Zejian Yuan

Affine Registration of Point Sets Using ICP and ICA

This letter proposes a novel algorithm for affine registration of point sets in the way of incorporating an affine transformation into the iterative closest point (ICP) algorithm. At each iterative step of this algorithm, a closed-form solution of the affine transformation is derived. Similar to the ICP algorithm, this new algorithm converges monotonically to a local minimum from any given initial parameters. To get the best affine registration result, good initial parameters are required which are successfully estimated by using independent component analysis (ICA). Experimental results demonstrate the robustness and high accuracy of this algorithm.

A SLAM algorithm based on the central difference Kalman filter

This paper presents an central difference Kalman filter (CDKF) based Simultaneous Localization and Mapping (SLAM) algorithm, which is an alternative to the classical extended Kalman filter based SLAM solution (EKF-SLAM). EKF-SLAM suffers from two important problems, which are the calculation of Jacobians and the linear approximations to the nonlinear models. They can lead the filter to be inconsistent. To overcome the serious drawbacks of the previous frameworks, Sterlings polynomial interpolation method is employed to approximate nonlinear models. Combined with the Kanlman filter framework, CDKF is proposed to solve the probabilistic state-space SLAM problem. The proposed approach improves the filter consistency and state estimation accuracy. Both simulated experiments and bench mark data set are used to demonstrating the superiority of the proposed algorithm.

Robust registration of partially overlapping point sets via genetic algorithm with growth operator

Recently, genetic algorithm (GA) has been introduced as an effective method to solve the registration problem. It maintains a population of candidate solutions for the problem and evolves by iteratively applying a set of stochastic operators. Accordingly, a key question is how to reduce the population size. In this study, the authors present two techniques for reducing the population size in the GA for registration of partially overlapping point sets. Based on the trimmed iterative closest point algorithm, they introduce a growth operator into the GA. The growth operator, which is also inspired by the biological evolution, can improve the GA efficiency for registration. Furthermore, they present a technique called centre alignment to confirm the value range of all the registration parameters, which can reduce the search space and allow the well-designed GA to directly solve the registration problem. Experimental results carried out with the m-dimensional point sets illustrate its advantages over previous approaches.

An Improved Technique for Robot Global Localization in Indoor Environments

Global localization problem is one of the classical and important problems in mobile robot. In this paper, we present an approach to solve robot global localization in indoor environments with grid map. It combines Hough Scan Matching (HSM) and grid localization method to get the initial knowledge of robots pose quickly. For pose tracking, a scan matching technique called Iterative Closest Point (ICP) is used to amend the robot motion model, this can drastically decreases the uncertainty about the robots pose in prediction step. Then accurate proposal distribution taking into account recent observation is introduced into particle filters to recover the best estimate of robot trajectories, which seriously reduces number of particles for pose tracking. The proposed approach can globally localize mobile robot fast and accurately. Experiment results carried out with robot data in indoor environments demonstrates the effectiveness of the proposed approach.

Unscented SLAM with conditional iterations

As reported, the extended Kalman Filter based Simultaneous Localization and Mapping (SLAM) algorithm has two serious drawbacks, namely the linear approximation of non-linear functions and the calculation of Jacobian matrices. These can introduce estimation error and induce a great ambiguity for data association. For overcoming these drawbacks, this paper presents an improved SLAM solution, based on the Unscented Kalman Filter (UKF) with conditional iterations (UiSLAM). Since the UKF can improve the performance of filters, it can be used to overcome the drawbacks of the previous frameworks. When the loop is closed, the condition to perform iterated update is satisfied. Then the iterative update procedure employed in the iterated extended Kalman Filter (IEKF) is implemented. This approach combines the virtues of IEKF and UKF for solving the SLAM problems and improves accuracy of the state estimation. Both the simulation and experimental results are proposed to illustrate the superiority of the UiSLAM algorithm over previous approaches.

Visual Appearance-Based Unmanned Vehicle Sequential Localization

Localizationis of vital importance for an unmanned vehicle to drive on the road. Most of the existing algorithms are based on laser range finders, inertial equipment, artificial landmarks, distributing sensors or global positioning system(GPS) information. Currently, the problem of localization with vision information is most concerned. However, vision-based localization techniquesare still unavailable for practical applications. In this paper, we present a vision-based sequential probability localization method. This method uses the surface information of the roadside to locate the vehicle, especially in the situation where GPS information is unavailable. It is composed of two step, first, in a recording stage, we construct a ground truthmap with the appearance of the roadside environment. Then in an on-line stage, we use a sequential matching approach to localize the vehicle. In the experiment, we use two independent cameras to observe the environment, one is left-orientated and the other is right. SIFT features and Daisy features are used to represent for the visual appearance of the environment. The experiment results show that the proposed method could locate the vehicle in a complicated, large environment with high reliability.

Point-to-line metric based Iterative Closest Point with bounded scale

This paper introduces a novel approach named the point-to-line metric based Iterative Closest Point (ICP) with bounded scale algorithm, which integrates a scale with boundaries into the traditional point-to-line metric-based ICP algorithm. It converges quadratically, requires few number of iterations and is not sensitive to large initial displacement errors. Based on the analysis of the error function being minimized, a efficient solution is proposed to reduce the computational cost. The proposed technique is fit for both laser scan data sets and other 2D m-D point sets, and yields more satisfying robust results than the traditional point-to-line ICP method. Further more, it provides a method to calculate the covariance of registration results. Experimental results illustrate the feasibility of the proposed theory and algorithms.

A Dynamic Model for Early Vision Processing

A novel model of the visual preprocessing was proposed , which is derived itself from the known structure of the retina and its dynamic processing for the physiological signals and improved by the demand driving of machine vision application. The model can rapidly detect the probability of the potential objects of interest or threats at every position in the video frames to immediately respond the emerging stimulus of vision.

A Novel Dual-Probe Adaptive Model for Image Change Detection

Change detection is the foremost pre-attention process of visual motion analysis. It provides important preprocessing clues for the following complex visual attention selection and pattern recognition process. In this letter, a novel dual-probe adaptive model of the weak image change signal detection is advanced. Then its basic parameter constraints are analyzed and the numerical analysis of its characteristic is discussed. Simulation results show that the related change detector could capture the tiny change signals in synthetic and nature scenes with noisy background.

A sequential mobile vehicle location method with visual features

Localization is of vital importance to a mobile vehicle system. Most of the existing algorithms are based on laser range finders, sonar sensors, artificial landmarks or GPS information. In this paper, we present a sequential probability location method for mobile vehicle, which uses scale-invariant image features as natural landmarks in unmodified environments. First, we construct a ground truth map with the appearance of the environment in a learning step, then by a proposed sequential matching approach and kd-trees, we could recognize the map and locate the mobile vehicle. In the experiment, we use two cameras, one is left oriented and the other is right. We have try several method, the experiment result shows that the proposed method could locate the vehicle in nearly realtime with higher matching rate than the other approach.