Real-Time Automated Classification of Sky Conditions Using Deep Learning and Edge Computing

Abstract

The radiometric quality of remotely sensed imagery is crucial for precision agriculture applications because estimations of plant health rely on the underlying quality. Sky conditions, and specifically shadowing from clouds, are critical determinants in the quality of images that can be obtained from low-altitude sensing platforms. In this work, we first compare common deep learning approaches to classify sky conditions with regard to cloud shadows in agricultural fields using a visible spectrum camera. We then develop an artificial-intelligence-based edge computing system to fully automate the classification process. Training data consisting of 100 oblique angle images of the sky were provided to a convolutional neural network and two deep residual neural networks (ResNet18 and ResNet34) to facilitate learning two classes, namely (1) good image quality expected, and (2) degraded image quality expected. The expectation of quality stemmed from the sky condition (i.e., density, coverage, and thickness of clouds) present at the time of the image capture. These networks were tested using a set of 13,000 images. Our results demonstrated that ResNet18 and ResNet34 classifiers produced better classification accuracy when compared to a convolutional neural network classifier. The best overall accuracy was obtained by ResNet34, which was 92% accurate, with a Kappa statistic of 0.77. These results demonstrate a low-cost solution to quality control for future autonomous farming systems that will operate without human intervention and supervision.

Sky Image Classification Based on Transfer Learning Approaches

“…For instance, the research conducted by Joby M. Prince Czarnecki et al [ 10 ] employed two ResNet architectures and achieved their best result with the ResNet-34 model. Similarly, the study by Muhammad Umair and Manzoor Ahmed Hashmani [ 19 ] utilized GoogLeNet , ResNet-50 , and EfficientNet-B0 architectures, with their best performance being obtained using the EfficientNet-B0 model.…”

“…Sky conditions, particularly cloud shadowing, play a pivotal role in determining the quality of images captured by low-altitude sensing platforms. For instance, in a study by Czarnecki et al [ 10 ], various deep learning approaches were compared to classify sky conditions, particularly regarding cloud shadows in agricultural fields, using visible spectrum cameras. Subsequently, they developed an artificial intelligence-based edge computing system to automate the classification process entirely.…”

Sky Image Classification Based Solar Power Prediction Using CNN

“…Therefore, as Xie et al [2] point out, renewable energy resources are being promoted due to their eco-friendly nature, inexhaustibility, low cost, reliability, and resilience. Energy from renewable sources [3] can be produced for transportation, space and water heating and cooling, and electrical production. Efficient methods of generating electrical power have become significant to the global economy [4].…”