Hyperspectral Remote Sensing Classifications: A Perspective Survey

Abstract

Classification of hyperspectral remote sensing data is more challenging than multispectral remote sensing data because of the enormous amount of information available in the many spectral bands. During the last few decades, significant efforts have been made to investigate the effectiveness of the traditional multispectral classification approaches on hyperspectral data. Formerly extensively established conventional classification methods have been dominated by the advanced classification approaches and many pre-processing techniques have been developed and incorporated in hyperspectral classification. A perspective survey of hyperspectral remote sensing classification approaches is presented here. It comprehensively highlights the taxonomy of major classification approaches reported during the last two decades and describes an experimental evaluation of a few major classification algorithms. Recent advancements in the development of classification approaches are also emphasized with a set of guidelines for achieving better classification performances.

Multiple Flights or Single Flight Instrument Fusion of Hyperspectral and ALS Data? A Comparison of their Performance for Vegetation Mapping

“…For classification, the Random Forests (RF) supervised classification algorithm was used; this creates multiple decision trees based on a random subset of the dataset [34]. The RF classifier is popular in the remote sensing community, with a range of commonly cited advantages, including its low parameterization requirements [34], good classification results [35], and ability to handle noisy observation data or outliers in a complex measurement space and small training data relative to the study area size [36][37][38]. Ensembles of 500 trees were used for each classification, which was sufficient to obtain consistent and stable results, with a number of variables considered for splitting equal to the square root of the number of features.…”

Deep&Dense Convolutional Neural Network for Hyperspectral Image Classification

“…This leads to a better discrimination among the different materials contained in the image, allowing hyperspectral imagery (HSI) to serve as a tool for the analysis of the surface of the Earth in many applications [26][27][28][29]. The analysis of HSIs involves a wide range of techniques, including classification [29,30], spectral unmixing [31][32][33][34], target and anomaly detection [35][36][37][38]. In recent years, HSI classification has become a popular research topic in the remote sensing field [39].…”

Crop recognition under weedy conditions based on 3D imaging for robotic weed control

“…Images containing invisible wavebands were reported to be effective in segmenting vegetation from soil, particularly images having near‐infrared band . Hyperspectral imaging was investigated for plant species differentiation and was found to be effective under controlled illumination and by using thermally stabilized cameras . Also, it is more robust to occlusion and less computationally intensive than shape‐based pattern recognition algorithms.…”