3D object recognition is an generic task in robotics and autonomous vehicles. In this paper, we propose a 3D object recognition approach using a 3D extension of the histogram-of-gradients object descriptor with data captured with a depth camera. The presented method makes use of synthetic objects for training the object classifier, and classify real objects captured by the depth camera. The preprocessing methods include operations to achieve rotational invariance as well as to maximize the recognition accuracy while reducing the feature dimensionality at the same time. By studying different preprocessing options, we show challenges that need to be addressed when moving from synthetic to real data. The recognition performance was evaluated with a real dataset captured by a depth camera and the results show a maximum recognition accuracy of 81.5%.


    Access

    Download


    Export, share and cite



    Title :

    Realworld 3d object recognition using a 3d extension of the hog descriptor and a depth camera


    Contributors:

    Publication date :

    2021-01-01


    Remarks:

    Scopus 2-s2.0-85099956966



    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    004 / 629



    3D shape descriptor for object recognition based on Kinect-like depth image

    As'ari, M. A. / Sheikh, U. U. / Supriyanto, E. | British Library Online Contents | 2014


    Performance of continuum models for realworld traffic flows: Comprehensive benchmarking

    Mohammadian, Saeed / Zheng, Zuduo / Haque, Md. Mazharul et al. | Elsevier | 2021


    Realworld Fuel Economy Testing - The Sea to Sea Econorallye 2

    McRae,F.W. / West.Washington Univ.,Veh.Res.Inst.,US | Automotive engineering | 1981


    Realworld Fuel Economy Testing - The Sea to Sea Econorallye II

    McRae, Forbes W. | SAE Technical Papers | 1981