THROUGH the integration of sensors and mobile land and air mapping systems, a team of digital forestry researchers at Purdue used advanced technology to locate, count and measure over a thousand trees in a matter of hours.
“The machines count and measure every tree – it’s not an estimate using modeling, it’s a real forest inventory,” said Songlin Fei, president of remote sensing dean and professor of forestry and natural resources and leader of the Digital Forestry initiative. Purdue University. “This is a revolutionary development on our path to using technology for rapid and accurate inventory of the global forest ecosystem, which would improve our ability to prevent forest fires, detect disease, perform accurate carbon counting and take informed decisions on forest management “.
The technology uses manned aircraft, unmanned drones and backpack-mounted systems. The systems integrate cameras with light sensing and sensing units, or LiDARs, along with navigation sensors, including Integrated Global Navigation Satellite Systems (GNSS) and Inertial Navigation Systems (INS). A Purdue team led by Ayman Habib, civil engineering professor Thomas A. Page and head of Purdue’s digital photogrammetry research group, who co-directed the project with Fei, designed and built the systems.
“The different parts of the systems exploit the synergistic characteristics of the acquired data to determine which component has the most accurate information for a given data point,” said Habib. “This is how we could integrate information on a small and large scale. One platform alone couldn’t do that. We needed to find a way for multiple platforms and sensors, providing different types of information, to work together. This gives the picture. full resolution in very high resolution. Fine details are not lost. “
A machine learning algorithm developed by the team to analyze the data is as important as the custom autonomous vehicles they created. Findings from a study using their technology are detailed in an article published in the journal Remote Sensing.
“This system collects a variety of information about each tree, including height, trunk diameter and branching information,” Habib said. “In addition to this information, we maintain the precise location and time tags of the acquired features.”
The result is like gifting a person with much-needed glasses. What was once blurry and uncertain becomes clear. Their vision has improved and, in turn, their understanding of what they see.
LiDAR works like a radar, but uses the light from a laser as a signal. LiDAR sensors evaluate the distance between the scanner and objects by using the time it takes for the signal to reach the objects and return to the sensor. On drones, airplanes or satellites, he takes measurements from above the canopy of trees and on itinerant vehicles or backpacks he takes measurements from under the canopy. Aircraft systems have continuous access to GNSS signals to locate sensor position and orientation after GNSS / INS integration and provide reasonable resolution. Ground systems, on the other hand, provide more detail and finer resolution, while suffering from potential GNSS signal dropouts, Habib said.
“This cross-platform system and this processing framework make the most of each to provide both fine detail and high positioning accuracy,” he said.
For example, if the backpack is in an area with poor access to GNSS signals, a drone could step in and put that data in the right place, he said.
“This is a breakthrough in applying new geomatic tools to forestry,” said Fei. “It is solving a real and urgent challenge in fields such as agriculture and transportation, but it is also extraordinary engineering and science that would be applied beyond an arena.”
As the different platforms work together, the system also identifies data points from each that equal the same characteristic of the tree. Eventually, it could correlate and find out what the data above the canopy means in terms of what’s happening under the canopy, Habib said. It would be a giant leap in speed and in the area of the forest that could be covered.