Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Semi-automatic image annotation using 3D LiDAR projections and depth camera data

Journal Article · · Annals of Nuclear Energy
 [1];  [1];  [1];  [1];  [1];  [2];  [2]
  1. Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
  2. Nevada National Security Site, North Las Vegas, NV (United States)
+ Show Author Affiliations
Efficient image annotation is necessary to utilize deep learning object recognition neural networks in nuclear safeguards, such as for the detection and localization of target objects like nuclear material containers (NMCs). This capability can help automate the inventory accounting of different types of NMCs within nuclear storage facilities. The conventional manual annotation process is labor-intensive and time-consuming, hindering the rapid deployment of deep learning models for NMC identifications. This paper introduces a novel semi-automatic method for annotating 2D images of nuclear material containers (NMCs) by combining 3D light detection and ranging (LiDAR) data with color and depth camera images collected from a handheld scan system. The annotation pipeline involves an operator manually marking new target objects on a LiDAR-generated map, and projecting these 3D locations to images, thereby automatically creating annotations from the projections. The semi-automatic approach significantly reduces manual efforts and the expertise in image annotation that is required to perform the task, allowing deep learning models to be trained on-site within a few hours. The paper compares the performance of models trained on datasets annotated through various methods, including semi-automatic, manual, and commercial annotation services. The evaluation demonstrates that the semi-automatic annotation method achieves comparable or superior results, with a mean average precision (mAP) above 0.9, showcasing its efficiency in training object recognition models. Additionally, the paper explores the application of the proposed method to instance segmentation, achieving promising results in detecting multiple types of NMCs in various formations.
Research Organization:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA), Office of Defense Nuclear Nonproliferation; USDOE Office of Science (SC)
Grant/Contract Number:
AC02-05CH11231
OSTI ID:
2496630
Journal Information:
Annals of Nuclear Energy, Journal Name: Annals of Nuclear Energy Vol. 213; ISSN 0306-4549
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (10)

Object modelling by registration of multiple range images journal April 1992
Advanced algorithms for radiographic material discrimination and inspection system design
  • Gilbert, Andrew J.; McDonald, Benjamin S.; Deinert, Mark R.
  • Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms, Vol. 385 https://doi.org/10.1016/j.nimb.2016.07.013
journal October 2016
A method for registration of 3-D shapes journal February 1992
ImageNet: A large-scale hierarchical image database
  • Deng, Jia; Dong, Wei; Socher, Richard
  • 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), 2009 IEEE Conference on Computer Vision and Pattern Recognition https://doi.org/10.1109/CVPR.2009.5206848
conference June 2009
YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors conference June 2023
Real-time visual odometry from dense RGB-D images conference November 2011
Faster-LIO: Lightweight Tightly Coupled Lidar-Inertial Odometry Using Parallel Sparse Incremental Voxels journal April 2022
Point Set Registration: Coherent Point Drift journal December 2010
Fine-Tuning CNN Image Retrieval with No Human Annotation journal July 2019
Direct visibility of point sets conference July 2007

Similar Records

Lidar Mapping and Surveillance of Nuclear Infrastructure
Conference · Mon Jul 01 00:00:00 EDT 2019 · OSTI ID:23005505
Lidar Cloud Detection with Fully Convolutional Networks
Conference · Wed Mar 06 23:00:00 EST 2019 · OSTI ID:1650662
WE-AB-BRA-05: Fully Automatic Segmentation of Male Pelvic Organs On CT Without Manual Intervention
Journal Article · Mon Jun 15 00:00:00 EDT 2015 · Medical Physics · OSTI ID:22570093

Related Subjects

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL PROTECTION
Computer vision
LiDAR-assisted image annotation
Nuclear safeguards
Object recognition neural networks