UAV Remote Sensing for Urban Vegetation Mapping Using Random Forest and Texture Analysis

By Quanlong Feng, Jiantao Liu, Jianhua Gong. Remote Sensing, 2015

552 citations recorded by the source corpus.

Unmanned aerial vehicle (UAV) remote sensing has great potential for vegetation mapping in complex urban landscapes due to the ultra-high resolution imagery acquired at low altitudes. Because of payload capacity restrictions, off-the-shelf digital cameras are widely used on medium and small sized UAVs. The limitation of low spectral resolution in digital cameras for vegetation mapping can be reduced by incorporating texture features and robust classifiers. Random Forest has been widely used in satellite remote sensing applications, but its usage in UAV image classification has not been well documented. The objectives of this paper were to propose a hybrid method using Random Forest and texture analysis to accurately differentiate land covers of urban vegetated areas, and analyze how classification accuracy changes with texture window size. Six least correlated second-order texture measures were calculated at nine different window sizes and added to original Red-Green-Blue (RGB) images as ancillary data. A Random Forest classifier consisting of 200 decision trees was used for classification in the spectral-textural feature space. Results indicated the following: (1) Random Forest outperformed traditional Maximum Likelihood classifier and showed similar performance to object-based image analysis in urban vegetation classification; (2) the inclusion of texture features improved classification accuracy significantly; (3) classification accuracy followed an inverted U relationship with texture window size. The results demonstrate that UAV provides an efficient and ideal platform for urban vegetation mapping. The hybrid method proposed in this paper shows good performance in differentiating urban vegetation mapping. The drawbacks of off-the-shelf digital cameras can be reduced by adopting Random Forest and texture analysis at the same time.

Subfields: Ecology, Environmental Engineering, Media Technology

View Paper: https://www.semanticscholar.org/paper/23b71fd06bab951765c8d60968a3210f6b196835

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Environmental Engineering

In Media Technology

Citations in the corpus

Unmanned Aerial Vehicle for Remote Sensing Applications - A Review (2019, methodology): “E ﬀ orts in such dynamic scene analysis include accurate mapping urban vegetation and impervious surfaces using combined high-resolution DSMs and orthophotos [78,142], with improved land-cover classiﬁcation [7].”
Evaluation of UAV imagery for mapping Silybum marianum weed patches (2017, background): “Similarly, classification of vegetation types improved considerably by inserting texture features in RGB very high resolution UAV images of an urban environment (Feng, Liu, and Gong 2015).”
Identification of banana fusarium wilt using supervised classification algorithms with UAV-based multi-spectral imagery (2020, background): “RF is an ensemble of many independent individual classification and regression trees (CART) and is defined as([47]): {h(x, θk), k=1,2,.”
Urban Flood Mapping Based on Unmanned Aerial Vehicle Remote Sensing and Random Forest Classifier—A Case of Yuyao, China (2015, methodology): “We chose Pix4D software [15] as the preprocessing tool due to its high efficiency and good accuracy.”
Quantifying Boreal Forest Structure and Composition Using UAV Structure from Motion (2018, background): “High-resolution orthophotos [20,21] and structure from motion (SfM) plus multi-view stereo (MVS) [22–26] have been shown to be effective for vegetation mapping across a wide range of forest biomes.”
Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery (2017, background): “In addition, Feng et al. [51] stated that with ntree = 200, RF could achieve accurate results.”
Building an efficient intrusion detection system based on feature selection and ensemble classifier (2019, background): “Besides, overfitting is less of an issue compared to individual decision tree, and there is no need to prune the trees which is a cumbersome task [27].”