nghiên cứu đề xuất phương pháp nhận dạng và phân loại vết dầu trên biển từ tư liệu viễn thám siêu cao tần bản tóm tắt tiếng anh

MINISTRY OF EDUCATION & TRAINING
UNIVERSITY OF MINING AND GEOLOGY


LE MINH HANG


RESEARCH PROPOSAL METHOD FOR IDENTIFICATION
AND CLASSIFICATION OF OIL SPILLS AT SEA
BY MICROWAVE REMOTE SENSING DATA

Research field: Geodesy and mapping
Code: 62520503


SUMMARY OF PHD THESIS




Hanoi – 2013

The thesis has been completed at Photogrammetry & Remote Sensing
Department, Faculty of Geodesy, University of Mining and Geology,
Hanoi

Full name of supervisors:
1. Assoc. Prof. Nguyen Dinh Duong
Institute of geographic, Vietnam Academy of Science and
Technology

2. Assoc. Prof . Tran Dinh Tri
University of Mining and Geology

Examiner 1: Assoc.Prof. Nguyen Dinh Minh
University of Science, Vietnam National University, Hanoi
Examiner 2: Dr. Tran Dinh Luat
Vietnam Natural Resources and Environment Corporation, Ministry of
Natural Resources and Environment
Examiner 3: Dr. Nguyen Du Khang
Vietnam Remote Sensing Center, Ministry of Natural Resources and
Environment

The thesis will be defended at the University examination Council at the
Hanoi university of Mining and Geology At… h, …/…/, 2013

This thesis can be referenced at the National Library
or at the library of the Hanoi University of Mining and Geology

LIST OF SCIENCE WORKS HAVE BEEN PUBLISHED BY
AUTHOR RELATED CONTENT OF THE THESIS

1. HANG le minh, DUONG Nguyen Dinh (2009), Oil spill detection and
Classification by ALOS PALSAR at VietnamEastSea, The 7
th
FIG Regional
Conference: Spatial Data Serving People, Land Governance and the
Environment-Building the Capacity, Hanoi, Vietnam
2. Lê Minh Hằng, Nguyễn Đình Dương (2010), Chuyển đổi dữ liệu từ
raster sang vector áp dụng với đối tượng vùng trong quan trắc vết dầu trên
biển, Tạp chí Khoa học kỹ thuật Mỏ - Địa chất, Số 30/4-2010, tr.63-69, Hà

Nội.
3. Le Minh Hang, Nguyen Dinh Duong (2010), Practical implementation of
vectorization of oil spills detected at sea on SAR image, The 31
th
Asian
Conference on Remote Sensing, Hanoi, Vietnam
4. Lê Minh Hằng, Nguyễn Đình Dương (2010), Xây dựng chương trình đọc
tư liệu viễn thám siêu cao tần phục vụ phân tích vết dầu trên biển, Tuyển tập
Báo cáo Hội nghị khoa học lần thứ 19 – Quyển 06 Trắc địa, tr.61- 66,
Trường Đại học Mỏ - Địa chất, Hà Nội.
5. Nguyễn Đình Dương, Nguyễn Mai Phương, Lê Minh Hằng (2010),
Chuẩn hóa tư liệu ảnh SAR trên biển trong mặt cắt ngang, Tuyển tập các
công trình khoa học, Hội nghị khoa học Địa lý – Địa chính, tr.5 – 14,
Trường Đại học Khoa học tự nhiên, Đại học quốc gia Hà Nội, Hà Nội
6. Lê Minh Hằng, Nguyễn Đình Dương (2011), Tổng quan về các phương
pháp nhận dạng và phân loại vết dầu trên biển bằng tư liệu viễn thám siêu
cao tần, Tạp chí Khoa học kỹ thuật Mỏ - Địa chất, Số 35/7-2011, tr.66-71,
Hà Nội.
7. Lê Minh Hằng, Nguyễn Đình Dương (2011), Xây dựng chương trình đọc
dữ liệu ảnh vệ tinh EnviSAT ASAR chế độ thu nhận WSM, Tạp chí Khoa
học kỹ thuật Mỏ - Địa chất, Số 36/10-2011,tr.68-73, Hà Nội.
8. Nguyen Dinh Duong, Nguyen Mai Phuong, Le Minh Hang (2012),
OilDetect 1.0 - A System for Analysis of Oil Spill in Sar Image, Vol 12, No
2, tr.12-18, Tạp chí AJG (Asian Journal of Geoinfomatics)
9. Lê Minh Hằng, Nguyễn Đình Dương (2012), Nghiên cứu tách vết dầu
trên dữ liệu ảnh SAR bằng thuật toán nở vùng, Tạp chí Khoa học kỹ thuật
Mỏ - Địa chất, Số 38/4-2012, tr. 68-72, Hà Nội.
1

