Fully-Automated Packaging Structure Recognition in Logistics Environments

Dörr, Laura; Brandt, Felix; Pouls, Martin; Naumann, Alexander

doi:10.1109/etfa46521.2020.9212152

Cited by 13 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They extend CornerNet [LD18] to support the detection of arbitrary four-cornered polygons, instead of axis-aligned bounding boxes. Their new model TetraPackNet shows significant improvements over a Mask R-CNN on the dataset presented in [Dör+20]. More precisely, the Mask AP increases from 58.7 to 75.5.…”

Section: Completeness and Occupancymentioning

confidence: 98%

See 1 more Smart Citation

Refined Plane Segmentation for Cuboid-Shaped Objects by Leveraging Edge Detection

Naumann

Dörr

Salscheider

et al. 2020

2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

Computer vision applications in transportation logisticsand warehousing have a huge potential for process automation. We present a structured literature review on research in the field to help leverage this potential. All literature is categorized w.r.t. the application, i.e. the task it tackles and w.r.t. the computer vision techniques that are used. Regarding applications, we subdivide the literature in two areas: Monitoring, i.e. observing and retrieving relevant information from the environment, and manipulation, where approaches are used to analyze and interact with the environment. In addition to that, we point out directions for future research and link to recent developments in computer vision that are suitable for application in logistics. Finally, we present an overview of existing datasets and industrial solutions. We conclude that while already many research areas have been investigated, there is still huge potential for future research. The results of our analysis are also available online at https://a-nau.github.io/cv-in-logistics.1 Verband der Automobilindustrie e.V. (VDA), see https://www.vda.de/en.

show abstract

Section: Completeness and Occupancymentioning

confidence: 98%

“…Dörr et al [Dör+20] developed a system for automated packaging structure recognition, where the goal is the localization of pallets and the analysis of their composition. They use a multi-step process: pallets are detected and for each pallet the side faces are segmented.…”

Section: Completeness and Occupancymentioning

confidence: 99%

Refined Plane Segmentation for Cuboid-Shaped Objects by Leveraging Edge Detection

Naumann

Dörr

Salscheider

et al. 2020

2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

show abstract

“…This approach was designed as an extension of a well-known NN called CornerNet [8]. Previously, in [9], the same authors implemented a pipeline consisting of a combination of segmentation algorithms. This pipeline detects the whole pallet unit and its number of visible stacked packaging boxes.…”

Section: Related Workmentioning

confidence: 99%

“…Unlike the works described above, our method is focused on detecting and recognising packaging loaded on pallets, and not on lumber platforms as described in [12,14,16]. Moreover, we use video sequences captured from an RGB camera with a bird's eye view configuration rather than a side view to detect the packing, as occurred in [7,9]. Our proposal is based on 2D techniques rather than 3D processing, as in [12,19,20], signifying that we require less computational complexity and there is less dependency on the camera type and its location.…”

Section: Related Workmentioning

confidence: 99%

MOSPPA: monitoring system for palletised packaging recognition and tracking

Castaño-Amorós

Fuentes²,

Gil³

2023

Int J Adv Manuf Technol

View full text Add to dashboard Cite

The paper industry manufactures corrugated cardboard packaging, which is unassembled and stacked on pallets to be supplied to its customers. Human operators usually classify these pallets according to the physical features of the cardboard packaging. This process can be slow, causing congestion on the production line. To optimise the logistics of this process, we propose a visual recognition and tracking pipeline that monitors the palletised packaging while it is moving inside the factory on roller conveyors. Our pipeline has a two-stage architecture composed of Convolutional Neural Networks, one for oriented pallet detection and recognition, and another with which to track identified pallets. We carried out an extensive study using different methods for the pallet detection and tracking tasks and discovered that the oriented object detection approach was the most suitable. Our proposal recognises and tracks different configurations and visual appearance of palletised packaging, providing statistical data in real time with which to assist human operators in decision-making. We tested the precision-performance of the system at the Smurfit Kappa facilities. Our proposal attained an Average Precision (AP) of 0.93 at 14 Frames Per Second (FPS), losing only 1% of detections. Our system is, therefore, able to optimise and speed up the process of logistic distribution.

show abstract

“…Chính vì vậy, việc xây dựng và áp dụng hệ thống phân loại bưu phẩm tự động dựa theo địa chỉ góp phần đem lại nhiều lợi ích cho doanh nghiệp chuyển phát nhanh, giúp giảm thời gian phân loại bưu phẩm, giảm tỷ lệ sai sót, giảm số lượng nhân công là vấn đề được nhiều doanh nghiệp Logistics chú trọng [6]. Hệ thống ứng dụng công nghệ AI với khả năng nhận diện chính xác tới 91% địa chỉ được in sẵn trên các bao bì thông thường, hàng hóa sẽ được chia theo các line riêng biệt [7]. Công nghệ kết nối IoT và AI để vận hành, kiểm tra, giám sát và quản lý dữ liệu từ xa giúp giám sát, phân tích và đưa ra những phương án về tình trạng hàng hóa giúp giải quyết các rủi ro nhanh chóng.…”

Section: Giới Thiệuunclassified

Hệ Thống Phân Loại Bưu Phẩm Tự Động Dựa Trên Công Nghệ Ai

Hằng¹

2022

TNUJST

View full text Add to dashboard Cite

Trong bài báo này, hệ thống phân loại bưu phẩm tự động được xây dựng dựa trên công nghệ AI nhằm tối ưu hóa quá trình phân loại sản phẩm, giảm tỉ lệ sai sót do nguyên nhân từ con người, giảm chi phí nhân công, rút ngắn thời gian giao hàng trong lĩnh vực logistic. Từ đó góp phần giúp các doanh nghiệp logistics tiết kiệm được chi phí, nâng cao chất lượng dịch vụ. Kết quả của hệ thống xây dựng bao gồm bộ phận nhận diện chữ in trên bao bì bưu phẩm để phân loại bưu phẩm theo địa chỉ, bộ phận xe tự hành AGV (Automatically Guided Vehicle) được điều khiển từ bộ phận AI thông qua kết nối WI-FI thực hiện vận chuyển bưu phẩm về từng khoang hàng cố định. Ngoài ra, hệ thống còn có phần mềm theo dõi có chức năng hiển thị vị trí xe tự hành, vị trí các kho hàng cũng như số lượng bưu phẩm trên từng khoang hàng.

show abstract

Fully-Automated Packaging Structure Recognition in Logistics Environments

Cited by 13 publications

References 10 publications

Refined Plane Segmentation for Cuboid-Shaped Objects by Leveraging Edge Detection

Refined Plane Segmentation for Cuboid-Shaped Objects by Leveraging Edge Detection

MOSPPA: monitoring system for palletised packaging recognition and tracking

Hệ Thống Phân Loại Bưu Phẩm Tự Động Dựa Trên Công Nghệ Ai

Contact Info

Product

Resources

About