Spatial Super Resolution of Real-World Aerial Images for Image-Based Plant Phenotyping

Abstract

Unmanned aerial vehicle (UAV) imaging is a promising data acquisition technique for image-based plant phenotyping. However, UAV images have a lower spatial resolution than similarly equipped in field ground-based vehicle systems, such as carts, because of their distance from the crop canopy, which can be particularly problematic for measuring small-sized plant features. In this study, the performance of three deep learning-based super resolution models, employed as a pre-processing tool to enhance the spatial resolution of low resolution images of three different kinds of crops were evaluated. To train a super resolution model, aerial images employing two separate sensors co-mounted on a UAV flown over lentil, wheat and canola breeding trials were collected. A software workflow to pre-process and align real-world low resolution and high-resolution images and use them as inputs and targets for training super resolution models was created. To demonstrate the effectiveness of real-world images, three different experiments employing synthetic images, manually downsampled high resolution images, or real-world low resolution images as input to the models were conducted. The performance of the super resolution models demonstrates that the models trained with synthetic images cannot generalize to real-world images and fail to reproduce comparable images with the targets. However, the same models trained with real-world datasets can reconstruct higher-fidelity outputs, which are better suited for measuring plant phenotypes.

REMA: A Rich Elastic Mixed Attention Module for Single Image Super-Resolution

“…In recent times, attention-based algorithms have gained prominence, notably after the popularity of Transformer-based algorithms. In fact, there have already been plenty of studies proposing attention-based SISR methods [14][15][16][17] to restore details. Most studies prefer to design a specific SISR network utilizing attention rather than a plug-and-play attention module to improve the reconstruction quality, resulting in a lack of flexibility in methods.…”

Development and application of a more refined process for extracting rock crack width information based on artificial intelligence

“…Therefore, the super-resolution reconstruction (SRR) technique is introduced to solve the problem of insufficient image resolution. Compared to SRR techniques based on interpolation algorithms, deep learning-based SRR networks can be used to overcome the technical obstacles of detecting rock cracks based on UAV and CV to obtain more accurate results [10]. On the other hand, for noncontact measurements, the accuracy of parameter information extraction of rock cracks is largely influenced by the detection results, which in turn is influenced by the performance of SRR networks.…”