INTRODUCTION

1. Background
With the coastline stretching from north to south, there are many
areas to exploit oil and gas in the Vietnam East Sea and lie on the main
traffic at sea of the world so that the Vietnam East Sea often appear oil
pollution at sea. In recent years, Vietnam has continuously occurred oil spill
which unknown origin in the central coastal region. The phenomenon of the
oil spill was detected only when oil spill was hit to ashore by the waves.
Vietnam completely passive to response the oil spill at sea because of non-
system for early detecting and monitoring of oil pollution at sea.
Nowadays, remote sensing techniques are being applied to the
early detecting and monitoring of oil pollution at sea all over the world,
especially RADAR system. RADAR is a system having active microwave
remote sensing, allowing the observation both day and night, in any kind of
weather conditions, not affected by cloud, fog over sea surface and having
wide swath. These are some advantages of microwave remote sensing data
comparing with the optical data for monitoring and early detection of oil
pollution at sea. Due to receiving backscatter energy of microwave sensors
and declining the wave fluctuations at oil slick, oil spills are constrasted with
surrounding sea using SAR image so that extraction and classification of oil
spills in SAR image can be processed automatically. However, sea weather,
the processing of microwave data systems in Vietnam is limited so that it is
needed of research proposal methods for identification and classification of
oil spills at sea by microwave remote sensing data consistent with the
Vietnam conditions.
2. Objectives of the study
- To study the methodology and the factors affecting the identification and
classification oil spill at sea by SAR image data.
- To research the method for identification and classification oil spill at sea
by SAR image data.

- To propose the method for identification and classification oil spill at sea
2

by SAR image data consistent with the Vietnam conditions.
3. Subjects of study
- The characteristics of the transmitting and receiving signals of microwave
satellite.
- The impact of oil spill in declining the intensity fluctuations of waves and
characteristics of backscatter at the microwave satellite sensor.
- The factors affecting the accuracy of the identification and classification
of oil spill at sea by SAR image.
- The method for identification and classification of oil spill at sea by
microwave remote sensing data.
4. Range of the research
- The methodology is proposed to identify and classify the unknown origin
oil spills at seamainly discharge from from ships by SAR image data.
- The range of study is Vietnam East Sea.
- The research ability RADAR image of synthetic aperture radar (SAR),
with Band-L (ALOS PALSAR data) and Band-C (ENVISAT ASAR data).
5. Research Contents
- Research methodologies and methods for identification and classification
oil spill at sea by SAR image.
- Propose the method for identification and classification oil spill at sea by
SAR image in accordance with characteristics of SAR images observed the
sea and in the wide mode.
- Develop a program which can identify and classify oil spill and look-alike
by SAR image.
6. The methodology
- Analysis, synthesis of materials including scientific articles published in
over the world and Vietnam, results of experiments for early detection and

monitoring of oil pollution at sea and the software for detecting oil spill in
SAR image. Hence, the authors proposed appropriate methodology, feasible
with Vietnam conditions.
- Study image processing algorithms, identifying and classifying oil spills at
sea algorithm, compare with the other algorithms and choose an appropriate
3

