Redirigiendo al acceso original de articulo en 22 segundos...
Inicio  /  Information  /  Vol: 14 Par: 7 (2023)  /  Artículo
ARTÍCULO
TITULO

Enabling Multi-Part Plant Segmentation with Instance-Level Augmentation Using Weak Annotations

Semen Mukhamadiev    
Sergey Nesteruk    
Svetlana Illarionova and Andrey Somov    

Resumen

Plant segmentation is a challenging computer vision task due to plant images complexity. For many practical problems, we have to solve even more difficult tasks. We need to distinguish plant parts rather than the whole plant. The major complication of multi-part segmentation is the absence of well-annotated datasets. It is very time-consuming and expensive to annotate datasets manually on the object parts level. In this article, we propose to use weakly supervised learning for pseudo-annotation. The goal is to train a plant part segmentation model using only bounding boxes instead of fine-grained masks. We review the existing weakly supervised learning approaches and propose an efficient pipeline for agricultural domains. It is designed to resolve tight object overlappings. Our pipeline beats the baseline solution by 23% for the plant part case and by 40% for the whole plant case. Furthermore, we apply instance-level augmentation to boost model performance. The idea of this approach is to obtain a weak segmentation mask and use it for cropping objects from original images and pasting them to new backgrounds during model training. This method provides us a 55% increase in mAP compared with the baseline on object part and a 72% increase on the whole plant segmentation tasks.

 Artículos similares

       
 
Nikos Tsiknakis, Elisavet Savvidaki, Sotiris Kafetzopoulos, Georgios Manikis, Nikolas Vidakis, Kostas Marias and Eleftherios Alissandrakis    
Pollen analysis and the classification of several pollen species is an important task in melissopalynology. The development of machine learning or deep learning based classification models depends on available datasets of pollen grains from various plant... ver más
Revista: Applied Sciences

 
Nikos Petrellis    
A low complexity image processing and a new classification method are proposed in this paper. These methods can be employed by plant disease diagnosis applications implemented on smart phones. The supported set of diseases can be extended by the end user... ver más
Revista: Applied Sciences

 
Jeyalakshmi S,R Radha    
Segmentation of leaf region from background is one of the essential pre-processing steps required in the Plant Leaf Image Processing.  This paper proposes an innovative segmentation approach for extracting color leaf region from the healthy or infec... ver más

 
Chengquan Zhou, Hongbao Ye, Zhifu Xu, Jun Hu, Xiaoyan Shi, Shan Hua, Jibo Yue and Guijun Yang    
Leaf coverage is an indicator of plant growth rate and predicted yield, and thus it is crucial to plant-breeding research. Robust image segmentation of leaf coverage from remote-sensing images acquired by unmanned aerial vehicles (UAVs) in varying enviro... ver más
Revista: Applied Sciences

 
Geice Paula Villibor, Fábio Lúcio Santos, Daniel Marçal de Queiroz, Joseph Kalil Khoury Júnior, Francisco de Assis de Carvalho Pinto     Pág. 41 - 48
Detachment of coffee fruit is usually accomplished by means of mechanical impacts and vibrations applied to the plant. Modal properties of the coffee fruit-stem system represent important information for efficient and selective harvesting. This study aim... ver más