Recognition and localization of maize leaves in RGB images based on Point-Line Net

Plant phenotype detection plays a crucial role in understanding and studying plant biology, agriculture, and ecology. It involves the quantification and analysis of various physical traits and characteristics of plants, such as plant height, leaf shape, angle, number, and growth trajectory. By accurately detecting and measuring these phenotypic traits, researchers can gain insights into plant growth, development, stress tolerance, and the influence of environmental factors. Among these phenotypic information, the number of leaves and growth trajectory of the plant are more accessible. Nonetheless, obtaining these information is labor-intensive and financially demanding. With the rapid development of computer vision technology and artificial intelligence, using maize field images to fully analyze plant-related information such as growth trajectory and number of leaves can greatly eliminate repetitive labor work and enhance the efficiency of plant breeding. However, the application of deep learning methods still faces challenges due to the serious occlusion problem and complex background of field plant images. In this study, we developed a deep learning method called Point-Line Net, which is based on the Mask R-CNN frame-work, to automatically recognize maize field images and determine the number and growth trajectory of leaves and roots. The experimental results demonstrate that the object detection accuracy (mAP) of our Point-Line Net can reach 81.5%. Moreover, to describe the position and growth of leaves and roots, we introduced a new lightweight "keypoint" detection branch that achieved 33.5 using our custom distance verification index. Overall, these findings provide valuable insights for future field plant phenotype detection, particularly for the datasets with dot and line annotations.