A solution is proposed for the real-time vehicle verification which is an important problem for numerous on- road vehicle applications. First, based on the vertical symmetry characteristics of vehicle images, a vertic...A solution is proposed for the real-time vehicle verification which is an important problem for numerous on- road vehicle applications. First, based on the vertical symmetry characteristics of vehicle images, a vertical symmetrical histograms of oriented gradients (VS-HOG) descriptor is proposed for extracting the image features. In the classification stage, an extreme learning machine (ELM) is used to improve the real-time performance. Experimental data demonstrate that, compared with other classical methods, the vehicle verification algorithm based on VS-HOG and ELM achieves a better trade-off between cost and performance. The computational cost is reduced by using the algorithm, while keeping the performance loss as low as possible. Furthermore, experimental results further show that the proposed vehicle verification method is suitable for on-road vehicle applications due to its better performance both in efficiency and accuracy.展开更多
Aiming at the diversity and nonlinearity of the elevator system control target, an effective group method based on a hybrid algorithm of genetic algorithm and neural network is presented in this paper. The genetic alg...Aiming at the diversity and nonlinearity of the elevator system control target, an effective group method based on a hybrid algorithm of genetic algorithm and neural network is presented in this paper. The genetic algorithm is used to search the weight of the neural network. At the same time, the multi-objective-based evaluation function is adopted, in which there are three main indicators including the passenger waiting time, car passengers number and the number of stops. Different weights are given to meet the actual needs. The optimal values of the evaluation function are obtained, and the optimal dispatch control of the elevator group control system based on neural network is realized. By analyzing the running of the elevator group control system, all the processes and steps are presented. The validity of the hybrid algorithm is verified by the dynamic imitation performance.展开更多
Vehicle detectition in still images is a comparatively difficult task. This paper presents a method for this task by using boosted local pattern detector constructed from two local features including Haar-like and ori...Vehicle detectition in still images is a comparatively difficult task. This paper presents a method for this task by using boosted local pattern detector constructed from two local features including Haar-like and oriented gradient features. The whole process is composed of three stages. In the first stage, local appearance features of vehicles and non-vehicle objects are extracted. Haar-tike and oriented gradient features are extracted separately in this stage as local features. In the second stage, Adabeost algorithm is used to select the most discriminative features as weak detectors from the two local feature sets, and a strong local pattern detector is built by the weighted combination of these selected weak detectors. Finally, vehicle detection can be performed in still images by using the boosted strong local feature detector. Experiment results show that the local pattern detector constructed in this way combines the advantages of Haar-like and oriented gradient features, and can achieve better detection results than the detector by using single Haar-like features.展开更多
Numerical investigation of a supersonic jet from the nose of a lifting-body vehicle opposing a hypersonic flow with the freestream Mach number being 8.0 at 40 km altitude was carried out by solving the three-dimension...Numerical investigation of a supersonic jet from the nose of a lifting-body vehicle opposing a hypersonic flow with the freestream Mach number being 8.0 at 40 km altitude was carried out by solving the three-dimensional, time-accurate Navier-Stokes equations with a hybrid meshes approach. Based on the analysis of the flow field structures and aerodynamic characteristics, the behaviours relevant to the LPM jet were discussed in detail, including the drag reduction effect, the periodic oscillation and the feedback loop. The obtained results show that the flow oscillation characteristic of the LPM jet is low-frequency and high-amplitude while that of the SPM jet is high-frequency and low-amplitude. Compared with the clearly dominant frequencies of the LPM jet, the SPM jet exhibits a broad-band structure. The LPM jet can sustain drag reduction effect until the angle of attack is 8°, and the lift-to-drag ratio of the vehicle is effectively improved by 6.95% at angle of attack of 6°. The self-sustained oscillation process was studied by a typical oscillating cycle of the drag force coefficient and the variation of the instantaneous pressure distribution,which reveals an off-axial flapping motion of the conical shear layer. The variation of the subsonic recirculation zone ahead of the vehicle nose strengthens the understanding of the jet behavior including the source of instability in the long penetration mode and the mechanism of the feedback loop. The aim of this paper is to advance the technology readiness level for the counterflowing jet applied as an active control technology in hypersonic flows by gaining a better insight of the flow physics.展开更多
基金The National Natural Science Foundation of China(No.61203237)the Natural Science Foundation of Zhejiang Province(No.LQ12F03016)the China Postdoctoral Science Foundation(No.2011M500836)
文摘A solution is proposed for the real-time vehicle verification which is an important problem for numerous on- road vehicle applications. First, based on the vertical symmetry characteristics of vehicle images, a vertical symmetrical histograms of oriented gradients (VS-HOG) descriptor is proposed for extracting the image features. In the classification stage, an extreme learning machine (ELM) is used to improve the real-time performance. Experimental data demonstrate that, compared with other classical methods, the vehicle verification algorithm based on VS-HOG and ELM achieves a better trade-off between cost and performance. The computational cost is reduced by using the algorithm, while keeping the performance loss as low as possible. Furthermore, experimental results further show that the proposed vehicle verification method is suitable for on-road vehicle applications due to its better performance both in efficiency and accuracy.
