TheLNet270v1 – A Novel Deep-Network Architecture for the Automatic Classification of Thermal Images for Greenhouse Plants

Abstract

The real challenge for separating leaf pixels from background pixels in thermal images is associated with various factors such as the amount of emitted and reflected thermal radiation from the targeted plant, absorption of reflected radiation by the humidity of the greenhouse, and the outside environment. We proposed TheLNet270v1 (thermal leaf network with 270 layers version 1) to recover the leaf canopy from its background in real time with higher accuracy than previous systems. The proposed network had an accuracy of 91% (mean boundary F1 score or BF score) to distinguish canopy pixels from background pixels and then segment the image into two classes: leaf and background. We evaluated the classification (segment) performance by using more than 13,766 images and obtained 95.75% training and 95.23% validation accuracies without overfitting issues. This research aimed to develop a deep learning technique for the automatic segmentation of thermal images to continuously monitor the canopy surface temperature inside a greenhouse.

A Comprehensive Review on Deep Learning Assisted Computer Vision Techniques for Smart Greenhouse Agriculture

“…Islam et al [97] addressed the complications in separating leaf pixels from backgrounds in thermal images due to factors like thermal radiation and greenhouse humidity. They proposed TheLNet270v1, achieving a remarkable 91% accuracy in distinguishing canopy pixels.…”

“…A major limitation identified is the shortage of large-scale standardized image datasets for the greenhouse domain (as noted in [65], [101], [104]). Most studies rely on small proprietary datasets collected by the researchers themselves, often just a few hundred images, which restricts generalization of techniques ( [92], [97], [106]). There is a need to establish extensive public databases encapsulating the diversity of greenhouse environments, with variability in factors like lighting, humidity, crop types, growth stages, and imaging angles represented ( [91], [94], [105]).…”

“…Overall, while deep learning has shown immense potential, realizing robust computer vision for greenhouses will require specialized model architectures and training techniques tailored to the unique intricacies of controlled environments ( [91], [93], [97]). Greenhouse-specific networks, re-training regimes, augmented data, and continual optimization will be instrumental in developing computer vision solutions adept at the nuances of greenhouse conditions.…”

Deep Learning in Controlled Environment Agriculture: A Review of Recent Advancements, Challenges and Prospects

“…As described in [ 40 , 42 , 45 , 48 , 50 , 61 ], R-CNN models such as Mask-RCNN and Faster-RCNN, two of the most widely used DL models, are used in crop yield prediction applications, especially for tomato and strawberry. Other custom DL models for detecting crops have been proposed in the studies of [ 35 , 38 , 44 , 54 ].…”

A Novel Method for Quantifying Plant Morphological Characteristics Using Normal Vectors and Local Curvature Data via 3D Modelling—A Case Study in Leaf Lettuce

“…Noncontact and nondestructive image-based analyses of plant morphology are continually advancing. Data obtained from image analysis technology, such as quantitative characteristic loci (QTL) analysis and genome-wide association studies (GWAS), have been used in molecular genetics [ 2 , 3 ] and is beginning to be used for growth monitoring and growth prediction in crop cultivation [ 4 , 5 , 6 , 7 , 8 ]. Furthermore, image-based 3D measurement methods are also being developed and researched [ 9 , 10 , 11 , 12 ].…”