Mingliang Gao

A novel visual tracking method using bat algorithm

Bat algorithm (BA) is a new meta-heuristic optimization algorithm that is inspired by the echolocation characteristics of bats with varying pulse rates of emission and loudness. BA has been proven to be a powerful tool in solving a wide range of global optimization problems. In this study, visual tracking is considered to be a process of searching for target by various bats in sequential images. A BA-based tracking architecture is proposed and the sensitivity and adjustment of the parameters in BA are studied experimentally. To demonstrate the tracking ability of the proposed tracker, comparative studies of tracking accuracy and speed of the BA-based tracker with three representative trackers, namely, particle filter, meanshift and particle swarm optimization are presented. Comparative results show that the BA-based tracker outperforms the other three trackers.

Face tracking based on differential harmony search

Owing to its significant roles in computer vision applications, human face tracking has drawn extensive attention in recent years. Most researchers solve face tracking using particle filter, meanshift and their derivatives. Unlike the traditional methods, in this study, face tracking is treated as an optimisation problem and a new meta-heuristic optimisation algorithm, differential harmony search (DHS), is introduced to solve face tracking problems. We compare the speed and accuracy of the proposed method with particle filter, meanshift and improved harmony search. Experimental results show that DHS-based tracker is faster and more accurate and it is easy to handle the parameters tuning. Furthermore, to improve the reliability of tracking, multiple visual cues are applied to DHS-based tracking system and experimental results demonstrate the increased robustness achieved by fusing multiple cues.

Experimental Study of Inductive Pulsed Power Supply Based on Multiple HTSPPT Modules

For electromagnetic emission applications that need a very high amplitude and an appropriate pulsewidth, a pulsed power supply based on multiple high-temperature superconducting pulsed power transformer (HTSPPT) modules is verified in this paper. First, the working processes of multiple HTSPPT modules are analyzed and two small experimental HTSPPTs are described in detail. Then, simulation is carried out to show the major pulse characteristics of two different discharge methods. To verify the feasibility of two discharge methods, high-current testing is carried out with the two HTSPPTs. The results show that a higher amplitude of current pulse can be achieved using synchronous parallel discharge and a larger pulsewidth of current pulse can be achieved using asynchronous parallel discharge.

Visual tracking method based on cuckoo search algorithm

Abstract. Cuckoo search (CS) is a new meta-heuristic optimization algorithm that is based on the obligate brood parasitic behavior of some cuckoo species in combination with the Lévy flight behavior of some birds and fruit flies. It has been found to be efficient in solving global optimization problems. An application of CS is presented to solve the visual tracking problem. The relationship between optimization and visual tracking is comparatively studied and the parameters’ sensitivity and adjustment of CS in the tracking system are experimentally studied. To demonstrate the tracking ability of a CS-based tracker, a comparative study of tracking accuracy and speed of the CS-based tracker with six “state-of-art” trackers, namely, particle filter, meanshift, PSO, ensemble tracker, fragments tracker, and compressive tracker are presented. Comparative results show that the CS-based tracker outperforms the other trackers.

Influence of Critical Parameters on the Performance of a Superconducting Inductive Pulsed-Power Supply Circuit

The superconducting inductive pulsed-power supply (SPPS) circuit consists of a high-temperature superconducting pulsed-power transformer (HTSPPT) and an auxiliary capacitor. The electrical losses and the power of the primary source can be cut down with the superconducting inductive energy storage. Although its energy density is slightly less than a purely superconducting inductive system, it can reduce the maximum voltage of the opening switch by the capacitor and achieve a high degree of current amplification factor. However, during the discharge process, the magnetic leakage flux energy stored in the primary of the HTSPPT requires the capacitor to have a certain capacity. The higher the ratio of the capacitive stored energy over the total inductive stored energy, the more the dominant position of inductive energy storage reduces. The current amplification factor (γ), the maximum voltage of the opening switch (VSmax), and the ratio of capacitive stored energy (η) are the three main properties of the SPPS circuit, which depends on several intertwined critical parameters, such as the inductance ratio n = L2/(L2 + LL) and the capacitance (C1). This paper studies the influence of the critical parameters on the main circuit performance with a 1-kJ SPPS system. The detailed selection method of the critical parameters for the specific system is also discussed with a coupling coefficient of 0.95. Such a system is easy to be utilized for the basic experimental study of a small railgun.

A novel construction method of convolutional neural network model based on data-driven

The convolutional neural network (CNN) is an excellent method for image recognition. However, there are some problems in the construction process of CNN model, such as network structure setting depends on experience knowledge, network parameters selection is difficult, and there is a lack of relevance between network model and training data. To overcome the shortcomings of CNN model construction theory, in this paper, we develop a new construction approach, named adaptive deep CNN network model based on data-driven. In our method, we first set up the initial CNN model in a simple way, and the initial model only contains one feature map in the convolution layer and pooling layer. And then, the network is adaptively constructed by using the idea of learning parameters and expanding network. In network expansion, the convergence rate of CNN model is used as evaluation index of global expansion, and some global branches are added to the network model. After global expansion, the CNN is controlled to local expansion according to the recognition rate of cross validation samples. The local network learning is stopped until the recognition rate reaches the expected value. Finally, the adaptive incremental learning of network structure is realized by expanding some new branches for new samples. Experimental results on two benchmark face databases, CMU-PIE face database and MIT-CBCL face database, demonstrate the effectiveness of the proposed method.

Orthogonal gradient measurement matrix optimisation method

The optimisation of measurement matrix that is within the compressive sensing framework is considered in this study. Based on the fact that an information factor with smaller mutual coherence performs better, the gradient measurement matrix optimisation method is improved by an orthogonal search direction revision factor. This algorithm updates the approximation of ideal Gram matrix of information operator and the measurement matrix alternatingly. Using measurement matrix and sparse basis to represent the Gram matrix, the measurement matrix is optimised by the gradient algorithm, in which an orthogonal gradient search direction revision factor is proposed and utilised to further improve the performance of measurement matrix. This orthogonal factor is computed by the Cayley transform of a real skew symmetric matrix that is related to the gradient and the measurement matrix. Results of several experiments show that compared with the initial random matrix, the optimised measurement matrix can lead to better signal reconstruction quality.

An Inductive Pulsed-Power Supply Circuit Consisting of Multiple HTSPPT Modules With Capacitor Reuse Methodology

Superconducting pulsed-power supply (SPPS) provides an efficient method for both high-density inductive energy storage and high current pulse generation. An SPPS consisting of eight high-temperature superconducting pulsed-power transformer (HTSPPT) modules with XRAM methodology was designed and simulated in preliminary studies. It recycled the leakage flux energy and reduced the voltage across the opening switch with a capacitor in primary. However, the SPPS with XRAM methodology has two problems. The first one is that it can provide high pulse amplitude, but cannot provide enough width. The other one is that the ratio of the maximum capacitive energy over the total inductive energy is relatively large, which cuts down the overall system energy density. This paper proposes a modified topology of SPPS with capacitor reuse methodology. Multiple HTSPPT modules are divided into several groups. Each group shares the same capacitor. The procedure of the modified SPPS is presented in detail. A 270-kJ SPPS with capacitor reuse methodology is designed and simulated to illustrate the modified topology. With the load parameters of a small railgun, the peak value of the load current is 207.15 kA and the pulse half-height width is 5.56 ms, the ratio of the maximum capacitive energy over the total inductive energy is 11%. The characteristics of the modified topology are also described in detail in this paper.