基金Supported by National Natural Science Foundation of China (No60874077) Specialized Research Funds for Doctoral Program of Higher Education of China (No20060056054) Research Funds for Scientific Financing Projects of Quality Control Public Welfare Profession (No2007GYB172)
文摘Aiming at the diversity and nonlinearity of the elevator system control target, an effective group method based on a hybrid algorithm of genetic algorithm and neural network is presented in this paper. The genetic algorithm is used to search the weight of the neural network. At the same time, the multi-objective-based evaluation function is adopted, in which there are three main indicators including the passenger waiting time, car passengers number and the number of stops. Different weights are given to meet the actual needs. The optimal values of the evaluation function are obtained, and the optimal dispatch control of the elevator group control system based on neural network is realized. By analyzing the running of the elevator group control system, all the processes and steps are presented. The validity of the hybrid algorithm is verified by the dynamic imitation performance.
基金supported by the Korea Research Foundation Grant funded by the Korean Government(MOEHRD),the MKE(The Ministry of Knowledge Economy,Korea)the ITRC(Information Technology Research Center)support program(NIPA-2009-(C1090-0902-0007))
文摘Vehicle detectition in still images is a comparatively difficult task. This paper presents a method for this task by using boosted local pattern detector constructed from two local features including Haar-like and oriented gradient features. The whole process is composed of three stages. In the first stage, local appearance features of vehicles and non-vehicle objects are extracted. Haar-tike and oriented gradient features are extracted separately in this stage as local features. In the second stage, Adabeost algorithm is used to select the most discriminative features as weak detectors from the two local feature sets, and a strong local pattern detector is built by the weighted combination of these selected weak detectors. Finally, vehicle detection can be performed in still images by using the boosted strong local feature detector. Experiment results show that the local pattern detector constructed in this way combines the advantages of Haar-like and oriented gradient features, and can achieve better detection results than the detector by using single Haar-like features.
基金supported by the Aerospace International Innovation Talent Cultivation Project of Program China Scholarship Councilthe National Natural Science Foundation of China(Grant No.11502291)
文摘Numerical investigation of a supersonic jet from the nose of a lifting-body vehicle opposing a hypersonic flow with the freestream Mach number being 8.0 at 40 km altitude was carried out by solving the three-dimensional, time-accurate Navier-Stokes equations with a hybrid meshes approach. Based on the analysis of the flow field structures and aerodynamic characteristics, the behaviours relevant to the LPM jet were discussed in detail, including the drag reduction effect, the periodic oscillation and the feedback loop. The obtained results show that the flow oscillation characteristic of the LPM jet is low-frequency and high-amplitude while that of the SPM jet is high-frequency and low-amplitude. Compared with the clearly dominant frequencies of the LPM jet, the SPM jet exhibits a broad-band structure. The LPM jet can sustain drag reduction effect until the angle of attack is 8°, and the lift-to-drag ratio of the vehicle is effectively improved by 6.95% at angle of attack of 6°. The self-sustained oscillation process was studied by a typical oscillating cycle of the drag force coefficient and the variation of the instantaneous pressure distribution,which reveals an off-axial flapping motion of the conical shear layer. The variation of the subsonic recirculation zone ahead of the vehicle nose strengthens the understanding of the jet behavior including the source of instability in the long penetration mode and the mechanism of the feedback loop. The aim of this paper is to advance the technology readiness level for the counterflowing jet applied as an active control technology in hypersonic flows by gaining a better insight of the flow physics.