Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313387849> ?p ?o ?g. }
- W4313387849 endingPage "101849" @default.
- W4313387849 startingPage "101849" @default.
- W4313387849 abstract "Machine vision, especially deep learning methods, has become a hot topic for product surface inspection. In practice, capturing high quality images is a base for defect detection. It turns out to be challenging for complex products as image quality suffers from occlusion, illumination, and other issues. Multiple images from different viewpoints are often required in this scenario to cover all the important areas of the products. Reducing the viewpoints while ensuring the coverage is the key to make the inspection system more efficient in production. This paper proposes a high-efficient view planning method based on deep reinforcement learning to solve this problem. First, visibility estimation method is developed so that the visible areas can be quickly identified for a given viewpoint. Then, a new reward function is designed, and the Asynchronous Advantage Actor-Critic method is applied to solve the view planning problem. The effectiveness and efficiency of the proposed method is verified with a set of experiments. The proposed method could also be potentially applied to other similar vision-based tasks." @default.
- W4313387849 created "2023-01-06" @default.
- W4313387849 creator A5011747260 @default.
- W4313387849 creator A5015851984 @default.
- W4313387849 creator A5054692962 @default.
- W4313387849 creator A5074841730 @default.
- W4313387849 date "2023-01-01" @default.
- W4313387849 modified "2023-10-16" @default.
- W4313387849 title "High-efficient view planning for surface inspection based on parallel deep reinforcement learning" @default.
- W4313387849 cites W1926660750 @default.
- W4313387849 cites W1975551334 @default.
- W4313387849 cites W1989823960 @default.
- W4313387849 cites W2024304003 @default.
- W4313387849 cites W2031136219 @default.
- W4313387849 cites W2031367292 @default.
- W4313387849 cites W2072573184 @default.
- W4313387849 cites W2078505501 @default.
- W4313387849 cites W2113775403 @default.
- W4313387849 cites W2122301224 @default.
- W4313387849 cites W2122585444 @default.
- W4313387849 cites W2149458426 @default.
- W4313387849 cites W2333091233 @default.
- W4313387849 cites W2588607166 @default.
- W4313387849 cites W2613333231 @default.
- W4313387849 cites W2798026007 @default.
- W4313387849 cites W2801015586 @default.
- W4313387849 cites W2887685891 @default.
- W4313387849 cites W2893889064 @default.
- W4313387849 cites W2980773070 @default.
- W4313387849 cites W3000688900 @default.
- W4313387849 cites W3004109511 @default.
- W4313387849 cites W3004986231 @default.
- W4313387849 cites W3015335398 @default.
- W4313387849 cites W3027429685 @default.
- W4313387849 cites W3137986185 @default.
- W4313387849 cites W3194839486 @default.
- W4313387849 cites W3211776777 @default.
- W4313387849 cites W4285030313 @default.
- W4313387849 cites W813120406 @default.
- W4313387849 doi "https://doi.org/10.1016/j.aei.2022.101849" @default.
- W4313387849 hasPublicationYear "2023" @default.
- W4313387849 type Work @default.
- W4313387849 citedByCount "3" @default.
- W4313387849 countsByYear W43133878492023 @default.
- W4313387849 crossrefType "journal-article" @default.
- W4313387849 hasAuthorship W4313387849A5011747260 @default.
- W4313387849 hasAuthorship W4313387849A5015851984 @default.
- W4313387849 hasAuthorship W4313387849A5054692962 @default.
- W4313387849 hasAuthorship W4313387849A5074841730 @default.
- W4313387849 hasConcept C108583219 @default.
- W4313387849 hasConcept C111472728 @default.
- W4313387849 hasConcept C119857082 @default.
- W4313387849 hasConcept C120665830 @default.
- W4313387849 hasConcept C121332964 @default.
- W4313387849 hasConcept C123403432 @default.
- W4313387849 hasConcept C138885662 @default.
- W4313387849 hasConcept C142362112 @default.
- W4313387849 hasConcept C151319957 @default.
- W4313387849 hasConcept C153349607 @default.
- W4313387849 hasConcept C154945302 @default.
- W4313387849 hasConcept C177264268 @default.
- W4313387849 hasConcept C199360897 @default.
- W4313387849 hasConcept C2524010 @default.
- W4313387849 hasConcept C26517878 @default.
- W4313387849 hasConcept C2776035091 @default.
- W4313387849 hasConcept C2779530757 @default.
- W4313387849 hasConcept C31258907 @default.
- W4313387849 hasConcept C31972630 @default.
- W4313387849 hasConcept C33923547 @default.
- W4313387849 hasConcept C38652104 @default.
- W4313387849 hasConcept C41008148 @default.
- W4313387849 hasConcept C5339829 @default.
- W4313387849 hasConcept C90673727 @default.
- W4313387849 hasConcept C97541855 @default.
- W4313387849 hasConceptScore W4313387849C108583219 @default.
- W4313387849 hasConceptScore W4313387849C111472728 @default.
- W4313387849 hasConceptScore W4313387849C119857082 @default.
- W4313387849 hasConceptScore W4313387849C120665830 @default.
- W4313387849 hasConceptScore W4313387849C121332964 @default.
- W4313387849 hasConceptScore W4313387849C123403432 @default.
- W4313387849 hasConceptScore W4313387849C138885662 @default.
- W4313387849 hasConceptScore W4313387849C142362112 @default.
- W4313387849 hasConceptScore W4313387849C151319957 @default.
- W4313387849 hasConceptScore W4313387849C153349607 @default.
- W4313387849 hasConceptScore W4313387849C154945302 @default.
- W4313387849 hasConceptScore W4313387849C177264268 @default.
- W4313387849 hasConceptScore W4313387849C199360897 @default.
- W4313387849 hasConceptScore W4313387849C2524010 @default.
- W4313387849 hasConceptScore W4313387849C26517878 @default.
- W4313387849 hasConceptScore W4313387849C2776035091 @default.
- W4313387849 hasConceptScore W4313387849C2779530757 @default.
- W4313387849 hasConceptScore W4313387849C31258907 @default.
- W4313387849 hasConceptScore W4313387849C31972630 @default.
- W4313387849 hasConceptScore W4313387849C33923547 @default.
- W4313387849 hasConceptScore W4313387849C38652104 @default.
- W4313387849 hasConceptScore W4313387849C41008148 @default.
- W4313387849 hasConceptScore W4313387849C5339829 @default.
- W4313387849 hasConceptScore W4313387849C90673727 @default.