algorithm for the purpose of thesis.
7. The meaning and practicing of science thesis
7.1. Scientific significance of the thesis
- A complete scientific basis for identification and classification of marine
oil stains from materials ultrasonic sensing.
- Develop a method for identification and classification of oil traces from the
literature on marine SAR images.
- Thesis has contributed in implementing scientific research missions of
research on state-level "Oil pollution in the East Sea Vietnam" with code
KC09.22/06-10 by Assoc. Prof Nguyen Dinh Duong.
7.2. Practical significance of the subject
- Improved application of the material in the SAR image monitoring and
early detecting of oil pollution off the East Sea Vietnam
- Provided adequate assessment theory and the results of experimental
studies on Band-L material (ALOS PALSAR) and Band-C materials
(ENVISAT ASAR).
8. The main acquisitions of the thesis
8.1. The SAR image data which has been calibrated to Normalized Radar
Cross Section (NRCS) still exist effect of near - far range. Effect of near –
far range affects the ability to detect automatically dark spots on SAR image
by total threshold algorithm.
8.2. The method for detecting dark spots by region growing algorithm
performance applications in case of oil spills which has been for a while and

affects by weather. Oil slick in this case is not high contrast with the sea
surface in the SAR image. As a result, oil slick on SAR image has many
gray levels.
8.3. The method for identification and classification oil spill at sea by
microwave remote sensing data proposed in the thesis can be applied in the
condition of materials, infrastructure and information of Vietnam.
9. The new ideas of the thesis
9.1. Propose the method for automatically identifying and classifying oil
spill by SAR image data.
4

9.2. Propose the method for limiting the influence of near-far range effect on
SAR images data applied for identification and classification of oil spills at
sea. The near-far range effect exists on microwave remote sensing data,
especially for the wide mode.
9.3. Research the application of neural network MLP for identification and
classification of oil spills and look-alike on SAR image with the number of
various input parameters.
10. Volume and structure of thesis
The structure of the thesis is presented in 118 pages, 62 figures and
diagrams and 05 tables.

Chapter 1. OVERVIEW THE RESULTS OF RESEARCH
IN THE WORLD AND VIETNAM
1. Introduction
1.2. Overview of the research in the world
The research of using SAR image data to detect oil spill on marine
has studied since 1992 by Bern [11]. The author has used ERS-1 data (band-
C) to investigate the possibility of detecting oil spill on sea surface. The
research result includes:

- Image pre-processing: No mention to eliminate the affecting of near-far
range effect during image preprocessing for detecting on SAR images.
- Detecting and localizing dark spots: Using threshold method to detect and
localize dark spots on the image [5]. Beside the dark spots can be detected
by other methods such as LOG algorithms, DoG, HMC [27] to detect the
image, CFAR algorithm [9], and FCM algorithm [34].
- Slick feature extraction: The shape of discharge oil spill at sea is linear
shape. So the method to identify and classify oil spills on SAR images are
based on the geometric characteristics and shape of the detected region,
physical characteristics of the backscatter level of the
spot and its surroundings and spot contextual features.
- Identification and classification method: A number of studies classified oil
spill by experts through SAR image interpretation [7]. Besides oil spills are
5

identified and classified by semi-automatic method [7]. Other authors have
proposed fully automatic method for identification and classification of oil
spills through neural network [18], [23] or fuzzy logic [22].
Some organizations also have built research module to detect oil
spill by SAR image such as Oil spill detection module in NEST software
(appendix 12). NEST software uses semi-automated method.
1.3. Overview the results of research archivement in Vietnam
This research is a part of the project KC09.22/06-10 which of "Oil
pollution in the East Sea Vietnam" of Assor.Prof Nguyen Dinh Duong
Institute of Geography – Vietnam academy of Science and Technology.
Thesis author attended in this research to build observation systems for early
detecting and monitoring of oil spill at sea by microwave remote sensing
data.
1.4. Evaluate results of research achieved in the world and Vietnam
The data in scientific articles are mostly ERS - 1.2, Envisat ASAR

and Radarsat (Band - C). There has not been much research on material
Band-L. The results of identification and classification of oil spill on SAR
image primarily based on expert knowledge. The completely automated
classification methods are still researched and experienced by different
mode. Vietnam have not invested a research method for monitoring and
detecting oil spill at sea.
1.5. These issues are developed in the thesis
The content of the thesis inherits the research which the student
have been done in KC09.22/06-10. Based on the results of research
archivement and published scientific journals, the student will continue to
study the application of image processing algorithms to improve the ability
to identify and classify oil spill in SAR image data such as:
- Research on application of contrast limited adaptive histogram
equalization (CLAHE) to remove influence of near-far rang effect on SAR
images.
- Research on application of automatic threshold algorithm to detect dark
spots on SAR image which adjusted near-far range effect.
6

