A Deep Learning Model Compression and Ensemble Approach for Weed Detection

Ofori, Martinson; El‐Gayar, Omar F.; O'Brien, Austin; Noteboom, Cherie

doi:10.24251/hicss.2022.138

Cited by 9 publications

(9 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results presented by the SSD ResNet 50 model align with those shown by Ofori et al [39], where this model performed better than other DL models, including SSD Inception v2. Pearse et al [35] and Samiei et al [40] presented the ResNet model variations that performed slightly better than that proposed in this study (98% and 90%, respectively).…”

Section: Discussionsupporting

confidence: 85%

“…Thus, the phenotypic traits for phenological identification are restricted to leaves (e.g., number, size, and colour). Furthermore, considering that vegetable crops are often sown as mixed cropping, and the morphological traits of leaves are very similar between plants, especially in the early growth stages, it is difficult to identify the specific phenotypic traits in order to classify the phenophases of the corresponding plant (crops and weeds included) [38][39][40].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Computer Vision and Deep Learning as Tools for Leveraging Dynamic Phenological Classification in Vegetable Crops

et al. 2023

View full text Add to dashboard Cite

The efficiency of agricultural practices depends on the timing of their execution. Environmental conditions, such as rainfall, and crop-related traits, such as plant phenology, determine the success of practices such as irrigation. Moreover, plant phenology, the seasonal timing of biological events (e.g., cotyledon emergence), is strongly influenced by genetic, environmental, and management conditions. Therefore, assessing the timing the of crops’ phenological events and their spatiotemporal variability can improve decision making, allowing the thorough planning and timely execution of agricultural operations. Conventional techniques for crop phenology monitoring, such as field observations, can be prone to error, labour-intensive, and inefficient, particularly for crops with rapid growth and not very defined phenophases, such as vegetable crops. Thus, developing an accurate phenology monitoring system for vegetable crops is an important step towards sustainable practices. This paper evaluates the ability of computer vision (CV) techniques coupled with deep learning (DL) (CV_DL) as tools for the dynamic phenological classification of multiple vegetable crops at the subfield level, i.e., within the plot. Three DL models from the Single Shot Multibox Detector (SSD) architecture (SSD Inception v2, SSD MobileNet v2, and SSD ResNet 50) and one from You Only Look Once (YOLO) architecture (YOLO v4) were benchmarked through a custom dataset containing images of eight vegetable crops between emergence and harvest. The proposed benchmark includes the individual pairing of each model with the images of each crop. On average, YOLO v4 performed better than the SSD models, reaching an F1-Score of 85.5%, a mean average precision of 79.9%, and a balanced accuracy of 87.0%. In addition, YOLO v4 was tested with all available data approaching a real mixed cropping system. Hence, the same model can classify multiple vegetable crops across the growing season, allowing the accurate mapping of phenological dynamics. This study is the first to evaluate the potential of CV_DL for vegetable crops’ phenological research, a pivotal step towards automating decision support systems for precision horticulture.

show abstract

Section: Discussionsupporting

confidence: 85%

Section: Introductionmentioning

confidence: 99%

Computer Vision and Deep Learning as Tools for Leveraging Dynamic Phenological Classification in Vegetable Crops

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Specifically, training accurate models for image segmentation requires the production of hand annotated training datasets, which is time consuming and requires specialized expertise to properly annotate training image data ( Kamilaris and Prenafeta-Boldú, 2018 ). Further, the computing resources required for training and applying deep learning models are unique, more common to computer gaming systems or graphics design work, rather than traditional computational systems ( Gao et al, 2020 ; Ofori et al, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

A workflow for segmenting soil and plant X-ray computed tomography images with deep learning in Google’s Colaboratory

et al. 2022

View full text Add to dashboard Cite

X-ray micro-computed tomography (X-ray μCT) has enabled the characterization of the properties and processes that take place in plants and soils at the micron scale. Despite the widespread use of this advanced technique, major limitations in both hardware and software limit the speed and accuracy of image processing and data analysis. Recent advances in machine learning, specifically the application of convolutional neural networks to image analysis, have enabled rapid and accurate segmentation of image data. Yet, challenges remain in applying convolutional neural networks to the analysis of environmentally and agriculturally relevant images. Specifically, there is a disconnect between the computer scientists and engineers, who build these AI/ML tools, and the potential end users in agricultural research, who may be unsure of how to apply these tools in their work. Additionally, the computing resources required for training and applying deep learning models are unique, more common to computer gaming systems or graphics design work, than to traditional computational systems. To navigate these challenges, we developed a modular workflow for applying convolutional neural networks to X-ray μCT images, using low-cost resources in Google’s Colaboratory web application. Here we present the results of the workflow, illustrating how parameters can be optimized to achieve best results using example scans from walnut leaves, almond flower buds, and a soil aggregate. We expect that this framework will accelerate the adoption and use of emerging deep learning techniques within the plant and soil sciences.

show abstract

“…With respect to related work, it becomes necessary to explore DL methods dealing with lower volumes such as transfer learning and model compression for more computationally efficient models. Ofori et al have several works showing that models with pre-trained weights outperform state-out-the-art CNNs [20,21].…”

Section: Discussionmentioning

confidence: 99%

“…Regarding greener DL models in applications domains, we can find advances for greener DL-based solutions as well. For instance, for weed detection, Ofori et al combined the mobile-sized EfficientNet with transfer learning to achieve up to 95.44% classification accuracy on plant seedlings [20], and model compression achieving 62.22% smaller in size than DenseNet (the smallest-sized full-sized model) [21]. Moreover, for pig posture classification, Witte et al reported the YOLOv5 model achieving an accuracy of 99,4% for pig detection, and EfficientNet achieving a precision of 93% for pig posture classification [22].…”

Section: Green Aimentioning

confidence: 99%

Energy Efficiency of Training Neural Network Architectures: An Empirical Study

Xu,

Martínez-Fernández,

Martinez

et al. 2023

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

The evaluation of Deep Learning (DL) models has traditionally focused on criteria such as accuracy, F1 score, and related measures. The increasing availability of high computational power environments allows the creation of deeper and more complex models. However, the computations needed to train such models entail a large carbon footprint. In this work, we study the relations between DL model architectures and their environmental impact in terms of energy consumed and CO 2 emissions produced during training by means of an empirical study using Deep Convolutional Neural Networks. Concretely, we study: (i) the impact of the architecture and the location where the computations are hosted on the energy consumption and emissions produced; (ii) the trade-off between accuracy and energy efficiency; and (iii) the difference on the method of measurement of the energy consumed using software-based and hardware-based tools.

show abstract

A Deep Learning Model Compression and Ensemble Approach for Weed Detection

Cited by 9 publications

References 31 publications

Computer Vision and Deep Learning as Tools for Leveraging Dynamic Phenological Classification in Vegetable Crops

Computer Vision and Deep Learning as Tools for Leveraging Dynamic Phenological Classification in Vegetable Crops

A workflow for segmenting soil and plant X-ray computed tomography images with deep learning in Google’s Colaboratory

Energy Efficiency of Training Neural Network Architectures: An Empirical Study

Contact Info

Product

Resources

About