A survey of image classification methods and techniques for improving classification performance

Lu, Dengsheng; Weng, Qihao

doi:10.1080/01431160600746456

Cited by 2,746 publications

(1,707 citation statements)

References 300 publications

Supporting

Mentioning

1,596

Contrasting

Unclassified

100

Order By: Relevance

“…The nature of LU/LC change maps ('from -to') were for seven epochs, namely 1985-1990, 1990-1995, 1995-2000, 2000-2005, 2005-2009, 2009-2015, and 1985-2015. Accuracy assessment measures the degree of closeness to true values. Error matrix is a common method in the accuracy assessment process, including overall accuracy, producer's accuracy, user's accuracy, and kappa coefficient [23]- [24]. Around 500 randomly distributed points were identified on the reference image and attributed to the four categories.…”

Section: Change Detection and Accuracy Assessmentmentioning

confidence: 99%

Spatio-Temporal Analysis of Land Use and Land Cover Changes in Arid Region of Saudi Arabia

Albalawi¹

2018

GEOMATE

View full text Add to dashboard Cite

Changes in land use/land cover (LU/LC) are a major factor driving global environmental change, especially in arid and semi-arid regions. As a result, expansion of agriculture and urbanization is occurring in ecologically fragile lands. This paper analyzed and assessed land use/land cover changes in an agricultural center Tabuk in Saudi Arabia, object-based classification technique (OBC) using Landsat images for seven years (1985, 1990, 1995, 2000, 2005, 2009, and 2015) were used for LU/LC analysis. The urban growth type for Tabuk was measured using Urban Growth Analysis Tool (UGAT) within a GIS. The study found an increase in urban areas from 48 km 2 in 1985 to 315 km 2 in 2015. A significant increase of 61% in agricultural land, from 1985 (112 km 2 ) to (577 km 2 ) in 2015. This expansion is occurring at the expense of the barren land with a loss of 768 km 2 . An overall classification accuracy ranged from 94% to 97% across all images. The urban growth type for Tabuk was determined as 72% to be of the extension-type over the study period, with urban areas expanding in a direction towards the northwest and west area. Assessing spatial and temporal LU/LC change has aided to understand the impacts of expanding agriculture and urban areas. The LU/LC maps could aid government planners and decision-makers to analyze and manage agricultural and urban growth.

show abstract

Section: Change Detection and Accuracy Assessmentmentioning

confidence: 99%

Spatio-Temporal Analysis of Land Use and Land Cover Changes in Arid Region of Saudi Arabia

Albalawi¹

2018

GEOMATE

View full text Add to dashboard Cite

show abstract

“…In [9], Lu & Weng present an overview of the problem of classification of remote sensing images including the steps which comprise the process (extraction of features, segmentation, classification and accuracy assessment) and the research challenges faced. For each step, most of the existing techniques until 2005 are presented, grouped by the approach adopted (such as techniques that exploits classification by pixels or regions).…”

Section: Related Workmentioning

confidence: 99%

Interactive Classification of Remote Sensing Images by Using Optimum-Path Forest and Genetic Programming

Santos

Silva

Torres

et al. 2011

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

Abstract. The use of remote sensing images as a source of information in agribusiness applications is very common. In those applications, it is fundamental to know how the space occupation is. However, identification and recognition of crop regions in remote sensing images are not trivial tasks yet. Although there are automatic methods proposed to that, users very often prefer to identify regions manually. That happens because these methods are usually developed to solve specific problems, or, when they are of general purpose, they do not yield satisfying results. This work presents a new interactive approach based on relevance feedback to recognize regions of remote sensing. Relevance feedback is a technique used in content-based image retrieval (CBIR) tasks. Its objective is to aggregate user preferences to the search process. The proposed solution combines the Optimum-Path Forest (OPF) classifier with composite descriptors obtained by a Genetic Programming (GP) framework. The new approach has presented good results with respect to the identification of pasture and coffee crops, overcoming the results obtained by a recently proposed method and the traditional Maximimun Likelihood algorithm.

show abstract

“…Many researchers have made great efforts in developing advanced techniques for improving classification accuracy [2]. As to the complexity of terrain and remote sensing process, the phenomenon of same terrain shows various spectral features and same spectral feature shows different terrain feature exist in the remote sensing images, which result in complex classification.…”

Section: Introductionmentioning

confidence: 99%

“…Land cover is a fundamental parameter that impacts on and links many parts of human and physical environments [1].Remote sensing image classification has become the main source for land cover maps, and the classification results are the basis for many environmental and socioeconomic applications [2]. For several decades the remote sensing data classification technology has gained great achievements.…”

Section: Introductionmentioning

confidence: 99%

A Novel ACO Based Land Cover Classification Approach Using Optical and SAR Data

Dai¹,

Liu²,

Yang³

et al. 2014

IJCEE

View full text Add to dashboard Cite

Abstract-The land cover classification methods based on statistical theory using remote sensing data have great achievements for the last several decades, but they have exposed some weaknesses in dealing with multi-source and multi-dimensional data. Ant colony optimization (ACO), as an excellent intelligent algorithm, has been applied on many research fields for solving optimization issues. How to solve the optimization problem of sampling data is the key step in process of land cover classification with multi-source and multi-dimensional data, so ACO algorithm has many potential advantages in the field of remote sensing data processing. In this paper, an intelligent method is developed for classifying the land cover types combining Landsat TM data with Envisat ASAR data on the basis of ACO algorithm. For identifying the classification precision of land cover with ACO algorithm, we respectively compare it with the results by Maximum Likelihood Classification (MLC) and decision tree C4.5. The comparing results show that ACO algorithm can well take advantages of optical and radar data to improve classification precision and select the best features subsets to construct simpler rules.Index Terms-Ant colony optimizations (ACO), combination of Landsat TM and envisat ASAR data, land cover classification.

show abstract

A survey of image classification methods and techniques for improving classification performance

Cited by 2,746 publications

References 300 publications

Spatio-Temporal Analysis of Land Use and Land Cover Changes in Arid Region of Saudi Arabia

Spatio-Temporal Analysis of Land Use and Land Cover Changes in Arid Region of Saudi Arabia

Interactive Classification of Remote Sensing Images by Using Optimum-Path Forest and Genetic Programming

A Novel ACO Based Land Cover Classification Approach Using Optical and SAR Data

Contact Info

Product

Resources

About