Unmanned Aerial Systems for Determining Vegetative Establishment on ALDOT Construction Sites

Details

• Creators:
  Singh, Puranjit ; Bao, Yin ; Perez, Michael A ; Donald, Wesley N.
• Corporate Creators:
  Auburn University. Highway Research Center
• Corporate Contributors:
  Alabama. Department of Transportation
• Subject/TRT Terms:
  Data Collection Image Analysis Landscape Maintenance Machine Learning Remote Sensing Roadside Flora Vegetation Control
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report
• Corporate Publisher:
  Alabama. Department of Transportation
• Abstract:
  Roadside vegetation composition assessment is essential to maintain ecological stability, control invasive species, and to ensure the adoption of environmental regulations around construction zones. Traditional monitoring methods involving visual inspections are time-consuming, labor-intensive, and not scalable. Remote sensing offers a valuable alternative in automating large-scale vegetation assessment tasks efficiently. Our study compares the performance of proximal RGB imagery processed using deep learning (DL) techniques against the Vegetation Indices (VIs) extracted at higher altitudes, establishing a foundation to use the prior in performing vegetation analysis using unmanned aerial vehicles (UAVs) for a broader scalability. A pixel-wise annotated dataset for eight roadside vegetation species was curated to evaluate the performance of multiple semantic segmentation models in this context. The best-performing MAnet DL achieved a mean intersection over union of 0.90, highlighting models’ capability in composition assessment tasks. Additionally, in predicting the vegetation cover – the DL model achieved a R2 of 0.99, RMSE of 1.761 and outperformed the top VI method of SAVI which achieved a R2 of 0.49, RMSE of 23.473. The strong performance of DL models on proximal RGB imagery under-scores the potential of UAV-mounted high resolution RGB sensors for automated roadside vegetation monitoring and management tasks at construction sites. The NDVI ortho mosaic image of the Prattville construction site.
• Format:
  PDF
• Collection(s):
  US Transportation Collection
• Main Document Checksum:
  urn:sha-512:dbddc721e058a47f8f6f0c948b12b789392de4dc0668eaa157e4443830123ca4664041d71b0504a16701ebc716ab230917b7523939dbf5137c348bedc7765e15
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/85648/dot_85648_DS1.pdf
• File Type:
  [PDF - 11.04 MB ]