Microscope-based computer vision to characterize soil texture and soil organic matter

Sudarsan, Bharath; Ji, Wenjun; Biswas, Asim; Adamchuk, Viacheslav I.

doi:10.1016/j.biosystemseng.2016.06.006

Cited by 25 publications

(10 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their study uses microscope images to study texture. The R 2 of the fine fractions (clay+silt) measured in the laboratory is 0.88, and the RMSE is 44.7, but slightly better than the results observed by Bharath et al [41] using microscope computer vision technology (RMSE is 84.7). The results of this study are generally lower than those using spectroscopy techniques.…”

Section: Performance Comparison and Limitationcontrasting

confidence: 52%

“…In the range of 25% to 75% of sand and clay, there was a strong correlation between the predicted and measured sand and clay contents (R 2 >0.92). Sudarsan et al [13] developed a set of image acquisition systems by using a small and cheap hand-held microscope, and estimated the soil texture and soil organic matter by using various calculation parameters of the obtained images. The predicted performance of sand was better (R 2 =0.63).…”

Section: Introduction mentioning

confidence: 99%

See 1 more Smart Citation

In-situ soil texture classification and physical clay content measurement based on multi-source information fusion

Meng

Yang

Ren

et al. 2023

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

Soil texture is one of the most important soil characteristics that affect soil properties. Rapid acquisition of soil texture information is of great significance for accurate farmland management. Traditional soil texture analysis methods are relatively complicated and cannot meet the requirements of temporal and spatial resolution. This research introduced a self-developed vehicle-mounted in-situ soil texture detection system, which can predict the type of soil texture and the particle composition of the texture, and obtain real-time data during the measurement process without preprocessing the soil samples. The detection system is mainly composed of a conductivity measuring device, a camera, an auxiliary mechanical structure, and a control system. The soil electrical conductivity (ECa) and the texture features extracted from the surface image were input into the embedded model to realize real-time texture analysis. In order to find the best model suitable for the detection system, measurements were carried out in three test fields in Northeast and North China to compare the performance of different models applied to the detection system. The results showed that for soil texture classification, ExtraTrees performed best, with Precision, Recall, and F1 all being 0.82. For particle content of soil texture prediction, the R 2 of ExtraTrees was 0.77, and RMSE and MAPE were 74.72 and 39.58. It was observed that ECa, Moment of inertia, and Entropy had larger weights in the drawn model influence weight map, and they are the main contributors to predicting soil texture. These results showed the potential of the vehicle-mounted in-situ soil texture detection system, which can provide a basis for fast, cost-effective, and efficient soil texture analysis.

show abstract

Section: Performance Comparison and Limitationcontrasting

confidence: 52%

Section: Introduction mentioning

confidence: 99%

In-situ soil texture classification and physical clay content measurement based on multi-source information fusion

Meng

Yang

Ren

et al. 2023

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

show abstract

“…[22]. On the other hand, a study evaluating OM and texture found a correlation for the prediction of sandy soils was found with an R2 of 0.63 and for OM of 0.83 [23] .…”

Section: Introductionmentioning

confidence: 97%

Intelligent Spectroscopy System Used for Physicochemical Variables Estimation in Sugar Cane Soils

Landeta-Escamilla¹,

Sandoval-Gonzalez²,

Martínez-Sibaja³

et al. 2018

Preprint

View full text Add to dashboard Cite

Soil conditions is a major aspect of interest for farmers due to the knowing of the physicochemical properties of the same can help with any necessary restoration of soil that guarantees the quality and the production of their crop. However, technology and analysis of the soil become of difficult access mainly in developing countries, by which the present paper shows the development of a system thought to estimate physicochemical variables of soils growing sugar cane through studies of spectroscopy. Its characteristic is that it is a portable system, with low cost, easy to use and can estimate physicochemical variables in-situ with the objective of knowing the degree of degradation present in the soil and through this help the farmers define possible strategies to restore it. The device uses the frequency response of the soil determining values of magnitude and phase, which are used by algorithms of artificial intelligence capable of getting an estimation of the physicochemical properties. The obtained results show errors below 8% in the estimation of the variables compared to the analysis results of the soil at laboratories.

show abstract

“…Soil color has been used in soil identification also [15]. Soil color is a feature that has been observed to have strong correlation with spectral reflectance features and between soil organic matter and soil color [16], [17], [18], [19], [20], [35] and soil moisture content and soil color [21], [22], [23], [24]. Dark color of the soil is essentially linked to higher values of SOM, SMC, intrinsic soil fertility [25], [26], [45].…”

Section: Introductionmentioning

confidence: 99%

Predictive Analysis for Soil moisture content and Soil organic matter from Soil Images

Srivast

Shukla

Bansal

2022

Preprint

View full text Add to dashboard Cite

– Soil organic matter (SOM) and soil moisture contents (SMC) are two main properties in defining soil health. It is a challenge to measure organic matter and moisture content in soil, as the conventional methods are time, labor and money consuming. In order to overcome these challenges, various image processing based models have been proposed to predict SOM and SMC. Proposed model uses a stepwise multiple linear regression (SMLR) method to predict these properties on basis of soil color features like color moments, GLCMs and different color models as well, since, soil moisture and organic content are influenced by soil color. Multiple soil samples from field are collected with a certain distance in order to simulate continuous variation in the contents. Loss of ignition method is used to generate the ground truth to feed the model. For produce and compare the result first 34 and then 6 optimal predictor variables are used in model. The output results in external validation for SOM prediction were: R 2 = 0.07, RMSE = 0.76, RPIQ = 1.00 and that for SMC were: R 2 = 0.77, RMSE = 0.55, RPIQ = 1.07.

show abstract

Microscope-based computer vision to characterize soil texture and soil organic matter

Cited by 25 publications

References 35 publications

In-situ soil texture classification and physical clay content measurement based on multi-source information fusion

In-situ soil texture classification and physical clay content measurement based on multi-source information fusion

Intelligent Spectroscopy System Used for Physicochemical Variables Estimation in Sugar Cane Soils

Predictive Analysis for Soil moisture content and Soil organic matter from Soil Images

Contact Info

Product

Resources

About