A novel hyperspectral image classification approach based on multiresolution segmentation with a few labeled samples

Cui, Binge; Ma, Xiudan; Faxi, Zhao; Wu, Yanan

doi:10.1177/1729881417710219

Cited by 6 publications

(5 citation statements)

References 22 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is mainly related to the characteristics of HSI, where samples in a homogenous region are highly likely to belong to the same class label. Several studies have leveraged this theoretical basis, including Cui et al who employed multiresolution segmentation to segment the HSI and then randomly selected unlabeled pixels in the same region as the labeled pixels and assigned them the same pseudo-label [67]. Similarly, Zheng et al performed superpixel segmentation of the HSI and selected superpixels that contained only one labeled sample.…”

Section: Methods Based On Intra-domain Sample Set Expansion and Pseud...mentioning

confidence: 99%

Advances in Hyperspectral Image Classification Methods with Small Samples: A Review

Wang,

Liu,

Chi

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Hyperspectral image (HSI) classification is one of the hotspots in remote sensing, and many methods have been continuously proposed in recent years. However, it is still challenging to achieve high accuracy classification in applications. One of the main reasons is the lack of labeled data. Due to the limitation of spatial resolution, manual labeling of HSI data is time-consuming and costly, so it is difficult to obtain a large amount of labeled data. In such a situation, many researchers turn their attention to the study of HSI classification with small samples. Focusing on this topic, this paper provides a systematic review of the research progress in recent years. Specifically, this paper contains three aspects. First, considering that the taxonomy used in previous review articles is not well-developed and confuses the reader, we propose a novel taxonomy based on the form of data utilization. This taxonomy provides a more accurate and comprehensive framework for categorizing the various approaches. Then, using the proposed taxonomy as a guideline, we analyze and summarize the existing methods, especially the latest research results (both deep and non-deep models) that were not included in the previous reviews, so that readers can understand the latest progress more clearly. Finally, we conduct several sets of experiments and present our opinions on current problems and future directions.

show abstract

Section: Methods Based On Intra-domain Sample Set Expansion and Pseud...mentioning

confidence: 99%

Advances in Hyperspectral Image Classification Methods with Small Samples: A Review

Wang,

Liu,

Chi

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The outcomes were consistent which demonstrated that the proposed method attained enhanced accuracy than both RMKL and RBMKL methods and resolves grouping coefficients of MKL by boosting systems. The limitation of the study was that it was used for limited training samples [20]. Sowmya et al (2016) proposed an algorithm for dimension reduction and classification of Indian Pines and Salinas-A datasets, using the techniques of band selection approach.…”

Section: Survey Carried Outmentioning

confidence: 99%

Approaches for Hyperspectral Image Classification Detailed Review

Kushalatha¹,

Prasantha²,

Shetty³

2021

IJSCE

View full text Add to dashboard Cite

Hyperspectral Image (HSI) processing is the new advancement in image / signal processing field. The growth over the years is appreciable. The main reason behind the successful growth of the Hyperspectral imaging field is due to the enormous amount of spectral and spatial information that the imagery contains. The spectral band that the HSI which contains is also more in number. When an image is captured through the HSI cameras, it contains around 200-250 images of the same scene. Nowadays HSI is used extensively in the fields of environmental monitoring, Crop-Field monitoring, Classification, Identification, Remote sensing applications, Surveillance etc. The spectral and spatial information content present in Hyperspectral images are with high resolutions.Hyperspectral imaging has shown significant growth and widely used in most of the remote sensing applications due to its presence of information of a scene over hundreds of contiguous bands In. Hyperspectral Image Classification of materials is the critical application of HSI using Hyperspectral sensors. It collects hundreds of spectrum channels, where each channel consists of a sharp point of Electromagnetic Spectrum. The paper mainly focuses on Deep Learning techniques such as Convolutional Neural Network (CNN), Artificial Neural Network (ANN), and Support Vector machines (SVM), K-Nearest Neighbour (KNN) for the accuracy in classification. Finally in the summary the current state-of-the-art scheme, a critical discussion after reviewing the research work by other professionals and organizing it into review-based paper, also implying about the present status on classification accuracy using neural networks is carried out.

show abstract

“…7 It proposes a new adaptive threshold segmentation algorithm which is resistant to interference from complex environments. The next work 8 develops a novel hyperspectral image classification approach based on multiresolution segmentation with a few labeled samples, which is motivated by the fact that pixels within a homogenous region are very likely to have the same class label, which can be utilized to increase the number of labeled samples. In another paper, 9 a hand and club tracking framework based on recognition with a complex descriptor combining histograms of oriented gradients and spatial–temporal vector is proposed to obtain their movement trajectories in golf video.…”

Section: The Papersmentioning

confidence: 99%