Zhenhe Chen

Recent advances in simultaneous localization and map-building using computer vision

Simultaneous localization and map-building (SLAM) continues to draw considerable attention in the robotics community due to the advantages it can offer in building autonomous robots. It examines the ability of an autonomous robot starting in an unknown environment to incrementally build an environment map and simultaneously localize itself within this map. Recent advances in computer vision have contributed a whole class of solutions for the challenge of SLAM. This paper surveys contemporary progress in SLAM algorithms, especially those using computer vision as main sensing means, i.e., visual SLAM. We categorize and introduce these visual SLAM techniques with four main frameworks: Kalman filter (KF)-based, particle filter (PF)-based, expectation-maximization (EM)-based and set membership-based schemes. Important topics of SLAM involving different frameworks are also presented. This article complements other surveys in this field by being current as well as reviewing a large body of research in the area of vision-based SLAM, which has not been covered. It clearly identifies the inherent relationship between the state estimation via the KF versus PF and EM techniques, all of which are derivations of Bayes rule. In addition to the probabilistic methods in other surveys, non-probabilistic approaches are also covered.

Robust and Efficient Feature Tracking for Indoor Navigation

Robust feature tracking is a requirement for many computer vision tasks such as indoor robot navigation. However, indoor scenes are characterized by poorly localizable features. As a result, indoor feature tracking without artificial markers is challenging and remains an attractive problem. We propose to solve this problem by constraining the locations of a large number of nondistinctive features by several planar homographies which are strategically computed using distinctive features. We experimentally show the need for multiple homographies and propose an illumination-invariant local-optimization scheme for motion refinement. The use of a large number of nondistinctive features within the constraints imposed by planar homographies allows us to gain robustness. Also, the lesser computation cost in estimating these nondistinctive features helps to maintain the efficiency of the proposed method. Our local-optimization scheme produces subpixel accurate feature motion. As a result, we are able to achieve robust and accurate feature tracking.

Feature Motion for Monocular Robot Navigation

Monocular vision based robot navigation requires feature tracking for localization. In this paper we present a tracking system using discriminative features as well as less discriminative features. Discriminative features such as SIFT are easily tracked and useful to obtain the initial estimates of the transforms such as affinities and homographies. On the other hand less discriminative features such as Harris corners and manually selected features are not easily tracked in a subsequent frame due to problems in matching. We use SIFT features to obtain the the estimates of the planar homographies representing the motion of the major planar structures in the scene. Planar structure assumption is valid for indoor and architectural scenes. The combination of discriminative and less discriminative feature are tracked using the prediction by these homographies. Then normalized cross correlation matching is used to find the exact matches. This produces robust matching and feature motion can be accurately estimated. We show the performance of our system with real image sequences.

Using multiple view geometry within extended Kalman filter framework for simultaneous localization and map-building

One of the recent and consistently interesting topics in robotics research community is the simultaneous localization and map-building (SLAM) problem. It examines the ability of an autonomous mobile vehicle starting in an unknown environment to incrementally build an environment map and simultaneously localize its pose within this map. In this paper, we present a solution to the SLAM problem with minimal initial knowledge. The novelty lies in its monocular vision sensing system, which uses a multiple view geometry (MVG) approach within an extended Kalman filter (EKF) framework. The MVG algorithm provides accurate structure and motion measurements from a monocular camera whereas traditional vision-based approaches require stereo-vision. It is evident from simulation results that the limitations of MVG and EKF, when used on their own are overcome in the proposed solution.

Implementation of an Update Scheme for Monocular Visual SLAM

An autonomous mobile robot is an intelligent agent which explores an unknown environment with minimal human intervention. Building a relative map which describes the spatial model of the environment is essential for exploration by such a robot. Recent advances for robot navigation motivate mapping algorithms to evolve into simultaneous localization and map-building (SLAM). Initial uncertainty is one of the key factors in SLAM. An update scheme of the feature initialization in monocular vision based SLAM will be briefly introduced, which is within a detailed implementation of feature detection and matching, and 3-D reconstruction by multiple view geometry (MVG) within extended Kalman filter (EKF) framework. Experiments clearly show that the proposed scheme can maximize the optimization capacity of EKF.

A Visual SLAM Solution Based on High Level Geometry Knowledge and Kalman Filtering

In this paper, two new methods are proposed for robotic simultaneous localization and map building (SLAM), namely high level geometric knowledge constraint and newly acquired feature initialization. These methods are implemented within classic extended Kalman filter (EKF) framework. Novelties lie in two aspects. First, high level geometric information, such as common geometric primitives (e.g. lines and triangles) constructed by observed feature points, is incorporated to EKF to enhance the robustness and resistance to noise. Second, a visual measurement approach, multiple view geometry (MVG), is employed for new feature initialization that is considered as a key factor affecting the lower bound error in robotic mapping. Simulations are performed, which can be deemed as concrete verifications and extensions to previous results reported by other researchers. The numerical results show great potentials