8/4/2019 Lu2004

1/22

Change Detection Techniques

D. LU, P. MAUSEL, E. BRONDIZIO and E. MORAN

Presented by Dahl WintersGeog 577, March 6, 2007

8/4/2019 Lu2004

2/22

Background

This paper summarizes change detection techniques, reviews their applications,and provides recommendations for selection of suitable change detectionmethods.

This paper is organized into eight sections as follows:

1. a brief introduction to applications of change detection techniques2. considerations before implementing change detection analyses

3. a summary and review of seven categories of change detection techniques

4. a review of comparative analyses among the different techniques

5. a brief review of global change analyses using coarse resolution satellitedata

6. threshold selection7. accuracy assessment

8. summary and recommendations

8/4/2019 Lu2004

3/22

Introduction

Good change detection research should provide the following information:

1. area change and change rate;

2. spatial distribution of changed types;

3. change trajectories of land-cover types; and

4. accuracy assessment of change detection results.

When implementing a change detection project, three major steps areinvolved:

1. image preprocessing including geometrical rectification and imageregistration, radiometric and atmospheric correction, and topographiccorrection if the study area is in mountainous regions;

2. selection of suitable techniques to implement change detectionanalyses; and

3. accuracy assessment.

8/4/2019 Lu2004

4/22

Introduction

The accuracies of change detection results depend on many factors,

including:

1. precise geometric registration between multi-temporal images,

2. calibration or normalization between multi-temporal images,

3. availability of quality ground truth data,

4. the complexity of landscape and environments of the study area,

5. change detection methods or algorithms used,

6. classification and change detection schemes,

7. analysts skills and experience,

8. knowledge and familiarity of the study area, and

9. time and cost restrictions.

8/4/2019 Lu2004

5/22

Applications of change detection techniques

land-use and land-cover (LULC) change

forest or vegetation change forest mortality, defoliation and damage assessment

deforestation, regeneration and selective logging

wetland change

forest fire and fire-affected area detection

landscape change

urban change

environmental change, drought monitoring, floodmonitoring, monitoring coastal marine environments,desertification, and detection of landslide areas

other applications such as crop monitoring, shiftingcultivation monitoring, road segments, and change in

glacier mass balance and facies.

8/4/2019 Lu2004

6/22

Considerations before doing change detection analyses

The temporal, spatial, spectral, and radiometric resolutions of remotely-sensed imagescan significantly impact the success of change detection.

Important environmental factors include atmospheric conditions, soil moisture conditions,and phenological characteristics.

The following conditions must be met:

1. precise registration of multi-temporal images2. precise radiometric and atmospheric calibration or normalization between multi-

temporal images

3. similar phenological states between multi-temporal images to eliminate seasonaland phenological differences, and

4. selection of the same spatial and spectral resolution images if possible

A change detection method should be selected that is appropriate to the data and studyarea. Some techniques can only provide change/no change information, while otherscan provide a complete matrix of change directions.

8/4/2019 Lu2004

7/22

The seven change detection technique categories

1. algebra

image differencing

image regression

image ratioing

vegetation index differencing

change vector analysis

background subtraction

2. transformation

PCA

Tasseled Cap (KT)

Gramm-Schmidt (GS)

Chi-Square

3. classification

Post-Classification Comparison

Spectral-Temporal Combined Analysis EM Transformation

Unsupervised Change Detection

Hybrid Change Detection

Artificial Neural Networks (ANN)

4. advanced models

Li-Strahler Reflectance Model Spectral Mixture Model

Biophysical Parameter Method

5. GIS

Integrated GIS and RS Method

GIS Approach

6. visual analysis

Visual Interpretation

7. other change detection techniques

Measures of spatial dependence

Knowledge-based vision system

Area production method

Combination of three indicators:

vegetation indices, land surfacetemperature, and spatial structure

Change curves

Generalized linear models

Curve-theorem-based approach

Structure-based approach

Spatial statistics-based method

8/4/2019 Lu2004

8/22

Category 1: Algebra

8/4/2019 Lu2004

9/22

Category 1: Algebra

8/4/2019 Lu2004

10/22

Category 2: Transformation

8/4/2019 Lu2004

11/22

Category 2: Transformation

8/4/2019 Lu2004

12/22

Category 3: Classification

8/4/2019 Lu2004

13/22

Category 3: Classification

8/4/2019 Lu2004

14/22

Category 3: Classification

8/4/2019 Lu2004

15/22

Category 4: Advanced Models

8/4/2019 Lu2004

16/22

Category 4: Advanced Models

8/4/2019 Lu2004

17/22

Category 5: GIS

8/4/2019 Lu2004

18/22

Categories 6 and 7

8/4/2019 Lu2004

19/22

Global change analyses and image resolution

For change detection at high or moderate spatial resolution: use Landsat TM, SPOT,or radar.

For change detection at the continental or global scale, use coarse resolution datasuch as MODIS and AVHRR.

AVHRR has daily availability at low cost; it is the best source of data for large areachange detection.

NDVI and land surface temperatures derived from MODIS or AVHRR thermal bandsare especially useful in large area change detection.

8/4/2019 Lu2004

20/22

Threshold Selection

Many change detection algorithms (in the algebra and transformation categories)

require threshold selection to determine whether a pixel has changed.

Thresholds can be adjusted manually until the resulting image is satisfactory, or theycan be selected statistically using a suitable standard deviation from a class mean.Both are highly subjective methods.

Other methods exist for improving the change detection results, such as using fuzzyset and fuzzy membership functions to replace the thresholds.

However, threshold selection is simple and intuitive, so it is still the most extensivelyapplied method for detecting binary change/no-change information.

8/4/2019 Lu2004

21/22

Accuracy Assessment

Accuracy assessments are important for understanding the change detection results

and using these results in decision-making.

However, they are difficult to do because reliable temporal field-based datasets areoften problematic to collect.

The error matrix is the most common method for accuracy assessment. To properly

generate one, the following factors must be considered:1. ground truth data collection,

2. classification scheme,

3. sampling scheme,

4. spatial autocorrelation, and

5. sample size and sample unit.

8/4/2019 Lu2004

22/22

Summary and Recommendations

Before any change detection project, there must be precise geometrical registration

and atmospheric correction or normalization between multi-temporal images. Also,suitable image acquisition dates and sensor data must be chosen, change categoriesmust be selected, and appropriate change detection techniques must be used.

The binary change/no-change threshold techniques all have difficulties indistinguishing true changed areas from the detected change areas. Single-bandimage differencing and PCA are the recommended methods.

Classification-based change detection methods can avoid such problems, but requiresmore effort to implement. Post-classification comparison is a suitable method whensufficient training data is available.

When multi-source data is available, GIS techniques can be helpful.

Advanced techniques such as LSMA, ANN, or a combination of change detectionmethods can produce higher quality change detection results.