Recognizing the target from a rotated and scaled image is an important and difficult task for computer vision. Visual system of humans has a unique space variant resolution mechanism(SVR) and log-polar transformations...Recognizing the target from a rotated and scaled image is an important and difficult task for computer vision. Visual system of humans has a unique space variant resolution mechanism(SVR) and log-polar transformations(LPT) is a mapping method that is invariant to rotation and scale. Motivated by biological vision, we propose a novel global LPT based template-matching algorithm(GLPT-TM) which is invariant to rotational and scale changes; and with pigeon-inspired optimization(PIO) used to optimize search strategy, a hybrid model of SVR and pigeon-inspired optimization(SVRPIO) is proposed to accomplish object recognition for unmanned aerial vehicles(UAV) with rotational and scale changes of the target. To demonstrate the efficiency, effectiveness and reliability of the proposed method, a series of experiments are carried out. By rotating and scaling the sample image randomly and recognizing the target with the method, the experimental results demonstrate that our proposed method is not only efficient due to the optimization, but effective and accurate in recognizing the target for UAV.展开更多
An annular sector model for the telephone cord buckles of elastic thin films on rigid substrates is established, in which the von Krman plate equations in polar coordinates are used for the elastic thin film and a dis...An annular sector model for the telephone cord buckles of elastic thin films on rigid substrates is established, in which the von Krman plate equations in polar coordinates are used for the elastic thin film and a discrete version of the Griffith criterion is applied to determine the shape and scale of the parameters. A numerical algorithm combining the Newmark-β scheme and the Chebyshev collocation method is designed to numerically solve the problem in a quasi-dynamic process. Numerical results are presented to show that the numerical method works well and the model agrees well with physical observations, especially successfully simulated for the first time the telephone cord buckles with two humps along the ridge of each section of a buckle.展开更多
基金the Aeronautical Foundation of China(Grant No.2015ZA51013)the National Natural Science Foundation of China(Grant No.61673327)
文摘Recognizing the target from a rotated and scaled image is an important and difficult task for computer vision. Visual system of humans has a unique space variant resolution mechanism(SVR) and log-polar transformations(LPT) is a mapping method that is invariant to rotation and scale. Motivated by biological vision, we propose a novel global LPT based template-matching algorithm(GLPT-TM) which is invariant to rotational and scale changes; and with pigeon-inspired optimization(PIO) used to optimize search strategy, a hybrid model of SVR and pigeon-inspired optimization(SVRPIO) is proposed to accomplish object recognition for unmanned aerial vehicles(UAV) with rotational and scale changes of the target. To demonstrate the efficiency, effectiveness and reliability of the proposed method, a series of experiments are carried out. By rotating and scaling the sample image randomly and recognizing the target with the method, the experimental results demonstrate that our proposed method is not only efficient due to the optimization, but effective and accurate in recognizing the target for UAV.
基金supported by the Major State Basic Research Projects (Grant No. 2005CB321701)National Natural Science Foundation of China (Grant No. 10871011)Research Foundation of Doctoral Program of the Ministry of Education of China (Grant No. 20060001007)
文摘An annular sector model for the telephone cord buckles of elastic thin films on rigid substrates is established, in which the von Krman plate equations in polar coordinates are used for the elastic thin film and a discrete version of the Griffith criterion is applied to determine the shape and scale of the parameters. A numerical algorithm combining the Newmark-β scheme and the Chebyshev collocation method is designed to numerically solve the problem in a quasi-dynamic process. Numerical results are presented to show that the numerical method works well and the model agrees well with physical observations, especially successfully simulated for the first time the telephone cord buckles with two humps along the ridge of each section of a buckle.
