Classification Model of Urban Riverside Landscape Using the Oder River as an Example

Abstract

This study aims to present the classification model of urban riverside landscapes. The subject of the research is the riverside landscape of Wroclaw, Poland, as seen from the level of the Oder River. The assessment was made with the use of the statistical method-the analysis of discriminant functions. The assessment was conducted on the basis of a detailed analysis of the linear film picture. In order to build the model on the passage of 70 km, eight parameters, in 354 points every 200 m, were assessed. The statistical method was used for modeling. The developed model, based on the 8 parameters, allows for classifying landscapes into the 5 classes of landscape value on the grounds of the classification values for cases. The efficiency of the developed model is estimated to be on the level of 77%. The built model can constitute an objective tool of landscape classification that supports making planning decisions. The application of the model in spatial planning would be allowed to include aesthetic and landscape aspects in the process of developing riverside areas of a city.

Using google street view panoramas to investigate the influence of urban coastal street environment on visual walkability

“…In streets with wide pavements and low interface continuity, boulevards can be created by planting tall trees that can enhance the walk and recreational quality of the streets. Some studies based on perception have shown that the plant community is an important factor influencing aesthetic perception (Iwona 2019), the abundant plant species can effectively enhance the visual quality of streets (Sun et al 2018). In addition, the monotonous street space is brought to life by enriching the hierarchy of plant landscapes (Held 2020).…”

Study on Remote Sensing Image Classification of Oasis Area Based on ENVI Deep Learning

“…It is calculated by dividing the number of pixels on the diagonal of a particular class of features in the confusion matrix by the sum of the pixels in the same row as that class. The following is the calculation formula: (5) Where: X ij for the number of samples with land cover j categorized as land cover type i; *j for the number of samples whose total number of samples is classified as land cover type j.…”

“…Remote sensing image classification method research has always been a critical component of the field of remote sensing science. Numerous scholars have conducted extensive research on remote sensing image classification in recent years and proposed many theories and models for remote sensing image classification [5][6]. Machine learning algorithms frequently use classification methods such as the artificial neural network (ANN) [7], the support vector machine (SVM) [8], and the random forest (RF) [9].…”