Unsupervised Greenhouse Tomato Plant Segmentation Based on Self-Adaptive Iterative Latent Dirichlet Allocation from Surveillance Camera

Abstract

It has long been a great concern in deep learning that we lack massive data for high-precision training sets, especially in the agriculture field. Plants in images captured in greenhouses, from a distance or up close, not only have various morphological structures but also can have a busy background, leading to huge challenges in labeling and segmentation. This article proposes an unsupervised statistical algorithm SAI-LDA (self-adaptive iterative latent Dirichlet allocation) to segment greenhouse tomato images from a field surveillance camera automatically, borrowing the language model LDA. Hierarchical wavelet features with an overlapping grid word document design and a modified density-based method quick-shift are adopted, respectively, according to different kinds of images, which are classified by specific proportions between fruits, leaves, and the background. We also utilize the feature correlation between several layers of the image to make further optimization through three rounds of iteration of LDA, with updated documents to achieve finer segmentation. Experiment results show that our method can automatically label the organs of the greenhouse plant under complex circumstances, fast and precisely, overcoming the difficulty of inferior real-time image quality caused by a surveillance camera, and thus obtain large amounts of valuable training sets.

Crop Organ Segmentation and Disease Identification Based on Weakly Supervised Deep Neural Network

“…That is to say, if the proportion of the fruit and the leaves in the image occupied most of the image and the background ratio is small, we prefer to define it as a close-up. To quantify the decision criterion, define a distance determination formula (DD) [22]:…”

A two-step registration-classification approach to automated segmentation of multimodal images for high-throughput greenhouse plant phenotyping

“…State of the art approaches to segmentation of plant images include Application of saliency approaches based on certain assumptions about image structure [ 2 , 3 ], for example, that majority of image pixels belong to plant-free background region, Construction of color-distance maps followed by their subsequent thresholding or clustering [ 4 , 5 ], Application of supervised and unsupervised classification and machine learning models [ 6 , 7 ], Co-registration of different image modalities, e.g., visible light (VIS) and infrared (IR) images [ 8 ], high-contrast fluorescence (FLU) and low-contrast visible light (VIS) or near-infrared (NIR) images [ 9 ]. Unfortunately, the prerequisites for saliency approaches is not always given.…”

“…Application of saliency approaches based on certain assumptions about image structure [ 2 , 3 ], for example, that majority of image pixels belong to plant-free background region,…”

“…• Application of saliency approaches based on certain assumptions about image structure [2,3], for example, that majority of image pixels belong to plant-free background region, • Construction of color-distance maps followed by their subsequent thresholding or clustering [4,5], • Application of supervised and unsupervised classification and machine learning models [6,7],…”