Wearable technology platform monitors inventory volume of bulk materials quickly and cost effectively
Purdue civil engineers developed a SMART platform with funding from the Indiana Department of Transportation
WEST LAFAYETTE, Ind. – Civil engineers at Purdue University have developed a fully automated, portable system for estimating inventory volume of bulk supplies like salt and other materials used in industrial, highway and agricultural applications.
The Indiana Department of Transportation funded the research through its Joint Transportation Research Program. An article on the innovation was published in the peer-reviewed journal Remote Sensing.
Inventory management is important in road maintenance, which uses salt to de-ice roads to keep traffic flowing safely, and in other applications. Government agencies are increasingly interested in monitoring stocks to assess their impact on the environment, including effects on roadside vegetation and surface water salinity. Salt and sand can also affect pavement durability.
Jeremy McGuffey, manager of statewide winter operations for INDOT, said the department has nearly 120 salt storage buildings statewide and most locations visually estimate the volume.
“This is inherently incorrect and will vary from person to person,” McGuffey said. “If I pointed to a pile of stone on the ground, could another person tell me the exact volume of that stone based on sight alone?
“There are a few places that use surveying equipment to take measurements based on the exterior size – the height and width – of the stock, but these don’t take depth into account. Many of our buildings are full of salt all year round, and there is no way to reach the back of the heap to determine its length.
Traditional inventory measurement methods use field survey procedures that take several hours and expose survey teams to hazardous conditions. Modern LiDAR technology – or light detection and ranging technology – is safer and more reliable, but its peak performance is limited to well-planned scanning schemes and complex data processing when it comes to large interior sites.
Salt Monitoring and Reporting Technology, or SMART, was created by Ayman Habib, Thomas A. Page Professor of Civil Engineering, and Darcy Bullock, Lyles Family Professor of Civil Engineering, both of the Lyles School of Civil Purdue Engineering.
Habib said SMART incorporates consumer sensing modalities of imaging and LiDAR units to acquire storage data in less than 10 minutes per installation, even in harsh environmental situations.
“SMART also uses an innovative data processing strategy that can manage this data for accurate inventory volume assessment and provide a visual record of the mapped facility in the form of colorized point clouds,” Habib said.
SMART is more accurate, more cost-effective, and more secure than traditional commercial technologies for estimating bulk material inventory volume.
“The technology estimates volume with less than 1% error and costs less than $10,000; existing technologies cost more than double,” Habib said. “It also enables convenient, fast and safe data acquisition. Some traditional technologies require an operator to scale inventory, which leads to prolonged and dangerous data acquisition.
McGuffey said SMART has already brought positive results to INDOT.
“With the system we developed with Purdue, the empty dimensions of the building are first solved, and then the volume of the salt pile can be easily calculated. The LiDAR system bounces light off the pile millions of times to collect the information we need to determine volume,” McGuffey said. “The other huge benefit is that this system is largely automated, with the only real human interaction being initial setup and then periodic cleaning.”
Habib and Bullock leaked the information to the Purdue Research Foundation’s technology commercialization office, which filed a patent application with the US Patent and Trademark Office. For more information on licensing opportunities, contact OTC’s Dhananjay Sewak at [email protected] on 2021-HABI-69512.
Habib said the next steps in SMART’s development are to package the system so it can be permanently mounted in a storage facility to enable automated data collection, to enhance its ability to work in storage facilities with domed roofs and to improve the value of the data by driving colorized points.
About Purdue University
Purdue University is a leading public research institution that develops practical solutions to today’s toughest challenges. Ranked in each of the past four years as one of the 10 most innovative universities in the United States by US News & World Report, Purdue delivers groundbreaking research and groundbreaking discoveries. Committed to hands-on, online, real-world learning, Purdue provides transformative education for all. Committed to affordability and accessibility, Purdue has frozen tuition and most fees at 2012-13 levels, allowing more students than ever to graduate debt-free. Learn how Purdue never stops in the persistent pursuit of the next giant leap at https://stories.purdue.edu.
About the Purdue Research Foundation Office of Technology Commercialization
The Purdue Research Foundation’s Office of Technology Commercialization operates one of the most comprehensive technology transfer programs among leading research universities in the United States. The services provided by this office support Purdue University’s economic development initiatives and benefit the university’s academic activities through Purdue’s marketing, licensing and protection. intellectual property. The office is located in the Convergence Center for Innovation and Collaboration in the Discovery Park District at Purdue, adjacent to the Purdue campus. In fiscal year 2021, the bureau reported 159 agreements finalized with 236 technologies signed, 394 disclosures received, and 187 U.S. patents granted. The office is managed by the Purdue Research Foundation, which received the 2019 Innovation and Economic Prosperity Universities Award for Place from the Association of Public and Land-grant Universities. In 2020, IPWatchdog Institute ranked Purdue third nationally for startup creation and in the top 20 for patents. The Purdue Research Foundation is a private, nonprofit foundation established to advance the mission of Purdue University. Contact [email protected] for more information.
Writer: Steve Martin, [email protected]
Sources: Ayman Habib, [email protected]
Jeremy McGuffey, [email protected]
Image-Assisted LiDAR Mapping Platform and Data Processing Strategy for Inventory Volume Estimation
Raja Manish, Seyyed Meghdad Hasheminasab, Jidong Liu, Yerassyl Koshan, Justin Anthony Mahlberg, Yi-Chun Lin, Radhika Ravi, Tian Zhou, Jeremy McGuffey, Timothy Wells, Darcy Bullock and Ayman Habib
Stock quantity monitoring is essential for agencies and companies to maintain inventory of bulk materials such as salt, sand, aggregates, lime and many other materials commonly used in agriculture, highways and industrial applications. Traditional approaches to volumetrically valuing bulk material inventory, such as counting truckloads, are inaccurate and subject to cumulative error over a long period of time. Modern airborne and ground-based remote sensing platforms equipped with cameras and/or light detection and ranging (LiDAR) units are increasingly popular for performing high-fidelity geometric measurements. Current use of these sensing technologies for stockpile volume estimation is affected by environmental conditions such as lack of Global Navigation Satellite System (GNSS) signals, poor lighting, and/or featureless surfaces. . This study addresses these limitations through a novel mapping platform called Stockpile Monitoring and Reporting Technology (SMART), which is designed and integrated as a fast and cost-effective stock monitoring solution. The new mapping framework is carried out using a camera and LiDAR data fusion that facilitates the estimation of stockpile volume under harsh environmental conditions. LiDAR point clouds are derived from a sequence of data collections from different scans. In order to handle the sparse nature of data collected during a given scan, an automated image-assisted LiDAR coarse registration technique is developed, followed by a novel segmentation approach to derive features, which are used for registration. end. The resulting 3D point cloud is then used for accurate volume estimation. Field surveys have been conducted on stocks of varying size and shape complexity. An independent assessment of inventory volume using terrestrial laser scanners (TLS) shows that the developed frame had a relative error of almost 1%.