disentangled Representations for Product Packaging Detection |
| title_fullStr | Oriented R-CNN With Disentangled Representations for Product Packaging Detection |
| title_full_unstemmed | Oriented R-CNN With Disentangled Representations for Product Packaging Detection |
| title_short | Oriented R-CNN With Disentangled Representations for Product Packaging Detection |
| title_sort | oriented r cnn with disentangled representations for product packaging detection |
| topic | Deep learning object detection product packaging representation disentanglement |
| url | https://ieeexplore.ieee.org/document/10648834/ |
| work_keys_str_mv | AT jiangyipan orientedrcnnwithdisentangledrepresentationsforproductpackagingdetection AT jianjunyang orientedrcnnwithdisentangledrepresentationsforproductpackagingdetection AT yinhaoliu orientedrcnnwithdisentangledrepresentationsforproductpackagingdetection AT yijielv orientedrcnnwithdisentangledrepresentationsforproductpackagingdetection |