Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313592046> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4313592046 endingPage "055011" @default.
- W4313592046 startingPage "055011" @default.
- W4313592046 abstract "Abstract Pointer meter automatic recognition (PMAR) in outdoor environments is a challenging task. Due to variable weather and uneven lighting factors, hand-crafted features or shallow learning techniques have low accuracy in meter recognition. In this paper, a multitask cascading convolutional neural network (MC-CNN) is proposed to improve the accuracy of meter recognition in outdoor environments. The proposed MC-CNN uses cascaded CNN, including three stages of meter detection, meter cropping and meter reading. Firstly, the YOLOV4 Network is used for meter detection to quickly determine the meter location from captured images. In order to accurately cluster pointer meter prior boxes in the YOLOV4 Network, an improved K-means algorithm is presented to further enhance the detection accuracy. Then, the detected meter images are cropped out of the captured images to remove redundant backgrounds. Finally, a meter-reading network based on an adaptive attention residual module (AARM) is proposed for reading meters from cropped images. The proposed AARM not only contains an attention mechanism to focus on essential information and efficiently diminish useless information, but also extracts information features from meter images adaptively. The experimental results show that the proposed MC-CNN can effectively achieve outdoor meter recognition, with high recognition accuracy and low relative error. The recognition accuracy can reach 92.6%. The average relative error is 2.5655%, which is about 3% less than the error in other methods. What is more, the proposed approach can obtain rich information about the type, limits, units and readings of the pointer meter and can be used when multiple pointer meters exist in one captured image simultaneously. Additionally, the proposed approach can significantly improve the accuracy of the recognized readings, and is also robust to natural environments." @default.
- W4313592046 created "2023-01-06" @default.
- W4313592046 creator A5011130685 @default.
- W4313592046 creator A5041998997 @default.
- W4313592046 creator A5047684739 @default.
- W4313592046 creator A5049341927 @default.
- W4313592046 creator A5053844560 @default.
- W4313592046 creator A5055349808 @default.
- W4313592046 creator A5056586913 @default.
- W4313592046 creator A5066083459 @default.
- W4313592046 date "2023-02-14" @default.
- W4313592046 modified "2023-10-18" @default.
- W4313592046 title "A multitask cascading convolutional neural network for high-accuracy pointer meter automatic recognition in outdoor environments" @default.
- W4313592046 cites W2471609828 @default.
- W4313592046 cites W2766144630 @default.
- W4313592046 cites W2806070179 @default.
- W4313592046 cites W2887293879 @default.
- W4313592046 cites W2904405026 @default.
- W4313592046 cites W2963037989 @default.
- W4313592046 cites W2963163009 @default.
- W4313592046 cites W2963918968 @default.
- W4313592046 cites W2970569803 @default.
- W4313592046 cites W2972566761 @default.
- W4313592046 cites W2974386388 @default.
- W4313592046 cites W2989852531 @default.
- W4313592046 cites W2998943318 @default.
- W4313592046 cites W3025611830 @default.
- W4313592046 cites W3110653358 @default.
- W4313592046 cites W3117495151 @default.
- W4313592046 cites W3130267610 @default.
- W4313592046 cites W3175873076 @default.
- W4313592046 cites W3210535920 @default.
- W4313592046 cites W4296998972 @default.
- W4313592046 cites W4309279743 @default.
- W4313592046 doi "https://doi.org/10.1088/1361-6501/acb003" @default.
- W4313592046 hasPublicationYear "2023" @default.
- W4313592046 type Work @default.
- W4313592046 citedByCount "2" @default.
- W4313592046 countsByYear W43135920462023 @default.
- W4313592046 crossrefType "journal-article" @default.
- W4313592046 hasAuthorship W4313592046A5011130685 @default.
- W4313592046 hasAuthorship W4313592046A5041998997 @default.
- W4313592046 hasAuthorship W4313592046A5047684739 @default.
- W4313592046 hasAuthorship W4313592046A5049341927 @default.
- W4313592046 hasAuthorship W4313592046A5053844560 @default.
- W4313592046 hasAuthorship W4313592046A5055349808 @default.
- W4313592046 hasAuthorship W4313592046A5056586913 @default.
- W4313592046 hasAuthorship W4313592046A5066083459 @default.
- W4313592046 hasConcept C108583219 @default.
- W4313592046 hasConcept C121332964 @default.
- W4313592046 hasConcept C1276947 @default.
- W4313592046 hasConcept C150202949 @default.
- W4313592046 hasConcept C151011524 @default.
- W4313592046 hasConcept C153180895 @default.
- W4313592046 hasConcept C154945302 @default.
- W4313592046 hasConcept C31972630 @default.
- W4313592046 hasConcept C41008148 @default.
- W4313592046 hasConcept C555944384 @default.
- W4313592046 hasConcept C76155785 @default.
- W4313592046 hasConcept C81363708 @default.
- W4313592046 hasConcept C93763578 @default.
- W4313592046 hasConceptScore W4313592046C108583219 @default.
- W4313592046 hasConceptScore W4313592046C121332964 @default.
- W4313592046 hasConceptScore W4313592046C1276947 @default.
- W4313592046 hasConceptScore W4313592046C150202949 @default.
- W4313592046 hasConceptScore W4313592046C151011524 @default.
- W4313592046 hasConceptScore W4313592046C153180895 @default.
- W4313592046 hasConceptScore W4313592046C154945302 @default.
- W4313592046 hasConceptScore W4313592046C31972630 @default.
- W4313592046 hasConceptScore W4313592046C41008148 @default.
- W4313592046 hasConceptScore W4313592046C555944384 @default.
- W4313592046 hasConceptScore W4313592046C76155785 @default.
- W4313592046 hasConceptScore W4313592046C81363708 @default.
- W4313592046 hasConceptScore W4313592046C93763578 @default.
- W4313592046 hasFunder F4320321001 @default.
- W4313592046 hasIssue "5" @default.
- W4313592046 hasLocation W43135920461 @default.
- W4313592046 hasOpenAccess W4313592046 @default.
- W4313592046 hasPrimaryLocation W43135920461 @default.
- W4313592046 hasRelatedWork W2731899572 @default.
- W4313592046 hasRelatedWork W2999805992 @default.
- W4313592046 hasRelatedWork W3011074480 @default.
- W4313592046 hasRelatedWork W3116150086 @default.
- W4313592046 hasRelatedWork W3133861977 @default.
- W4313592046 hasRelatedWork W3192840557 @default.
- W4313592046 hasRelatedWork W4200173597 @default.
- W4313592046 hasRelatedWork W4291897433 @default.
- W4313592046 hasRelatedWork W4312417841 @default.
- W4313592046 hasRelatedWork W4321369474 @default.
- W4313592046 hasVolume "34" @default.
- W4313592046 isParatext "false" @default.
- W4313592046 isRetracted "false" @default.
- W4313592046 workType "article" @default.