Zize Liang

Deploying a Wireless Sensor Network on the Coal Mines

In this paper we describe our experiences using a wireless sensor network to monitor the coal mines with sensors. Wireless networks that link sensors have the potential to greatly benefit for monitoring of coal mine conditions and localization of miners. Substituting light, small wireless sensor network nodes for traditional wired, heavy and fixed monitoring equipment leads to faster, easier and larger-scale deployments in complicated environment. Network consisted of many wireless sensor nodes is now feasible in practice. The primary problem of designing a wireless sensor network for coal mine monitoring and localization of miners is the high system reliability and robustness demanded by its application and safety. The topology of sensor networks is also a main factor we have to take into account. The sensor network application we designed for coal mine monitoring bases on Berkeley TinyOS and Motes platform. We evaluate this design and gain some useful experiences which will benefit our subsequent work.

An adaptive mixture Gaussian background model with online background reconstruction and adjustable foreground mergence time for motion segmentation

Motion segmentation is a very critical task in video surveillance system. In the paper two novel components, background reconstruction and foreground mergence time control, have been incorporated into the adaptive mixture Gaussian background model. The background reconstruction algorithm constructs a static background image from a video sequence that contains moving objects in the scene; then the static background image is used to initialize the background model. The foreground mergence time control mechanism is introduced to make the foreground mergence time adjustable and independent of the models learning rate. Rationales are discussed in detail and experimental results are shown.

A Power Efficient Routing Protocol for Wireless Sensor Network

In recent years, the wireless sensor network (WSN), which has a good application prospect in both civil and military fields, has received increasing attention. But due to the particularity of the WSN, the traditional network routing protocol is not suitable to it. There is a great need for new routing protocols for the WSN. For WSN, the network node energy is usually limited, so how to save and even the consumption of the overall energy is an important problem. To deal with this problem, several algorithms have been proposed, such as LEACH which is a cluster-based routing protocol. In this paper, an improved protocol based on LEACH is proposed. In this protocol, the position and energy information are used and K -means clustering algorithm is adopted to determine the cluster heads and the traditional minimum-energy protocol like scheme is adopted to send data from the cluster heads to the base station. Inside the cluster the geography information is used to determine if some nodes are close enough to keep only one of them awake to monitor the environment and communicate with the cluster head while other nodes sleep to save energy without losing any monitoring information. The simulation results show the protocol proposed in this paper has better performance than LEACH.

Energy-based balance control approach to the ball and beam system

This article investigates the set-point balance control problem of the ball and beam system acting on the ball which is an underactuated system. The control law is designed, based on the total mechanical energy and the passivity properties of the system. According to the desired set-point, the zero equilibrium point and non-zero equilibrium points are studied respectively. For the zero case, it is proved that a single PD feedback controller is sufficient to bring the state to zero from any initial condition, on condition that the control parameters satisfy an inequality. For the non-zero case, the control problem is much more complicated. Unlike the previous energy-based control laws, a new form of Lyapunov function candidate is constructed. A complete analysis of the convergence of the energy and the dynamics is given, and the characteristics of the closed-loop system with the proposed feedback control law are illustrated. Moreover, it is proved that with the parameter choice rules proposed in this article, the ball and beam system will eventually converge exactly to the desired non-zero equilibrium point. Furthermore, since the length of the beam is not unlimited, the trajectory of the ball should be restricted within a limited range. The balance control laws are modified to avoid the ball running beyond the joint range limitation for the zero case and the non-zero case respectively. Simulation results show that the control laws proposed in this article are effective for the set-point balance control problem of the ball and beam system.

