Significance of Textural Features in Aerial Images

Chaluvadi, Mahesh; Raghunadh, M. V.; Pullarao, Chennamsetty; Kishore, M. Sankar

doi:10.1080/09747338.2012.10876088

Cited by 2 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study aimed at assessing the performance of GLCM texture values derived from individual bands of WorldView-2 imagery in quantifying woody plant species diversity in a dry season. Many studies have focused on imagery at coarser resolutions (e.g., [33,35,37,43,59,[76][77][78][79]) that may ignore processes occurring at finer spatial resolutions (i.e. within pixel variation).…”

Section: Discussionmentioning

confidence: 99%

“…It is noteworthy to mention the weak estimation capability of some of the GLCMs, particularly homogeneity and mean (Fig 3) which do not specifically measure gray level dispersion. Homogeneity measures and represents the amount of local similarity in the image window [76] while mean measures the average gray level values in a window.…”

Section: Glcms Vs Model Performancementioning

confidence: 99%

See 1 more Smart Citation

Estimation of woody plant species diversity during a dry season in a savanna environment using the spectral and textural information derived from WorldView-2 imagery

et al. 2020

View full text Add to dashboard Cite

Remote sensing techniques are useful in the monitoring of woody plant species diversity in different environments including in savanna vegetation types. However, the performance of satellite imagery in assessing woody plant species diversity in dry seasons has been understudied. This study aimed to assess the performance of multiple Gray Level Co-occurrence Matrices (GLCM) derived from individual bands of WorldView-2 satellite imagery to quantify woody plant species diversity in a savanna environment during the dry season. Woody plant species were counted in 220 plots (20 m radius) and subsequently converted to a continuous scale of the Shannon species diversity index. The index regressed against the GLCMs using the all-possible-subsets regression approach that builds competing models to choose from. Entropy GLCM yielded the best overall accuracy (adjusted R 2 : 0.41−0.46; Root Mean Square Error (RMSE): 0.60−0.58) in estimating species diversity. The effect of the number of predicting bands on species diversity estimation was also explored. Accuracy generally increased when three-five bands were used in models but stabilised or gradually decreased as more than five bands were used. Despite the peak accuracies achieved with three-five bands, performances still fared well for models that used fewer bands, showing the relevance of few bands for species diversity estimation. We also assessed the effect of GLCM window size (3×3, 5×5 and 7×7) on species diversity estimation and generally found inconsistent conclusions. These findings demonstrate the capability of GLCMs combined with high spatial resolution imagery in estimating woody plants species diversity in a savanna environment during the dry period. It is important to test the performance of species diversity estimation of similar environmental setups using widely available moderate-resolution imagery.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Glcms Vs Model Performancementioning

confidence: 99%

Estimation of woody plant species diversity during a dry season in a savanna environment using the spectral and textural information derived from WorldView-2 imagery

et al. 2020

View full text Add to dashboard Cite

show abstract

“…There are different metrics used as expressions of textural features, and entropy is one of them. This parameter measures an image's disorder: if an image is not uniform in terms of texture, a high entropy value will characterise it [42]. Entropy and other textural features have been widely used in remote sensing with reasonably satisfactory results [43]; in particular, these features can be directly used for scene classification or to improve LULC classification accuracy by adding information to spectrum-related data [44].…”

Section: Introductionmentioning

confidence: 99%

Supporting Pro-Poor Reforms of Agricultural Systems in Eastern DRC (Africa) with Remotely Sensed Data: A Possible Contribution of Spatial Entropy to Interpret Land Management Practices

Marinis

Petris

Sarvia

et al. 2021

Land

View full text Add to dashboard Cite

In the eastern Democratic Republic of Congo, agriculture represents the most important economic sector, and land control can be considered a perpetual source of conflict. Knowledge of the existing production system distribution is fundamental for both informing national land tenure reforms and guiding more effective agricultural development interventions. The present paper focuses on existing agricultural production systems in Katoyi collectivity, Masisi territory, where returning Internally and Externally Displaced People are resettling. We aim to define a repeatable methodology for building evidence-based and updated knowledge concerning the spatial distribution of the two existing production systems: subsistence-oriented agriculture (SOA) and business-oriented agriculture (BOA). To this aim, we used a supervised object-based classification approach on remotely sensed Sentinel-2 imagery to classify land cover. To classify production systems further within the “agriculture” and “pasture” land use classes, binary classification based on an entropy value threshold was performed. An iterative approach was adopted to define the final HNDVI threshold that minimised commission and omission errors and maximised overall accuracy and class separability. The methodology achieved acceptable observed accuracy (OA equal to 80–90% respectively for agricultural and pasture areas) in the assessment. SOA and BOA respectively covered 24.4 and 75.6% of the collectivity area (34,606 ha). The results conclude that land use and entropy analysis can draw an updated picture of existing land distribution among different production systems, supporting better-adapted intervention strategies in development cooperation and pro-poor agrarian land tenure reforms in conflict-ridden landscapes.

show abstract

Significance of Textural Features in Aerial Images

Cited by 2 publications

References 2 publications

Estimation of woody plant species diversity during a dry season in a savanna environment using the spectral and textural information derived from WorldView-2 imagery

Estimation of woody plant species diversity during a dry season in a savanna environment using the spectral and textural information derived from WorldView-2 imagery

Supporting Pro-Poor Reforms of Agricultural Systems in Eastern DRC (Africa) with Remotely Sensed Data: A Possible Contribution of Spatial Entropy to Interpret Land Management Practices

Contact Info

Product

Resources

About