In the field of traffic sign recognition,traffic signs usually occupy very small areas in the input image.Most object detection algorithms directly reduce the original image to a specific size for the input model duri...In the field of traffic sign recognition,traffic signs usually occupy very small areas in the input image.Most object detection algorithms directly reduce the original image to a specific size for the input model during the detection process,which leads to the loss of small object information.Addi-tionally,classification tasks are more sensitive to information loss than local-ization tasks.This paper proposes a novel traffic sign recognition approach,in which a lightweight pre-locator network and a refined classification network are incorporated.The pre-locator network locates the sub-regions of the traffic signs from the original image,and the refined classification network performs the refinement recognition task in the sub-regions.Moreover,an innovative module(named SPP-ST)is proposed,which combines the Spatial Pyramid Pool module(SPP)and the Swin-Transformer module as a new feature extractor to learn the special spatial information of traffic sign effec-tively.Experimental results show that the proposed method is superior to the state-of-the-art methods(82.1 mAP achieved on 218 categories in the TT100k dataset,an improvement of 19.7 percentage points compared to the previous method).Moreover,both the result analysis and the output visualizations further demonstrate the effectiveness of our proposed method.The source code and datasets of this work are available at https://github.com/DijiesitelaQ/TSOD.展开更多
This paper focuses on the statistical characteristics of the 3D MHD equations.We firstly establish an existence theorem of a Vishik-Fursikov measure of the 3D MHD equations by taking advantage of the Krein-Milman theo...This paper focuses on the statistical characteristics of the 3D MHD equations.We firstly establish an existence theorem of a Vishik-Fursikov measure of the 3D MHD equations by taking advantage of the Krein-Milman theorem along with some functional and measure theories.Then by applying the Topsoe lemma on the constructed trajectory space possessing some special topological properties,we show that the Vishik-Fursikov measure and the stationary Vishik-Fursikov statistical solution of the 3D MHD system are approximated by the counterparts of the 3D MHD-αsystem,respectively,as the parameterαdecreases to zero.展开更多
Most results on the polynomial-like iterative equation are given under the condition that the given function is monotone,while a work by L.Liu and X.Gong gets nonmonotone PM solutions with height 1 when the given func...Most results on the polynomial-like iterative equation are given under the condition that the given function is monotone,while a work by L.Liu and X.Gong gets nonmonotone PM solutions with height 1 when the given function is of the same case.Removing the condition on height for the given function,we first give a method to assert the nonexistence of C^(0)solutions,then present equivalent conditions for the existence of PM solutions with finite height.Finally,as an application of the equivalent conditions,we construct the PM solutions in the case that the given function has one fort.展开更多
基金supported by the Natural Science Foundation of Sichuan,China (No.2022NSFSC0571)the Sichuan Science and Technology Program (No.2018JY0273,No.2019YJ0532)+1 种基金supported by funding of V.C.&V.R.Key Lab of Sichuan Province (No.SCVCVR2020.05VS)supported by the China Scholarship Council (No.201908510026).
文摘In the field of traffic sign recognition,traffic signs usually occupy very small areas in the input image.Most object detection algorithms directly reduce the original image to a specific size for the input model during the detection process,which leads to the loss of small object information.Addi-tionally,classification tasks are more sensitive to information loss than local-ization tasks.This paper proposes a novel traffic sign recognition approach,in which a lightweight pre-locator network and a refined classification network are incorporated.The pre-locator network locates the sub-regions of the traffic signs from the original image,and the refined classification network performs the refinement recognition task in the sub-regions.Moreover,an innovative module(named SPP-ST)is proposed,which combines the Spatial Pyramid Pool module(SPP)and the Swin-Transformer module as a new feature extractor to learn the special spatial information of traffic sign effec-tively.Experimental results show that the proposed method is superior to the state-of-the-art methods(82.1 mAP achieved on 218 categories in the TT100k dataset,an improvement of 19.7 percentage points compared to the previous method).Moreover,both the result analysis and the output visualizations further demonstrate the effectiveness of our proposed method.The source code and datasets of this work are available at https://github.com/DijiesitelaQ/TSOD.
基金supported by the National Natural Science Foundation of China(Grant No.12171343)the Sichuan Science and Technology Program(Grant No.2022JDTD0019).
文摘This paper focuses on the statistical characteristics of the 3D MHD equations.We firstly establish an existence theorem of a Vishik-Fursikov measure of the 3D MHD equations by taking advantage of the Krein-Milman theorem along with some functional and measure theories.Then by applying the Topsoe lemma on the constructed trajectory space possessing some special topological properties,we show that the Vishik-Fursikov measure and the stationary Vishik-Fursikov statistical solution of the 3D MHD system are approximated by the counterparts of the 3D MHD-αsystem,respectively,as the parameterαdecreases to zero.
基金supported by the Natural Science Foundation of Shandong Province(ZR2017MA019)the Scientific Research Fund of Binzhou University(BZXYL1802)+2 种基金supported by the National Science Foundation of China(11501394)the Science Research Fund of Sichuan Provincial Education Department(15ZB0041)funding of School of Mathematical Sciences and V.C.&V.R.Key Lab of Sichuan Province。
文摘Most results on the polynomial-like iterative equation are given under the condition that the given function is monotone,while a work by L.Liu and X.Gong gets nonmonotone PM solutions with height 1 when the given function is of the same case.Removing the condition on height for the given function,we first give a method to assert the nonexistence of C^(0)solutions,then present equivalent conditions for the existence of PM solutions with finite height.Finally,as an application of the equivalent conditions,we construct the PM solutions in the case that the given function has one fort.