- Research on using region growing algorithm to detect dark spots in the
case the oil spill was weathered and had low contrast on SAR image.
- Research on ability to discriminate oil spill and look-alike based on neural
network models MLP with geometric characteristics index of each slick.
- Experiment with 2 type data content of Band-C and band-L ranges. There
are the main remote sensing data being used in Vietnam.

Chapter 2. THE METHODOLOGY OF IDENTIFICATION AND
CLASSIFICATION OIL SPILL AT SEA BY SAR IMAGE
2.1. Principles of Synthetic Aperture Radar (SAR)
2.1.1. RADAR image system

2.1.2. Synthetic Aperture Radar (SAR)
According to the principles of the system, the SAR antenna will
receive backscattering response from the object. Backscatter energy is
received by microwave sensor of satellite depend on the surface roughness
of the object.
2.2. SAR image of the sea surface
2.2.1. Sea surface description
On sea surface there has three main waveform is capillary waves,
gravitational waves and capillary-gravity waves. According to [25], the
capillary-gravity waves will impact on microwave which are used in
satellite observations of ocean.
2.2.2. Reflection of electromagnetic waves from the sea surface
2.2.2.1. Effect of dielectric constant
Dielectric constant of the marine environment will affect the
permeability of high-frequency waves.
2.2.2.2. Ocean surface roughness
The impact between the microwave and capillary-gravity waves on
sea surface is primarily due to Bragg scattering law.
2.2.2.3. Interaction of short and long wave
As long as waves grow steeper, the radial velocity components
increase, creating more smearing azimuth on SAR image [20].
7

2.2.2.4. Interaction of short waves and currents
The interaction of surface waves and currents will significantly
change the wavelength of the waves on sea surface increase or decrease the
response microwave scattering from the sea surface and the redistribution of
Bragg scattering waves on SAR images.
2.3. Methodology of identification and classification oil spill at sea by
SAR image

2.3.1. Oil spill on SAR imagery
The viscosity of oil slick will reduce the short-wave oscillations,
increase surface tension and reduce wind pressure at oil spill location. So,
energy backscattering at that position will be reduced and as a result oil spill
on SAR image is dark spot, contrast to sea surface (Figure 2.10). The
contrast between oil spill and sea surface on SAR image data is the
important characteristic for identification and classification oil spill and it is
the advantages of SAR image to others remote sensing data. However, due
to fluctuations of the sea surface are complex with the natural conditions at
sea, the accuracy of the identification and classification results depends on
the objective conditions.
Figure 2.10. Oil spill on
SAR image
(a) Backscattering at oil
spill position and region
surrounding;
(b) Oil spill on SAR
image

2.3.2. Identification and classification of oil spill at sea by SAR images
According to research agency Aerospace Europe (ESA) [16], 45%
of the oil pollution comes from operative discharges from ships. The ships
often discharge waste oil on the road and oil slick has linear shape. Scientists
base on this shape to identify and classify oil spill on SAR image.
2.4. The affection of identify and classify oil spill on SAR image


Bề mặt biển
Vết dầu
Vết dầu

(b)

Vết dầu trên biển
Sóng phản xạ
Sóng tán xạ

8

2.4.1. Wind speed on sea surface

Figure 2.12.
Wind speed
effect the
ability of
detection oil
spill on SAR
image [37]

2.4.2. Effect of speckle noise on SAR images
Noise filtering method need to maintain the original boundaries of
an oil spill in the process.
2.4.3. Satellite configurations for oil spill detection
In fact that the incidence angle effect the satellite signal in the SAR
image although the image has been calibrated on NRCS and converted to
sigma naught, especially in wide mode. It is called the far-near range effect
on SAR images.
2.4.4. The impact of look-alike at sea
On sea surface there is also exists the natural phenomenon which
decreases fluctuations waves and create dark spots on the SAR image. The
dark spot on SAR image which is not oil spill is called look alike.

