ROS Integrated Object Detection for SLAM in Unknown, Low-Visibility Environments
Abstract
Integrating thermal (or infrared) imagery on a robotics platform allows Unmanned Ground Vehicles (UGV) to function in low-visibility environments, such as pure darkness or low-density smoke. To maximize the effectiveness of this approach we discuss the modifications required to integrate our low-visibility object detection model on a Robot Operating System (ROS). Furthermore, we introduce a method for reporting detected objects while performing Simultaneous Localization and Mapping (SLAM) by generating bounding boxes and their respective transforms in visually challenging environments.
Document Details
- Document Type
- Technical Report
- Publication Date
- Nov 01, 2021
- Accession Number
- AD1153093
Entities
People
- Benjamin A. Christie
- Garry P. Glaspell
- Osama Ennasr
Organizations
- Engineer Research and Development Center