Object detection in 3D point clouds is essential in fields such as geospatial intelligence and autonomous driving. The common machine learning problem of scarce labeled training data is even more acute with 3D point cloud data. Active learning provides a framework to prioritize the additional effort to manually annotate unlabeled training data. Most active learning methods for deep learning fall into one of two categories: uncertainty methods and diversity methods. Uncertainty methods select data by assessing model outputs for their confidence and consistency and are therefore dependent on the expected output of each deep learning task. These methods tend to select batches of informative yet highly similar samples to label. Diversity-based active learning aims to create a labeled dataset that is both varied and representative of the remaining unlabeled data. Diversity methods operate directly on the feature representations of the inputs and are thus more flexible with respect to the specifics of the deep learning task. Our current work explores applying diversity methods and uncertainty-diversity hybrid methods to 3D object detection. We evaluate various approaches to incorporate diversity, including K-Medoids clustering, core set selection, and furthest nearest neighbors. We address the high dimensionality of the features extracted from a VoxelNet-based object detector by varying the distance metric used in the active learning algorithms. Furthermore, we compare our results to those obtained using only uncertainty methods. We assess the performance and efficiency of each active learning method in addition to the representativeness and diversity of the labeled datasets produced. We find that hybrid uncertainty-diversity methods outperform other methods in terms of object detection AP50 throughout active learning, annotation efficiency, and class balance.
KEYWORDS: Clouds, Sensors, 3D modeling, Detection and tracking algorithms, Stochastic processes, Monte Carlo methods, LIDAR, Synthetic aperture radar, Uncertainty analysis, Spatial data uncertainty, Image classification
Deep learning-based object detection and classification in 3D point clouds has numerous applications including defense, autonomous driving, and augmented reality. A challenge in applying deep learning to point clouds is the frequent scarcity of labeled data. Often, one must manually label a large quantity of data for the model to be useful in application. To overcome this challenge, active learning provides a means of minimizing the manual labeling required. The crux of active learning algorithms is defining and calculating the potential added “value” of labeling each unlabeled sample. We introduce a novel active learning algorithm, LOCAL, with an anchorbased object detection architecture, a modified object matching strategy, and an acquisition metric designed for object detection in any dimension. We compare the performance of common acquisition functions to our novel metric that utilizes all of the model outputs—including both bounding box localizations and softmax classification scores—to capture both the classification and spatial uncertainty in the model. Finally, we identify opportunities for further exploration, such as alternative measures of spatial uncertainty as well as increasing the stochasticity of the model in order to improve robustness of the algorithm.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.