Structure-Constrained Obstacles Recognition for Power Transmission Line Inspection Robot

Inspection robot must plan its behavior to detect the obstacles from the complex background according to their types when it is crawling along the power transmission line in order to negotiate reliably. However, in most instances, detecting the obstacles from the complex background is a hard task. For this purpose, a novel and fast visual obstacle recognition algorithm is designed based on the structure of the 220 KV power transmission line. Basic principle and architecture of the algorithm are given. By this approach, three typical obstacles on the power transmission line such as insulator strings, counterweights and suspension clamps can be recognized with high accuracy. Experiments in the real power transmission line show its effectiveness. This method can contribute to the process of the mobile robot negotiating obstacles

Fuzzy Control of the Inspection Robot for Obstacle-Negotiation

This paper proposes the structure of hierarchical behavior controller for the inspection robot. And a fuzzy controller is designed based on the structure to realize the turning behavior of robot. The inspection robot is a multivariable, nonlinear, strongly coupling and underactuated dynamic system. It is difficult to establish an accurate mathematic model of the system. The fuzzy control method can be applicable to those objects which hardly have an accurate mathematic model or whose system parameters are variable. This paper also discusses the stability of fuzzy control system. The experiment results show that the designed fuzzy controller can meet the requirement of the obstacle-negotiation control system.

Multiple kernel learning from sets of partially matching image features

Recent publications and developments based on SVM have shown that using multiple kernels instead of a single one can enhance interpretability of the decision function and improve classifier performance, which motivates researchers to explore the use of homogeneous model obtained as linear combinations of kernels. However, the use of multiple kernels faces the challenge of choosing the kernel weights, and an increased number of parameters that may lead to overfitting. In this paper we show that MKL problem with a enhanced spatial pyramid match kernel can be solved efficiently using projected gradient method. Weights on each kernel matrix (level) are included in the standard SVM empirical risk minimization problem with a L2 constraint to encourage sparsity. We demonstrate our algorithm on classification tasks, which is based on a linear combination of the proposed kernels computed at multiple pyramid levels of image encoding, and we show that the proposed method is accurate and significantly more efficient than current approaches.

Modeling and simulation of folding-boom aerial platform vehicle based on the flexible multi-body dynamics

Folding-boom aerial platform vehicle is a type of construction vehicle used to hoist personnel to the appointed location in the aerial. As for aerial platform vehicle, the flexible deformations of the arm system cannot be neglected. Therefore, the flexible multi-body dynamics equations of the arm system of folding-boom aerial platform vehicle are established based on flexible multi-body dynamics theory and Lagranges equation. Following, the simulation is carried out. The simulation results show that the moving beams exist high frequency vibrations, which caused by the elastic deformations of them. As a result, the vibrations cause the work platform of aerial platform vehicle to shake, and at the same time, the deflections of the beams lead to small deviations of the trajectory of the work platform. Therefore, the establishment of the equations lays the basis of vibration controlling and accurately controlling the trajectory of the work platform of aerial platform vehicle.

Vision based navigation for power transmission line inspection robot

Inspection robot must plan its behavior to loose or grasp the power transmission line, or recognize the obstacles from the complex background when it is crawling along the line in order to negotiate reliably. This paper describes a vision-based navigation system for a power line inspection robot. The main emphasis of this paper is on the ability of object recognition. A recognition method based on straight line extraction is proposed, which is used to recognize the typical obstacles in the power transmission line. Random sample consensus (RANSAC) paradigm is used to group the line segments. The proposed method scales well with respect to the size of the input image and the number and size of the shapes within the data. Moreover the algorithm is conceptually simple and easy to implement. Experimental results show that good recognition can be achieved using the proposed vision system.

Motion Based Image Deblur Using Recurrent Neural Network for Power Transmission Line Inspection Robot

High-voltage power transmission line inspection robot must plan its behavior to detect the obstacles from the complex background according to their types when it is crawling along the power transmission line in order to negotiate reliably. In most cases, robot fulfills the task by its vision system. However, motion blur due to camera motion caused by wind or other unknown causes can significantly degrade the quality of the image acquired. This is a typical kind of the so called image restoration problem, which is a hard problem since no prior knowledge of the motion is available. For this purpose, a novel approach for image restoration is proposed. The restoration procedure consists of two stages: estimation of blur function parameters and reconstruction of images. Image degradation model is proposed first to identify blur function parameters, then a recurrent neural network is used to restore the blurred image. Experiments on real blurred images on power transmission line prove the feasibility and reliability of this algorithm. Our experiments show that the restoration procedure consumes only small amount of computation time.