In the heart of Prague, a team of researchers led by Jiří Mach from the University of Chemistry and Technology has developed a groundbreaking, cost-effective solution for 3D plant reconstruction that could revolutionize precision agriculture and plant phenotyping. Published in the journal *Plant Methods* (translated to English as “Plant Methods”), this innovative approach leverages close-range photogrammetry and a robotic arm to capture detailed 3D models of plants, offering a flexible, affordable, and highly precise alternative to existing systems.
The study introduces a novel photogrammetric apparatus designed for routine analysis of plant morphological traits under controlled laboratory conditions. Unlike existing systems that often rely on expensive instrumentation and offer limited adaptability, this new platform combines affordability with high precision and robustness. The key innovation lies in the use of a robotic arm to control an industrial RGB camera, providing substantial flexibility in image acquisition. This mobility ensures comprehensive coverage of plants of different sizes and architectures while minimizing occlusions.
“Our system is designed to be both cost-effective and highly adaptable,” said Jiří Mach, lead author of the study. “By integrating a robotic arm with an industrial camera, we can capture detailed 3D models of plants with remarkable precision, making it a game-changer for plant phenotyping and precision agriculture.”
One of the distinctive features of this apparatus is the implementation of an optimized parameter tweak in the photogrammetric pipeline, which significantly improves the reconstruction of thin and delicate plant parts such as leaves, petioles, and fine stems. Combined with optimized acquisition parameters, including an exposure time of 50 milliseconds, a tweak value of 0.9, and a camera-to-object distance of 16 centimeters, the system achieves consistent model fidelity across diverse plant structures.
Efficiency was further enhanced through automation and an optimized scanning procedure. Comparative testing showed that using a larger number of camera positions with fewer frames per position improved throughput, with the best configuration consisting of three height levels and 40 frames each. These improvements reduced the processing time by 75%, decreasing the average scan duration from 8 minutes to only 2.7 minutes per plant, while maintaining accuracy and reliability.
The commercial implications of this research are substantial. Precision agriculture relies heavily on accurate and efficient 3D modeling to monitor plant development and health, supporting data-driven decision-making. The affordability and flexibility of this new system make it accessible to a broader range of researchers and practitioners, potentially accelerating advancements in crop protection, food quality assessment, and overall agricultural productivity.
“This research not only advances the field of plant phenotyping but also opens up new possibilities for precision agriculture,” added Mach. “By providing a cost-effective and highly precise tool, we hope to empower researchers and farmers to make more informed decisions, ultimately leading to improved crop yields and sustainability.”
The developed apparatus constitutes a reliable and low-cost solution that integrates robotic-assisted flexibility, improved reconstruction through the parameter tweak, and markedly reduced scanning time. The combination of precision, affordability, and efficiency makes the system competitive with existing approaches and, due to its accessibility and detailed methodological description, provides a distinctive contribution to the phenotyping community.
As the agricultural sector continues to evolve, the integration of advanced technologies like this photogrammetric apparatus will be crucial in driving innovation and sustainability. This research not only shapes the future of plant phenotyping but also sets a new standard for precision agriculture, paving the way for more efficient and data-driven farming practices.