FEATURE Machine Vision
New method allows robot vision to identify hidden objects
Much like human vision, the new robot-vision method allows for the detection of visible, partially occluded and unseen objects in a single framework
R
obotic vision has come a long way, reaching a level of sophistication with applications in complex and demanding tasks, such as autonomous driving and object manipulation. However, it still struggles to identify individual objects in cluttered scenes, where some objects are partially or completely hidden behind others.
When artifi cial intelligence systems encounter scenes where objects are not fully visible, they have to make estimations based only on the object’s visible parts. This partial information leads to detection errors, and large training data is required to correctly recognise such scenes. Now, researchers at the Gwangju Institute of Science and Technology have developed a framework that allows robot vision to detect objects successfully in the same way that we perceive them. “We expect a robot to recognise and manipulate objects they have not encountered before or been trained to
12 July/August 2022 | Automation
recognise. In reality, however, we need to manually collect and label data one by one as the object classifi cation of deep neural networks depends highly on the quality and quantity of the training dataset,” said Seunghyeok Back of Gwangju Institute of Science and Technology (GIST) in Korea, who works on this project. The GIST research team led by Associate
Professor Kyoobin developed a model called “Unseen Object Amodal Instance Segmentation” (UOAIS) for detecting occluded objects in cluttered scenes. To train the model in identifying object geometry, the team created a database of some 45,000 photorealistic synthetic images containing depth information. With this (limited) training data, the model was able to detect a variety of occluded objects. Upon encountering a cluttered scene, it fi rst picked out the object of interest and then determined if the object is occluded by segmenting it into a “visible mask” and an “amodal mask”. “Previous methods are limited to either detecting only specifi c types of objects or detecting only the visible regions without explicitly reasoning over occluded areas.
By contrast, our method can infer the hidden regions of occluded objects like a human vision system. This enables a reduction in data collection eff orts while improving performance in a complex environment,” said Back. To enable occlusion reasoning in their system, the researchers introduced a “Hierarchical Occlusion Modelling” (HOM) scheme, which assigned a hierarchy to the combination of multiple extracted features and their prediction order. By testing their model against three benchmarks, they validated the eff ectiveness of the HOM scheme, which achieved excellent performance. The researchers are hopeful about the
future prospects of their method. “Perceiving unseen objects in a cluttered
environment is essential for amodal robotic manipulation. Our UOAIS method could serve as a baseline here,” said Back.
http://www.gist.ac.kr/ CONTACT:
GIST
automationmagazine.co.uk
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64
