3D object detection is the task of detecting the full 3D pose of objects relative to an autonomous platform. It is an important perception system that can be used to plan actions according to the behavior of other dynamic objects in an environment. Due to the poor generalization of object detectors trained and tested on different datasets, this thesis concerns the utilization of unsupervised domain adaptation to train object detectors fit for mobile robotics without any labeled training data. To tackle the problem a novel approach Unsupervised Adversarial Domain Adaptation 3D (UADA3D) is presented to adapt LiDAR-based detectors, through drawing inspiration from the success of adversarial adaptation for 2D object detection in RGB images. The method adds learnable discriminator layers that discriminate between the features and bounding box predictions in the labeled source and unlabeled target data. The gradients are then reversed through gradient reversal layers during backpropagation to the base detector, which in turn learns to extract features that are similar between the domains in order to fool the discriminator. The method works for multi-class detection by simultaneous adaptation of all classes in an end-to-end trainable network and works for both point-based and voxel-based single-stage detectors. The results show that the proposed method increases detection scores for adaptation from dense to sparse point clouds and from simulated data toward the data of a mobile delivery robot, successfully handling the two relevant domain gaps given by differences in marginal and conditional probability distributions. ; 3D-objektdetektering handlar om att upptäcka hela 3D-positionen för objekt i förhållande till en autonom plattform. Det är ett viktigt perceptionsystem som kan användas för att planera åtgärder baserat på beteendet hos andra dynamiska objekt i en miljö. På grund av den dåliga generaliseringen av objektavkännare som tränats och testats på olika datamängder, handlar denna avhandling om användningen av ...


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Unsupervised Domain Adaptation for 3D Object Detection Using Adversarial Adaptation : Learning Transferable LiDAR Features for a Delivery Robot ; Icke-vägledd Domänanpassning för 3D-Objektigenkänning Genom Motspelaranpassning : Inlärning av Överförbara LiDAR-Drag för en Leveransrobot


    Beteiligte:

    Erscheinungsdatum :

    2023-01-01


    Medientyp :

    Hochschulschrift


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    004 / 629



    Unsupervised Evaluation of Lidar Domain Adaptation

    Hubschneider, Christian / Roesler, Simon / Zollner, J. Marius | IEEE | 2020


    Cross-Sensor Deep Domain Adaptation for LiDAR Detection and Segmentation

    Rist, Christoph B. / Enzweiler, Markus / Gavrila, Dariu M. | IEEE | 2019


    Unsupervised Domain Adaptive Object Detection Using Forward-Backward Cyclic Adaptation

    Yang, Siqi / Wu, Lin / Wiliem, Arnold et al. | British Library Conference Proceedings | 2021


    DALi: Domain Adaptation in LiDAR Point Clouds for 3D Obstacle Detection

    Cortes, Irene / Beltran, Jorge / De La Escalera, Arturo et al. | IEEE | 2022


    A Survey on Deep Domain Adaptation for LiDAR Perception

    Triess, Larissa T. / Dreissig, Mariella / Rist, Christoph B. et al. | IEEE | 2021