A Dataset for 3D Object Recognition in Industry

Journal Title: GRD Journal for Engineering - Year 2018, Vol 3, Issue 0

Abstract

We introduce the 3D Object Detection Dataset, public dataset for 3D object detection and pose estimation with a strong focus on objects, settings, and requirements that are realistic for industrial setups. Contrary to other 3D object detection datasets that often represent scenarios from everyday life or mobile robotic environments, our setup models industrial bin picking and object inspection tasks that often face different challenges. Additionally, the evaluation citeria are focused on practical aspects, such as runtimes, memory consumption, useful correctness measurements, and accuracy. The dataset contains 28 objects with different characteristics, arranged in over 800 scenes and labelled with around 3500 rigid 3D transformations of the object instances as ground truth. Two industrial 3D sensors and three high-resolution grayscale cameras observe the scene from different angles, allowing to evaluate methods that operate on a variety of different modalities. We initially evaluate 5 different methods on the dataset. Even though some show good results, there is plenty of room for improvement. The dataset and the results are publicly available and we invite others to submit results for evaluation and for optional inclusion in the result lists on the dataset’s website.

Authors and Affiliations

Ashwini . G, Deeptha Nivetha J

Keywords

Related Articles

Optimization of Cylindrical Grinding Machine Parameters for Minimum Surface Roughness and Maximum MRR

Cylindrical grinding is very important process to improve quality of the component and to get precision dimensions with smooth surface finish. In the manufacturing sector, producing smooth surface finish plays an importa...

A Detailed Study On Car-Free City And Conversion Of Existing Cities And Suburbs To The Car-Free Model

Manufacture and use of cars are increasing day by day. This is creating environmental, social and aesthetic issues that we never imagined in last few decades. These problems force urban planners to think and design the c...

Comparative Study of GFRP Rebar and Steel Rebar used in Concrete Sections

The main problem encountered in steel reinforced concrete structures is the corrosion of the steel bars which eventually results in the failure and disintegration of the structure. Fiber-reinforced polymer (FRP) rebar ha...

Design and Thermal Analysis of 250cc Engine Cylinder Fin by using Different Materials

The 250 cc engine is well-known mechanical component used for power generation, but this is subjected to very high temperature and thermal stresses. Therefore cooling of engine is essential. For this purpose we have two...

Applications of Google Glass-Review

Google Glass is a brand of smart glasses - an optical head-mounted display designed in the shape of a pair of eyeglasses. It was developed by X (previously Google X) with the mission of producing a ubiquitous computer. I...

Download PDF file
  • EP ID EP295320
  • DOI -
  • Views 96
  • Downloads 0

How To Cite

Ashwini . G, Deeptha Nivetha J (2018). A Dataset for 3D Object Recognition in Industry. GRD Journal for Engineering, 3(0), 17-25. https://europub.co.uk/articles/-A-295320