Measuring plant phenotypic parameters using improved neural radiance fields

Plant phenotyping has been widely used to quantitatively describe the plant's anatomical, ontogenetical, physiological, and biochemical properties. However, traditional measurement can often pose some challenges in recent years, due to the destructive nature, subjectivity, high costs, and operational complexities, particularly with three-dimensional measurement equipment. In this study, an advanced measurement approach was introduced for plant phenotypic parameters using an improved version of the Neural Radiance Field (NeRF), termed L-NeRF. Capturing image data from a multitude of perspectives and harnessing the prowess of L-NeRF technology for three-dimensional reconstruction has unlocked a new paradigm in the non-destructive acquisition of essential plant phenotypic parameters. This method has illuminated the path to obtaining critical measurements such as plant height, leaf width, and leaf length with unprecedented accuracy. The Prosopis juliflora, serving as a case study within a meticulously controlled indoor experimental environment, has yielded results that are a testament to the method's precision. The determination coefficients (R²) for leaf width, leaf length, and plant height are nothing short of remarkable, with values of 0.9037, 0.7827, and 0.8516, respectively. These high R² values are a clear indication of the strong correlation between the measured parameters and their true values, highlighting the method's reliability and accuracy. In stark contrast to the traditional Structure from Motion (SFM) visual reconstruction techniques, the L-NeRF technology has demonstrated a significant acceleration in the reconstruction process, reducing the time by an average of 30%. Moreover, it has substantially improved model accuracy, evidenced by a nearly 45% reduction in the standard deviation of model precision. These enhancements are not just quantitative—they represent a qualitative leap forward in the efficiency and precision of plant phenotyping. The experimental outcomes not only validate the efficacy and practicality of L-NeRF technology in measuring plant phenotypic parameters but also highlight its potential to significantly augment research efficiency and precision. The implications of these findings are far-reaching, opening the door to future studies that will explore a wider array of plant species, thereby expanding the method's applicability and versatility. The significance of this research extends beyond the immediate context of the study. It heralds the potential to revolutionize phenotyping in plant biology. By streamlining data acquisition and enhancing the accuracy of measurements, L-NeRF technology is poised to elevate the standards of plant phenotyping research. The pursuit of a more comprehensive dataset will contribute to a deeper understanding of plant phenotypic diversity, paving the way for innovative approaches in agricultural and botanical studies. Furthermore, the application of L-NeRF technology could extend to other domains of biological research, such as zoology, medical imaging, and environmental science. Its ability to provide high-resolution, three-dimensional data sets could prove invaluable in these fields, offering new insights and possibilities for research and application. In conclusion, the advent of L-NeRF technology for 3D reconstruction in plant phenotyping is a significant milestone. It represents a paradigm shift towards more efficient and accurate data acquisition methods, which will undoubtedly contribute to the advancement of scientific knowledge and the development of innovative solutions in agriculture and beyond. The non-destructive plant phenotyping techniques have promising potential for future innovations in the field of agricultural science and technology. The finding can also offer a novel approach to transforming plant phenotypic studies into breeding programs.