2.4.5. The SAR image data on the experiment
According to the results published in the document [35], the value
of signal attenuation when sattelite observes an oil spill at sea by band- C
and band-L data are different.
2.4.6. Effected by meteorological conditions on sea surface
Under the impact of the environment at sea and by the physical and
chemical characteristics, the new oil spill is extracted easlier than the old one
on SAR image [35].
2.5. Conclusion Chapter 2
Methodology of the identification and classification oil spill at sea
9

by microwave remote sensing data based on the interaction of
electromagnetic waves and oscillations of the waves on sea surface. Oil
spills are dark spots on SAR images due to the decline Bragg scattering at
the oil slick position compare with region surrounding. Identified and
classified an oil spill on SAR image result is major influenced by wind
speed above the sea surface, look alike, characteristics of microwave data,
meteorological conditions of sea surface, chemistry and physical properties
of oil spill.
Chapter 3. PROPOSED METHOD FOR IDENTIFICATION AND
CLASSIFICATION OIL SPILL AT SEA BY SAR IMAGE
3.1. Data preprocessing SAR image
3.1.1. Converting the origin format to GeoTIFF
3.1.1.1. The format GeoTIFF data
3.1.1.2. Conversion ALOS PALSAR format data
The flow chart of converting from origin format of ALOS
PALSAR data to GeoTIFF is described in Figure 3.1.

Figure 3.1. The
flow chart
algorithm of
converting ALOS
PALSAR format
to GeoTIFF






10

3.1.1.3. Conversion Envisat ASAR format
In Figure 3.6 shows the flow chart of conversion Envisat ASAR to
GeoTIFF.




Figure 3.6.
Flow chart
algorithm of
conversion
and
geometric
correction

ASAR
image data








3.1.2. Masking land and islands
The land and island are masked automatically base on the Coast East
Sea Vietnam data (reference Appendix 3).
3.1.3. Adjusting near-far range effection on SAR images
In the thesis, the author uses contrast-limited adaptive histogram
equalization (CLAHE) to adjust near-far range effection [30] (Figure 3.9).
11

(a) (b)
Figure 3.9. ALOS PALSAR image adjusted to normal of azimuth
(a) Before adjustment; (b) After adjustment



(a) (b)
Figure 3.10. Graph profile of backscatter by normal of azimuth
(a) Before adjustment; (b) After adjustment
Equalization process is done on each of the image window. In the
thesis used to adapt the window size 8x8 and contrast limit coeffection is
0.03. After adjusting near-far range effect by CLAHE algorithm, the

intensity of pixels at near range and far range approximately has been
balanced (Figure 3.10). At the same time, the dark spot on the adjusted
image can be detected by total threshold algorithm (Figure 3.13).




12


Figure 3.13. The results of detection dark spots on the before and after
image adjusted near-far range effect
a. Image before adjustment; b. Image after adjustment
3.1.4. Speckle noise filtering in SAR images
In this thesis, the author proposes to use median filter to
decrease the noise on SAR image.
3.2. Detect dark spots on SAR images
3.2.1. Automatic threshold algorithm
3.2.1.1. The concept of threshold image
3.2.1.2. Automatic threshold algorithm by Huang
Based on the concept of fuzzy set, an effective threshold
method is proposed. Given a certain threshold value, the membership
function of a pixel is defined by the absolute difference between the
gray level and the average gray level of its belonging region (i.e. The
object or the background). The optimal threshold can then be
effectively determined
By minimizing the measure of fuzziness of an image [21].
Entropy value of X is described by the following formula:

S

(3.17)
(a)
(b)
13

Shannon function in Equation (3.17) is a linear increase in the range
of [0, 0.5] and decreases linear from [0.5, 0]. The process of fuzzy
measuring using the formula (3.17) was calculated with a loop until
max
1tg
in which
1tt
. Optimal threshold value will be
determined by the smallest fuzzy value (refer to Appendix 4).
3.2.2. The region growing algorithm
The region growing algorithm is computed by a number of
seed points and grows the search area depending on the proximity of
threshold of these points. Formula (3.18) describes the growing
algorithm by gray-scale value of seed points and the pixel under
consideration.
 
