Automated creation of labeled pointcloud datasets in support of machine learning-based perception
Watson, Andrew K.
MetadataShow full item record
Autonomous vehicles continue to struggle with understanding their environments and robotic perception remains an active area of research. Machine learning–based approaches to computer vision, particularly the increasing application of deep neural networks, have been responsible for many of the breakthroughs in robotic perception over the last decade. We propose a three-phase model for improving pointcloud classification. Progress in applying machine learning-based perception to new problem sets is hampered by the difficulty in creating new training data. As such, our primary contribution is a technique to automate the creation of training data for 3D pointcloud classification problems. Our proposed implementation collects synchronized 2D camera images and 3D LIDAR pointclouds, depth clusters each LIDAR frame to spatially segment a scene, correlates each resultant pointcloud segment to a cropped 2D image, and processes each crop through a 2D image classifier to assign a segment label. Our automated implementation produced labeled 3D pointclouds from raw LIDAR collection and, during testing, yielded a small dataset with 81% accuracy of annotations. We also propose a method of scene context discovery to boost pointcloud classification performance. Our approach explores a method to scrape regionally geotagged media for processing through an object-detection neural network. We develop a database mapping of object-type spatial relationships in a specific physical environment and propose applying these relationships as weights to boost pointcloud classifier performance.
RightsCopyright is reserved by the copyright owner.
Showing items related by title, author, creator and subject.
Sasao, Tsutomu; Nagayama, Shinobu; Butler, Jon T. (2005-08);This paper presents an architecture and a synthesis method for programmable numerical function generators of trigonometric functions, logarithm functions, square root, reciprocal, etc. Our architecture uses an LUT (Look-Up ...
Bilzor, Michael; Huffmire, Ted; Irvine, Cynthia; Levin, Tim (2011);To counter the growing threat of malicious subversions to the design of a microprocessor, there is a great need for simple, automated methods for detecting such malevolent changes. Based on the adoption of the Property ...
Tysver, Joseph Bryce (Monterey, California. Naval Postgraduate School, 1986-01); NPS55-86-003PRThe proposed BASIC program for smoothing NUWES data uses the Least- Squares Method to fit a polynomial to a 7-point data segment. It determines the best fitting polynomial of order 1, 2, or 3 and establishes an estimate ...