Integration advances forestry technology | The Manila Times

Through the integration of sensors and systems for mobile aerial and ground mapping, a team of digital forestry researchers in Purdue has used advanced technology to locate, count, and measure more than a thousand trees in just a few hours.

“The machines are counting and measuring each tree; it’s not a calculation using modeling, it’s a real forest inventory,” said Songlin Fei, dean’s remote sensing president and professor of forestry and natural resources and leader of Purdue University’s Digital Forestry initiative. . “This is a pioneering development in the use of technology to make a rapid and accurate inventory of the global forest ecosystem on our path, which would improve the ability to prevent forest fires, detect diseases, perform accurate carbon counts, and make forest management decisions.”

The technology uses manned aircraft, unmanned drones and backpack-mounted systems. The systems integrate light detection and cameras with distance units or LiDARs, along with navigation sensors, including integrated global navigation systems (GNSS) and inertial navigation systems (INS). Ayman Habib, Professor of Civil Engineering at Thomas A. Page and Head of Purdue’s Digital Photogrammetry Research Group, co-designed and created the systems designed and created by a Purdue team who led the project together with Fei.

“Different parts of the system take advantage of the synergistic characteristics of the data obtained to determine which component contains the most accurate information for a particular data point,” Habib said. “That way we could incorporate small-scale and large-scale information. A single platform couldn’t do that. We had to find a way for multiple platforms and sensors to work together, providing different types of information. That gives the whole picture very high resolution. Fine details are not lost. “

The machine learning algorithm developed by the data analysis team is just as important as the custom autonomous vehicles they have created. The results of a study using their technology are set out in an article published in the journal Remote Sensing.

Get the latest news

send it to your inbox

Sign up for The Manila Times daily

By registering with an email address, I agree to read and agree to the Terms of Service and Privacy Policy.

“This system collects a variety of information about each tree, including height, trunk diameter, and branch information,” Habib said. “In addition to this information, we maintain accurate location and time labels for acquired features.”

The result is like giving a person the glasses they need. What was once vague and questionable is clear. It improves their vision and, at the same time, their understanding of what they see.

LiDAR works like a radar, but uses the light of a laser as a signal. LiDAR sensors evaluate the distance between the scanning system and objects using the time it takes for signals to travel to objects and return to the sensor. In drones, airplanes, or satellites, it takes measurements above the fat of trees, and in vehicles or backpacks, it takes measurements below fat. Overhead systems have continuous access to GNSS signals to determine the location and orientation of the sensor after GNSS / INS integration and provide reasonable resolution. Ground-based systems, on the other hand, provide more detail and finer resolution while suffering from potential GNSS signals, Habib said.

“This cross-platform system and processing framework takes the best of each to provide fine detail and high position accuracy,” he said.

For example, if the backpack is in an area with poor access to GNSS signals, a drone can enter it and put that data in the right place, he said.

“It’s a breakthrough in applying new geomatic tools to forestry,” Feik said. “It is solving a real and urgent challenge in areas such as agriculture and transportation, but it is also an amazing engineering and science that would be applied beyond one area.”

As different platforms work together, the system is also identifying the data points of each with the same characteristics as the tree. In the end, it could correlate and find out what the data above means, in terms of what happens under the cannon, Habib said. It would be a huge leap in the speed and area of ​​the forest that could be covered.


Leave a Comment