:
i seed
P R True if z z T  
(3.18)
To compare the results of Huang method and region growing
method in Figure 3.17 and Figure 3.20, the region growing method have
been appropriated to detect dark spots which have low contrast with
surrounding sea surface on SAR image.

Figure 3.17d Figure 3.20a Figure 3.20b
Where Figure 3.17d - Oil spill detected by threshold Huang algorithm;
Figure 3.20a - Oil spill in the origin SAR image; Figure 3.20b- Oil spill
detected by region growing algorithm
3.3. Identification and classification of oil spill and look-alike
3.3.1. The geometric shape of oil spill and look-alike
- The perimeter index (P):
- The area index (A):
14

- The shape index (Sf):
- The complexity of the (PT):
- The standard deviation of gray values belong oil spill (OSD):
- The average number of gray levels belong oil spill (Osm)
- The largest value within the gray oil spill (Max)
- The smallest gray level values belong oil spill (Min)
3.3.2. Automatic extract boundary and compute feature indexs of oil spill
Figure 3.22. Flow chart of automatic extract boundary of oil spill
3.3.3. Identification and classification of oil spill on SAR image
3.3.3.1. Discriminate between oil spill and look-alike by the geometric
shape index
Table 3.2 shows the difference shape index of oil spill and look-
alike such as P, A, Sf and index C. The look-alikes are created by the calm
sea areas which have heterogeneous of gray values higher than the oil spill.
3.3.3.2. Discriminate between oil spill and look-alike by Neural network
(MLP)
Classification by Neural network is supervised classification
method. The analysis and classification of oil spill and look-alike bases on a
set of templates content of a collection of specific oil spill and look-alike.
Extract boundary of dark spot

Set label for each region
Coordinate of points on boundary
Computer the index of region
Converted to geographic coordinate
Save data to Shapefile format
BEGIN
Origin image data
Detect dark spots in SAR image

END
15

Data input of neural network include geometric shape index of oil spill and
look-alike on SAR image. The output is the reliability of the classification
oil spill and look-alike. The number of experience test in this thesis is 100
samples including 67 oil spill and 33 look-alikes. The program choose 70
samples to train the network, 15 samples to validation and use 15
independence samples to test. The neural network structure are 8:8:2 which
input data consist of 8 shape indexs of dark spot including area, perimeter,
shapes (Sf), the complexity (PT), the standard deviation of gray values
(OSD), the average gray values (Osm), the largest value of gray, smallest
gray level values. Classification results are presented in Table 3.3 to achieve
93% accuracy. To confirm the role of the shape index affects the
classification result by neural networks, the author experiences other
structure model 4:4:2 which input data have 4 indexs including only area,
perimeter, and shape complexity; 4 hidden layer and output layer is 2 oil
spill and look-alike. The analytical results are presented in Table 3.4 to
achieve 96% accuracy.
Comparison of classification results with oil spill and look-alike by
neural network (MLP) with the structure 8:8:2 and 4:4:2, we have some

conclusions:
- According to the results, oil spill with ID 95, 96 on both models
have higher accuracy by 4:4:2 model than 8:8:2 model such as reliability oil
spill is 0.94 and look alike is 0.04. The oil spill and look-alike is unclearly
classified in 8:8:2 model.
- Neural network can identify and classify better than which oil
spill have characteristic shape that linear form and the reliability is 0.9.
- Some oil spills appear on the image have unspecified shape index,
for example the large complex index with ID 74, hence the accuracy of
classification is very low. The oil spill with ID 74 has reliability 0.4 for oil
spill, 0.2 for look-alike in 4:4:2 model. In which the reliability of 8:8:2
model is approximately 0.8 for oil spill and look-alike without distinct with
output results.
The difference between oil spill and look-alike by the shape index
16

are not quite high as the result of the near-far range effect and speckle noise
in SAR image. Therefore, it sometimes makes to reduce accuracy of the
analysis.
3.4. Proposed method
Based on the results of research archivement, the author proposes a
method for identification and classification of oil spill at sea by SAR images
with two difference processing divided by the characteristics of oil slick on
sea surface. The process is shown in Figure 3.27 which applies to the new
oil slick. The oil slick on SAR image is contrast with the surrounding
surface.

