Mobile robot navigation using visual sensors requires that a robot be able to detect landmarks and obtain pose information from a camera image. This paper presents a vision system for finding man-made markers of known size and calculating the pose of these markers. The algorithm detects and identifies the markers using a weighted pattern matching template. Geometric constraints are then used to calculate the position of the markers relative to the robot. The selection of geometric constraints comes from the typical pose of most man-made signs, such as the sign standing vertical and the dimensions of known size. This system has been tested successfully on a wide range of real images. Marker detection is reliable, even in cluttered environments, and under certain marker orientations, estimation of the orientation has proven accurate to within 2 degrees, and distance estimation to within 0.3 meters.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Vision based object pose estimation for mobile robots


    Contributors:
    Wu, Annie (author) / Bidlack, Clint (author) / Katkere, Arun (author) / Feague, Roy (author) / Weymouth, Terry (author)


    Publication date :

    1994-03-01


    Type of media :

    Conference paper


    Type of material :

    No indication


    Language :

    English


    Keywords :


    Vision Based Object Pose Estimation for Mobile Robots

    Wu, A. / Bidlack, C. R. / Weymouth, T. et al. | British Library Conference Proceedings | 1994


    Pose Estimation for Mobile Robots with Monocular Vision

    Fu, Qiang / Liu, Zhijie / He, Wei | British Library Conference Proceedings | 2022


    Pose Estimation for Mobile Robots with Monocular Vision

    Fu, Qiang / Liu, Zhijie / He, Wei | Springer Verlag | 2021


    Pose Estimation for Mobile Robots with Monocular Vision

    Fu, Qiang / Liu, Zhijie / He, Wei | TIBKAT | 2022


    Vision-Based Categorical Object Pose Estimation and Manipulation

    Meng, Qiwei / Liao, Jianfeng / Jun, Shao et al. | TIBKAT | 2023