Deep learning is currently being used in various fields. It is also used in plants for various purposes. 3D plant shoot segmentation has progressed significantly by integrating deep learning techniques with point clouds. Traditionally, 2D methods were used, but faced challenges in depth perception and structural determination. 3D images have addressed the limitations, providing better trait analysis in plant phenotypic trait extraction. However, 3D images also present the challenge that each point in the image must be carefully labeled, which is an expensive and time-consuming operation. That's why researchers have been investigating the use of supervised learning models, which use fewer labeled points.
Consequently, in a recent study called Eff-3DPSeg: 3D Organ-Level Plant Shoot Segmentation Using Deep Learning with Efficient Annotations, Researchers have introduced Eff-3DPSeg, a weakly supervised deep learning framework for plant organ segmentation. This framework uses a multi-view Stereo Pheno platform (MVSP2) and acquires point clouds of individual plants. These point clouds are then annotated using a Meshlab-based Plant Annotator (MPA).
For this framework, the researchers proposed two steps. First, they reconstructed high-resolution point clouds of soybean plants using a low-cost photogrammetry system, and developed a Meshlab-based Plant Annotator for plant point cloud annotation. After this, they used a weakly supervised deep learning method for plant organ segmentation. To do this, they first pre-trained the model with only about 0.5 percent of labeled points, then fine-tuned it using Viewpoint's bottleneck loss to learn a meaningful representation of intrinsic structure from point clouds. without processing. They then extracted three phenotypic traits: leaf length, width, and stem diameter.
Next, the researchers tested the framework's performance at various growth stages on a large spatiotemporal soybean data set. They compared this to fully labeled techniques on tomato and soybean plants. The stem-leaf segmentation results were accurate but had small classification errors at the junctions and edges of the leaves. Additionally, the approach performed better on less complex plant structures and achieved higher accuracy with larger training sets. Furthermore, quantitative results showed notable improvements over baseline techniques, particularly in less supervised environments.
However, the study also faced certain limitations. It had limitations due to lack of data and the need for separate training for different segmentation tasks. The researchers emphasized focusing on refining the framework in the future. They also want to expand the range of plant classifications made by this framework and the growth phases and improve the diversity of the method.
In conclusion, the Eff-3DPSeg framework may prove to be an important step forward in 3D plant shoot segmentation. Its efficient annotation process and precise segmentation capabilities have great potential to improve high performance. Furthermore, Eff-3DPSeg overcomes the challenges of expensive and time-consuming labeling processes through its weakly supervised deep learning and innovative annotation techniques.
Rachit Ranjan is a consulting intern at MarktechPost. He is currently pursuing his B.tech from the Indian Institute of technology (IIT), Patna. He is actively shaping his career in the field of artificial intelligence and data science and is passionate and dedicated to exploring these fields.
<!– ai CONTENT END 2 –>
