Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313162183> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4313162183 abstract "Since instance segmentation are popular in the field of unmanned driving, object recognition and instance segmentation in the case of high ambiguity are lacking at the present stage, this paper compares the training results of mask-RCNN algorithm under normal conditions and low visibility with fuzzy conditions. Firstly, for the dataset part, video downloaded from YouTube and be divided into pictures frame by frame by video processing software, which are used as datasets under normal conditions. Then, images are blurred by Fourier transform, which are used as training sets under low visibility conditions. After that, the dataset needs to be normalization, which is to divide the pixel value of the picture by 255 and map them to 0-1 and to improve the training speed. Then we test the data through mask-RCNN, through the tensor Flow library, and train the results on Colabortary. And this algorithm is based on Feature Pyramid Network (FPN) and ResNet101 backbone. Meanwhile there is an Area of Interest (ROI) Pool layer that processes of different sizes into a uniform size output. Through the test of these two datasets, the results show that mask-RCNN's test accuracy can reach more than 99% under normal visibility, and the error rate is extremely low." @default.
- W4313162183 created "2023-01-06" @default.
- W4313162183 creator A5072827198 @default.
- W4313162183 date "2022-10-12" @default.
- W4313162183 modified "2023-10-09" @default.
- W4313162183 title "Robustness of Mask-RCNN at High Ambiguous Environments" @default.
- W4313162183 cites W2116973876 @default.
- W4313162183 cites W2127717018 @default.
- W4313162183 cites W2912420051 @default.
- W4313162183 cites W2962970995 @default.
- W4313162183 cites W2963150697 @default.
- W4313162183 cites W3011735758 @default.
- W4313162183 cites W4207020977 @default.
- W4313162183 doi "https://doi.org/10.1109/iccasit55263.2022.9986700" @default.
- W4313162183 hasPublicationYear "2022" @default.
- W4313162183 type Work @default.
- W4313162183 citedByCount "0" @default.
- W4313162183 crossrefType "proceedings-article" @default.
- W4313162183 hasAuthorship W4313162183A5072827198 @default.
- W4313162183 hasConcept C104317684 @default.
- W4313162183 hasConcept C120665830 @default.
- W4313162183 hasConcept C121332964 @default.
- W4313162183 hasConcept C123403432 @default.
- W4313162183 hasConcept C153180895 @default.
- W4313162183 hasConcept C154945302 @default.
- W4313162183 hasConcept C160633673 @default.
- W4313162183 hasConcept C185592680 @default.
- W4313162183 hasConcept C2776151529 @default.
- W4313162183 hasConcept C31972630 @default.
- W4313162183 hasConcept C41008148 @default.
- W4313162183 hasConcept C55493867 @default.
- W4313162183 hasConcept C63479239 @default.
- W4313162183 hasConcept C89600930 @default.
- W4313162183 hasConceptScore W4313162183C104317684 @default.
- W4313162183 hasConceptScore W4313162183C120665830 @default.
- W4313162183 hasConceptScore W4313162183C121332964 @default.
- W4313162183 hasConceptScore W4313162183C123403432 @default.
- W4313162183 hasConceptScore W4313162183C153180895 @default.
- W4313162183 hasConceptScore W4313162183C154945302 @default.
- W4313162183 hasConceptScore W4313162183C160633673 @default.
- W4313162183 hasConceptScore W4313162183C185592680 @default.
- W4313162183 hasConceptScore W4313162183C2776151529 @default.
- W4313162183 hasConceptScore W4313162183C31972630 @default.
- W4313162183 hasConceptScore W4313162183C41008148 @default.
- W4313162183 hasConceptScore W4313162183C55493867 @default.
- W4313162183 hasConceptScore W4313162183C63479239 @default.
- W4313162183 hasConceptScore W4313162183C89600930 @default.
- W4313162183 hasLocation W43131621831 @default.
- W4313162183 hasOpenAccess W4313162183 @default.
- W4313162183 hasPrimaryLocation W43131621831 @default.
- W4313162183 hasRelatedWork W2004370856 @default.
- W4313162183 hasRelatedWork W2090093270 @default.
- W4313162183 hasRelatedWork W2309573947 @default.
- W4313162183 hasRelatedWork W2497633036 @default.
- W4313162183 hasRelatedWork W2613186388 @default.
- W4313162183 hasRelatedWork W2739874619 @default.
- W4313162183 hasRelatedWork W4292829955 @default.
- W4313162183 hasRelatedWork W4312857205 @default.
- W4313162183 hasRelatedWork W2183878799 @default.
- W4313162183 hasRelatedWork W2187221949 @default.
- W4313162183 isParatext "false" @default.
- W4313162183 isRetracted "false" @default.
- W4313162183 workType "article" @default.