# Estimates of maize plant density from UAV RGB images using Faster-RCNN detection model: impact of the spatial resolution

arXiv: https://arxiv.org/abs/2105.11857 · HTML: https://mlsanity.com/paper/2105.11857/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 78 references that are in the map.
- First posted on arXiv 25 May 2021.

## Builds on (most cited first, 20 of 20)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Learning a Single Convolutional Super-Resolution Network for Multiple Degradations](https://mlsanity.com/paper/1712.06116/) (2017)
- [An open access repository of images on plant health to enable the development of mobile disease diagnostics](https://mlsanity.com/paper/1511.08060/) (2015)
- [Frequency Separation for Real-World Super-Resolution](https://mlsanity.com/paper/1911.07850/) (2019)
- [Augmentation for small object detection](https://mlsanity.com/paper/1902.07296/) (2019)
- [Unsupervised Learning for Real-World Super-Resolution](https://mlsanity.com/paper/1909.09629/) (2019)
- [The Effects of Super-Resolution on Object Detection Performance in Satellite Imagery](https://mlsanity.com/paper/1812.04098/) (2018)
- [Task-Driven Super Resolution: Object Detection in Low-resolution Images](https://mlsanity.com/paper/1803.11316/) (2018)
- [HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection](https://mlsanity.com/paper/1604.00600/) (2016)
- [Global Wheat Head Detection (GWHD) dataset: a large and diverse dataset of high resolution RGB labelled images to develop and benchmark wheat head detection methods](https://mlsanity.com/paper/2005.02162/) (2020)
- [Face Detection with the Faster R-CNN](https://mlsanity.com/paper/1606.03473/) (2016)
- [Is Image Super-resolution Helpful for Other Vision Tasks?](https://mlsanity.com/paper/1509.07009/) (2015)
- [Unsupervised Image Super-Resolution with an Indirect Supervised Path](https://mlsanity.com/paper/1910.02593/) (2019)
- [Leveraging multiple datasets for deep leaf counting](https://mlsanity.com/paper/1709.01472/) (2017)

## Built on by (most cited first, 1 of 1)

- [Segmentation of arbitrary features in very high resolution remote sensing imagery](https://mlsanity.com/paper/2412.16046/) (2024)

## Abstract (arXiv)

Early-stage plant density is an essential trait that determines the fate of a genotype under given environmental conditions and management practices. The use of RGB images taken from UAVs may replace traditional visual counting in fields with improved throughput, accuracy and access to plant localization. However, high-resolution (HR) images are required to detect small plants present at early stages. This study explores the impact of image ground sampling distance (GSD) on the performances of maize plant detection at 3-5 leaves stage using Faster-RCNN. Data collected at HR (GSD=0.3cm) over 6 contrasted sites were used for model training. Two additional sites with images acquired both at high and low (GSD=0.6cm) resolution were used for model evaluation. Results show that Faster-RCNN achieved very good plant detection and counting (rRMSE=0.08) performances when native HR images are used both for training and validation. Similarly, good performances were observed (rRMSE=0.11) when the model is trained over synthetic low-resolution (LR) images obtained by down-sampling the native training HR images, and applied to the synthetic LR validation images. Conversely, poor performances are obtained when the model is trained on a given spatial resolution and applied to another spatial resolution. Training on a mix of HR and LR images allows to get very good performances on the native HR (rRMSE=0.06) and synthetic LR (rRMSE=0.10) images. However, very low performances are still observed over the native LR images (rRMSE=0.48), mainly due to the poor quality of the native LR images. Finally, an advanced super-resolution method based on GAN (generative adversarial network) that introduces additional textural information derived from the native HR images was applied to the native LR validation images. Results show some significant improvement (rRMSE=0.22) compared to bicubic up-sampling approach.