Skip to main content
ARS Home » Plains Area » Temple, Texas » Grassland Soil and Water Research Laboratory » Research » Publications at this Location » Publication #418885
Research Project: Enhancing Cropping System and Grassland Sustainability in the Texas Gulf Coast Region by Managing Systems for Productivity and Resilience

Location: Grassland Soil and Water Research Laboratory

Title: Early seedling counts: Enhancing producer confidence

Author
item RAM SAPKOTA, BALA - Texas A&M University
item BAATH, GURJINDER - Texas Agrilife Research
item BAWA, ARUN - Texas Agrilife Research
item SARKAR, SAYANTAN - Texas Agrilife Research
item Flynn, Kyle
item Smith, Douglas

Submitted to: Meeting Abstract
Publication Type: Abstract Only
Publication Acceptance Date: 8/29/2024
Publication Date: N/A
Citation: N/A

Interpretive Summary: n/a - abstract only.

Technical Abstract: Seedling emergence is crucial for timely field decisions like replanting. Conventional methods, such as manual stand counts, are time-consuming and resource-intensive. Recent advancements in aerial imagery using unmanned aerial systems (UAS) offer a high-throughput alternative for field scouting. However, these systems often rely on discriminating green plant pixels from soil, which is unreliable in organic production systems with weeds and crop stubbles. Our study aimed to develop an algorithm to estimate cotton and corn seedling counts from aerial imagery, discriminating them from weeds and stubbles. We utilized automated plant detection and counting algorithms resembling an organic field setup. Results showed that for cotton, flying at 20 m height, the best results were at 16 days after planting (DAP) with an R² of 0.85, improving to 0.89 at 26 DAP after weed removal. For corn, flying at 30 m, R² values were 0.97 at 12 DAP and 0.94 at 17 DAP. These findings demonstrate that multispectral imagery from UAS can significantly benefit plant population assessment, aiding early replanting decisions.