Figure 3.27. The method
automatic identification and
classification oil spill at sea by
SAR image











Detect dark
spots
Conversion data to GeoTIFF format
Removing mainland and island
Adjusting near-far range effect
Filtering speckle noise in SAR image
Automatic threshold by Huang
Dark spots detected image
(Binary format)
Extracting boundary of dark spot
Computer shape index of dark spots
Input data to

ArcGIS or Neural Network (MLP)
Identify and classify
Oil spill and look-alike
BEGIN
Preprocessing SAR image
Identification and classification
Oil spill and look-alike
END
Input SAR image data
Analysis and control the oil spill position
17

The process is shown in Figure 3.28 which applies for oil spill exits
a long time at sea. In fact, the oil spill exits a long time will be affected by
many factors such as the marine meteorological conditions, hydrological
sea, wave oscillations of the sea, the wind speed (lower than 2.5m/s or
higher than 12.5m/s), and physical and chemical properties of crude oil. In
this case oil spill have been decayed and not clear on SAR images, the
contrast of oil spill is not high with sea surface and have many gray levels in
the same spot so that the automatic extraction dark spot is very difficult.






Figure 3.28. The method
semi-automatic
identification and
classification oil spill at sea

by SAR image














Detect dark spots

Conversion data to GeoTIFF format

Removing mainland and island

Adjusting near-far range effect

Filtering speckle noise in SAR image

Choose seed points in oil spill
Dark spots detected image
(Binary format)

Extracting boundary and computer shape index of dark spot

Analysis and control the oil spill position

Identify and classify oil spill
and look-alike by manual

BEGIN

Preprocessing SAR image

Identification and
classification
END
Input SAR image data
Region growing algorithm
18


3.5. Conclusion Chapter 3
In summary, method identification and classification of oil spill at
sea by SAR image is a collection of essential steps processing include: 1)
Preprocessing image; 2) Detecting dark spots; 3) Identification and
classification of oil spill and look-alike in which the detection dark spots on
SAR images plays an important role. The detection dark spots on SAR
image are carried out automatic threshold algorithm or region growing
algorithm which improve the automated identification and classification of
oil spill at sea by SAR images.
However, almost dark spots on the image are detected by
automatic threshold algorithm by Huang so the image is need to treat by
pre-processing steps, especially adjust near-far range effect. The near-far

range effect creates the difference gray values of oil spill near range and far
range at the same image. It makes difficult to use automatic threshold
algorithm to detect dark spot on SAR image. We need to use region
growing algorithm to detect dark spots on SAR image in the case of oil spill
weathered by time and have many gray levels in oil spill.
According to the test results of identification and classification of
oil spill and look alike in Chapter 3 has confirmed the possibility of using
the shape index to discriminate between oil spill and look alike at sea by
SAR image. The shape index which is characteristic illegal discharges oil
spill are higher shape index (Sf), lower complexity index (C), lower area
and perimeter index compared with look-alike at the same time observation.
Besides, the experimental results confirm the ability application of multi-
layer neural network (MLP) to identify and classify oil spill and look alike,
improve the capability of the fully automated process identify and classify
oil spill and look alike at sea by SAR images.

Chapter 4. EXPERIMENT IDENTIFICATION AND CLASSIFICATION
OIL SPILL AT SEA BY SAR IMAGE
4.1. Analysis and system design detection of oil spill by SAR image
19

4.1.1. Design the functional component modules
4.1.2. Diagram of experimental program

Figure 4.1. Flow chart of the experimental program
4.1.3. Integrated modules and program design
4.1.4. Analysis the main modules of the program
4.1.4.1. Module analysis oil spill at sea by SAR image
4.1.4.2. Module display analysis results
4.1.4.3. Exit program

