Clifford Geometric Algebra-Based Approach for 3D Modeling of Agricultural Images Acquired by UAVs

Three-dimensional image modeling is essential in many scientific disciplines, including computer vision and precision agriculture.

So far, various methods of creating three-dimensional models have been considered. However, the processing of transformation matrices of each input image data is not controlled.

Site-specific crop mapping is essential because it helps farmers determine yield, biodiversity, energy, crop coverage, etc. Clifford Geometric Algebraic understanding of signaling and image processing has become increasingly important in recent years.

Geometric Algebraic treats multi-dimensional signals in a holistic way to maintain relationship between side sizes and prevent loss of information. This article has used agricultural images acquired by UAVs to construct three-dimensional models using Clifford geometric algebra. The qualitative and quantitative performance evaluation results show that Clifford geometric algebra can generate a three-dimensional geometric statistical model directly from UAVs’ RGB (Red Green Blue) images.

Through Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and visual comparison, the proposed algorithm’s performance is compared with latest algorithms. Experimental results show that proposed algorithm is better than other leading 3D modeling algorithms.

Read more:

https://www.researchgate.net/publication/347679848_Clifford_Geometric_Algebra-Based_Approach_for_3D_Modeling_of_Agricultural_Images_Acquired_by_UAVs

Aspen detection in boreal forests: Capturing a key component of biodiversity using airborne hyperspectral, lidar, and UAV data

Importance of biodiversity is increasingly highlighted as an essential part of sustainable forest management.

As direct monitoring of biodiversity is not possible, proxy variables have been used to indicate site's species richness and quality. In boreal forests, European aspen (Populus tremula L.) is one of the most significant proxies for biodiversity.

Aspen is a keystone species, hosting a range of endangered species, hence having a high importance in maintaining forest biodiversity. Still, reliable and fine-scale spatial data on aspen occurrence remains scarce and incomprehensive. Although remote sensing-based species classification has been used for decades for the needs of forestry, commercially less significant species (e.g., aspen) have typically been excluded from the studies.

This creates a need for developing general methods for tree species classification covering also ecologically significant species. Our study area, located in Evo, Southern Finland, covers approximately 83 km2, and contains both managed and protected southern boreal forests. The main tree species in the area are Scots pine (Pinus sylvestris L.), Norway spruce (Picea abies (L.) Karst), and birch (Betula pendula and pubescens L.), with relatively sparse and scattered occurrence of aspen.

Along with a thorough field data, airborne hyperspectral and LiDAR data have been acquired from the study area. We also collected ultra high resolution UAV data with RGB and multispectral sensors. The aim is to gather fundamental data on hyperspectral and multispectral species classification, that can be utilized to produce detailed aspen data at large scale. For this, we first analyze species detection at tree-level. We test and compare different machine learning methods (Support Vector Machines, Random Forest, Gradient Boosting Machine) and deep learning methods (3D Convolutional Neural Networks), with specific emphasis on accurate and feasible aspen detection.

The results will show, how accurately aspen can be detected from the forest canopy, and which bandwidths have the largest importance for aspen. This information can be utilized for aspen detection from satellite images at large scale.

Read more at https://ui.adsabs.harvard.edu/abs/2020EGUGA..2221268K/abstract

Tree Species Classification of UAV Hyperspectral and RGB Imagery with Deep Learning Convolutional Neural Networks

Interest in UAV solutions in forestry applications is growing.

Using UAVs, datasets can be captured flexibly and at high spatial and temporal resolutions when needed.

In forestry applications, fundamental tasks include the detection of individual trees, tree species classification, biomass estimation, etc. Deep Neural Networks (DNN) have shown superior results when comparing with conventional machine learning methods such as MLP (Multi-Layer Perceptron) in cases of huge input data.

The objective of this research is to investigate 3D Convolutional Neural Networks (3D-CNN) to classify three major tree species in a boreal forest: pine, spruce, and birch. The proposed 3D-CNN models were employed to classify tree species in a test site in Finland. The classifiers were trained with a dataset of 3039 manually labelled trees. Then the accuracies were assessed by employing independent datasets of 803 records.

To find the most efficient set of feature combination, it was compared the performances of 3D-CNN models trained with HS (HyperSpectral) channels, Red-Green-Blue (RGB) channels, and Canopy Height Model (CHM), separately and combined. It is demonstrated that the proposed 3D-CNN model with RGB and HS layers produces the highest classification accuracy. The producer accuracy of the best 3D-CNN classifier on the test dataset were 99.6%, 94.8%, and 97.4% for pines, spruces, and birches, respectively.

The best 3D-CNN classifier produced ~5% better classification accuracy than the MLP with all layers. The results suggest that the proposed method provides excellent classification results with acceptable performance metrics for HS datasets. The results show that pine class was detectable in most layers. Spruce was most detectable in RGB data, while birch was most detectable in the HS layers. Furthermore, the RGB datasets provide acceptable results for many low-accuracy applications.

Read more at: https://www.mdpi.com/2072-4292/12/7/1070

3D printed hyperspectral imagers to be mounted on UAVs

A team of researchers in Norway has developed a low-cost, 3D printed hyperspectral imager device which could be installed on UAVs to give them advanced imaging capabilities.

A study in the journal Optics Express details how to make the hyperspectral imager for about $700, which is significantly cheaper than existing tools of a similar caliber.

Hyperspectral imaging devices, for those unfamiliar, are not totally unlike color cameras you may be accustomed to, except that instead of only working with a color array based off of just three colors (RGB), they can detect hundreds of colors.

Presently, the research team is working on improving the imaging device’s sensitivity, as it is not quite as powerful as its more expensive counterparts: “There are many ways to use data acquired by hyperspectral imagers,” explains Fred Sigernes, the project’s leader from the University Centre in Svalbard (UNIS) in Norway. “By lowering the cost of these instruments, we hope that more people will be able to use this analytical technique and develop it further.”

The lightweight (200g)  3D printed device was tested using an octocopter UAV. Balanced with the help of a two-axis electronic stabilizing setup, the low-cost hyperspectral imager reportedly “performed well,” successfully detecting different elements of the landscape below it. The research team reportedly used a desktop 3D printer to manufacture customized holders for the device’s optics. According to Sigernes, the team opted to use plastic 3D printing rather than metal to cut back on time and costs: “3D printing with plastic is inexpensive and very effective for making even complex parts, such as the piece needed to hold the grating that disperses the light. I was able to print several versions and try them out,” he said. Down the line, the researchers say metal will be considered to make the device more durable.