Generative Model With Coordinate Metric Learning for Object Recognition Based on 3D Models

Yida Wang; Weihong Deng

doi:10.1109/tip.2018.2858553

Generative Model With Coordinate Metric Learning for Object Recognition Based on 3D Models

IEEE Transactions on Image Processing ◽

10.1109/tip.2018.2858553 ◽

2018 ◽

Vol 27 (12) ◽

pp. 5813-5826 ◽

Cited By ~ 3

Author(s):

Yida Wang ◽

Weihong Deng

Keyword(s):

Object Recognition ◽

Metric Learning ◽

3D Models ◽

Generative Model

Download Full-text

A Generative Model for Multi Class Object Recognition and Detection

Artificial Intelligence and Neural Networks - Lecture Notes in Computer Science ◽

10.1007/11803089_4 ◽

2006 ◽

pp. 32-40

Author(s):

Ilkay Ulusoy

Keyword(s):

Object Recognition ◽

Generative Model

Download Full-text

An Automated Training of Deep Learning Networks by 3D Virtual Models for Object Recognition

Symmetry ◽

10.3390/sym11040496 ◽

2019 ◽

Vol 11 (4) ◽

pp. 496 ◽

Cited By ~ 7

Author(s):

Kamil Židek ◽

Peter Lazorík ◽

Ján Piteľ ◽

Alexander Hošovský

Keyword(s):

Deep Learning ◽

Object Recognition ◽

Augmented Reality ◽

3D Models ◽

Processing Unit ◽

Assembly Process ◽

Learning Networks ◽

Embedded Devices ◽

New Approach ◽

Virtual Models

Small series production with a high level of variability is not suitable for full automation. So, a manual assembly process must be used, which can be improved by cooperative robots and assisted by augmented reality devices. The assisted assembly process needs reliable object recognition implementation. Currently used technologies with markers do not work reliably with objects without distinctive texture, for example, screws, nuts, and washers (single colored parts). The methodology presented in the paper introduces a new approach to object detection using deep learning networks trained remotely by 3D virtual models. Remote web application generates training input datasets from virtual 3D models. This new approach was evaluated by two different neural network models (Faster RCNN Inception v2 with SSD, MobileNet V2 with SSD). The main advantage of this approach is the very fast preparation of the 2D sample training dataset from virtual 3D models. The whole process can run in Cloud. The experiments were conducted with standard parts (nuts, screws, washers) and the recognition precision achieved was comparable with training by real samples. The learned models were tested by two different embedded devices with an Android operating system: Virtual Reality (VR) glasses, Cardboard (Samsung S7), and Augmented Reality (AR) smart glasses (Epson Moverio M350). The recognition processing delays of the learned models running in embedded devices based on an ARM processor and standard x86 processing unit were also tested for performance comparison.

Download Full-text