PVANet(performance vs accuracy network)卷积神经网络用于小目标检测的检测能力较弱.针对这一瓶颈问题,采用对PVANet网络的浅层特征提取层、深层特征提取层和HyperNet层(多层特征信息融合层)进行改进的措施,提出了一种适用于小目标物...PVANet(performance vs accuracy network)卷积神经网络用于小目标检测的检测能力较弱.针对这一瓶颈问题,采用对PVANet网络的浅层特征提取层、深层特征提取层和HyperNet层(多层特征信息融合层)进行改进的措施,提出了一种适用于小目标物体检测的改进PVANet卷积神经网络模型,并在TT100K(Tsinghua-Tencent 100K)数据集上进行了交通标志检测算法验证实验.结果表明,所构建的卷积神经网络具有优秀的小目标物体检测能力,相应的交通标志检测算法可以实现较高的准确率.展开更多
A closed form solution to the problem of segmenting multiple 3D motion models was proposed from straight-line optical flow. It introduced the multibody line optical flow constraint (MLOFC), a polynomial equation relat...A closed form solution to the problem of segmenting multiple 3D motion models was proposed from straight-line optical flow. It introduced the multibody line optical flow constraint (MLOFC), a polynomial equation relating motion models and line parameters. The motion models can be obtained analytically as the derivative of the MLOFC at the corresponding line measurement, without knowing the motion model associated with that line. Experiments on real and synthetic sequences were also presented.展开更多
This paper proposes a support vector machine-based fuzzy rules acquisition system(SVM-FRAS) .The character of SVM in extracting support vector provides a mechanism to extract fuzzy If-Then rules from the training data...This paper proposes a support vector machine-based fuzzy rules acquisition system(SVM-FRAS) .The character of SVM in extracting support vector provides a mechanism to extract fuzzy If-Then rules from the training data set.We construct the fuzzy inference system using fuzzy basis function(FBF) .The gradient technique is used to tune the fuzzy rules and the inference system.Theoretical analysis and comparative tests are performed comparing with other fuzzy systems.Experimental results show the SVM-FRAS model possesses good generalization capability as well as high comprehensibility.展开更多
基金奥地利Austrian Research Promotion Agency(FFG)基金“RoboCar”项目(861000)
文摘PVANet(performance vs accuracy network)卷积神经网络用于小目标检测的检测能力较弱.针对这一瓶颈问题,采用对PVANet网络的浅层特征提取层、深层特征提取层和HyperNet层(多层特征信息融合层)进行改进的措施,提出了一种适用于小目标物体检测的改进PVANet卷积神经网络模型,并在TT100K(Tsinghua-Tencent 100K)数据集上进行了交通标志检测算法验证实验.结果表明,所构建的卷积神经网络具有优秀的小目标物体检测能力,相应的交通标志检测算法可以实现较高的准确率.
基金The National Natural Science Foundation of China (No. 60675017) The National Basic Research Program (973) of China (No. 2006CB303103)
文摘A closed form solution to the problem of segmenting multiple 3D motion models was proposed from straight-line optical flow. It introduced the multibody line optical flow constraint (MLOFC), a polynomial equation relating motion models and line parameters. The motion models can be obtained analytically as the derivative of the MLOFC at the corresponding line measurement, without knowing the motion model associated with that line. Experiments on real and synthetic sequences were also presented.
基金the Shanghai Sciences and Technology Committee under Grant No.08DZ1202500 (No.08DZ1202502)the Young Faculty Research Grant of Shanghai Maritime Universitythe Shanghai Young Faculty Research Grant (No.shs08032)
文摘This paper proposes a support vector machine-based fuzzy rules acquisition system(SVM-FRAS) .The character of SVM in extracting support vector provides a mechanism to extract fuzzy If-Then rules from the training data set.We construct the fuzzy inference system using fuzzy basis function(FBF) .The gradient technique is used to tune the fuzzy rules and the inference system.Theoretical analysis and comparative tests are performed comparing with other fuzzy systems.Experimental results show the SVM-FRAS model possesses good generalization capability as well as high comprehensibility.