BEGIN
Input image data

Input CSDL.dat
file

Conversion data to GeoTIFF format

Removing mainland and islands

Adjusting near-far range effect

Filtering speckle noise in SAR image

Window size
Filter

Input detection dark
spot method

Check
Huang=1
Choose seed points
Region growing algorithm
Dark spots detected image
(Binary format)

Extracting boundary and computer
shape index of dark spot

Saving data to Shapefile format

END
F
T
Analysis by ArcGIS or Neural Network (MLP)

20

4.1.5. Practical solutions in the experimental program
4.1.5.1. Image processing solution for larger image
The adjustment algorithm near-far range effection, filtering speckle
noise on SAR images are computed on each block and adjusts the gray level
which is difference between the block borders.
4.1.5.2. Limited the region to extract boundaries
The solution of limited the region in extracting boundaries include:
finding and detecting edges on the border of the image (reference Appendix
6) finding and cropping the smallest rectangle surround the entire oil spill
(reference Appendix 7) automatically. The process extracting boundary of
an oil spill would be carried out on limited image.
4.2. Experience results identification and classification oil spill at sea by
SAR image
4.2.1. Database of experience image
4.2.2. Experience results
Experience results by ALOS PALSAR image for example
PASL4200706130316260911040000 image which is supported by
ERSDAC, level SCG 4.2, collected on 13/06/2007 is shown Figure 4.6 and
Figure 4.7.

Figure 4.6. Detect dark spots Figure 4.7. Vector boundary of oil spill
21

Testing by Envisat ASAR image, for example
ASA_WSM_1PNxxx20080614_024255_00000057V035_00031_32880_0
064.N1 image, WSM mode, level 1B is shown in Figure 4.11 and Figure
4.12.

Figure 4.11.Detect dark spots Figure 4.12.Vector boundary of oil spill
4.3. Conclusion Chapter 4
The image processing algorithms have been proposed to improve
the ability to automatically identify and classify an oil spill at sea by SAR
images. Processing time is approximately 03 minutes per picture. The
experimental program has examined two main SAR image data in Vietnam
which is used in monitoring and early detecting oil spill at sea such as
ALOS PALSAR data (Band L) and ENVISAT ASAR (Band C). Position
and time of the experimental area is Vietnam East Sea. The meteorological
conditions in the experience time has wind speed from 2.5m/s to 7.5m/s, no
extreme weather events such as rain, thunderstorm at sea.
The method for detectionation dark spots on SAR images is used
Huang threshold algorithm to give good results for both types of SAR
images. The application of threshold algorithm of Huang improves to
automatic the method for identification and classification oil spill at sea by
SAR images proposed in the thesis.

22

CONCLUSIONS AND RECOMMENDATONS
A. CONCLUSIONS
1. Methodology of identification and classification oil spill at sea by SAR

images is based on the difference in backscattering energy at the oil spill
position and the surrounding sea surface on SAR image. Energy
backscattering response obtained at microwave sensor of satellite when
observed at sea mainly Bragg scattering. Bragg scattering is created by the
interaction of microwave signals and oscillations of the waves. However,
the reliability of the identification and classification of an oil spill at sea by
SAR images depend on wind speed on sea surface, incident angle and
physico-chemical properties oil.
2. In general, there are three methods for identification and classification of
oil spill at sea by SAR images such as manual method, semi-automatic
method and fully automatic method. The manual method have been
identified and classified by the knowledge of experts. The semi-automatic
method is used widely because this method can be automatically detected
dark spots and calculated the geometric shape indexs of oil spill and look
alike. The fully automatic method is studying to discriminate between oil
spill and look alike by MLP neural networks.
3. The proposed methods in the thesis include in multi-step process image
with 3 main parts: 1) Image pre-processing; 2) Detecting dark spots on the
SAR image; 3) Identification and classification of oil spill and look alike.
4. The experience results prove of the proposed method well on band - L
data (ALOS PALSAR) and band C data (ENVISAT ASAR). There are two
main data which is being used in Vietnam. The proposed results are
experienced in normal meteorological conditions on the Vietnam East Sea
and without extreme weather such as hurricanes, thunderstorms …
5. It is reduce much processing time to analysis context by detecting dark
spots by automated threshold Huang algorithm, extracting the boundaries of