روشی نوین در بهبود نتایج آشکارسازی تغییرات با تلفیق تصاویر اپتیک و رادار و بکارگیری روشی بدون نظارت و مبتنی بر الگوریتم PSO

نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناس ارشد مهندسی سنجش از دور، دانشگاه تحصیلات تکمیلی صنعتی و فناوری پیشرفته، کرمان

2 استادیار، گروه مهندسی نقشه برداری، دانشگاه تحصیلات تکمیلی صنعتی و فناوری پیشرفته،کرمان

10.22131/sepehr.2021.242857

چکیده

اطلاعات حاصل از آشکارسازی تغییرات در مناطق شهری تأثیر بسزایی در برنامهریزی و مدیریت شهری خواهد داشت.مناطق شهری به دلیل تنوع پدیدهها، انواع پوشش سطح به عنوان یک منطقه پیچیده در نظر گرفته میشوند که کسب اطلاعات از این مناطق همواره با چالشهایی روبه رو میباشد. از این رو این احتمال وجود داد که در صورت استفاده مستقل از دادههای اپتیک و رادار در بحث آشکارسازی تغییرات، بعضی از مناطق تغییر یافته تشخیص داده نشوند یا نتایج کاذب از خود ارائه دهند.با توجه به مزیت تلفیق دادههای اپتیک و رادار و همچنین بکارگیری روشهای بدون نظارت در بحث آشکارسازی تغییرات، در پژوهش حاضر به توسعه روشی بدون نظارت جهت تلفیق دادههای اپتیک و رادار با هدف تشخیص تغییرات پرداخته شد.به این منظور ویژگیهایی از تصاویر اپتیک و رادار استخراج و وارد الگوریتم C2VA شد. در ادامه برای هر یک از ویژگیهای ورودی به بخش C2VA یک وزن با استفاده از الگوریتم PSO برآورد گردید.خروجی روش پیشنهادی تصویر تک باندی با محتوای اطلاعاتی بالاتر خواهد بود که بعد از اعمال حد آستانه OTSUبه دو کلاس تغییر یافته و بدون تغییر تفکیک میشود. روش پیشنهادی با دیگر روشهای آشکارسازی تغییرات، مقایسه و مورد ارزیابی قرار گرفت. یافتههای این پژوهش نشان دهنده کارایی و صحت بالای روش توسعه داده شده جهت تشخیص تغییرات میباشد به گونهای که نسبت پیکسلهای اشتباه شناسایی شده به کل پیکسلها دادهی ارزیابی9.21 درصد بوده که دارای پایینترین مقدار است و صحت کلی طبقهبندی و ضریب کاپا بهترتیب با 90.79 ،0.819 به عنوان بالاترین مقادیر، نسبت به دیگر روشهای مورد استفاده در پژوهش حاضر میباشند.

کلیدواژه‌ها


عنوان مقاله [English]

Developing a new method for improving change detection results using optical and radar image fusion based on an unsupervised method and PSO-based algorithm

نویسندگان [English]

  • Saeid Mahmoodizadeh 1
  • Ali Esmaeily 2
1 M.Sc. in Remote sensing engineering, Graduate University of Advanced Technology, Kerman
2 Assistant professor, Dept. of Surveying engineering, Graduate University of Advanced Technology, Kerman
چکیده [English]

Extended Abstract
Introduction
Information obtained from change detection processes in urban regions has a remarkable effect on urban planning and management. Due to the variety of land coversin urban regions, they are considered as a complex region extracting information from which is quite challengeable. Hence, independent application ofoptical and radar data in changedetection may result in improper recognition of some altered regions and falsification ofobtained results. These two sensors record different kinds of information from different phenomenonat the earth’s surface, and thus can be considered as complementing each other. So, the fusion of these two data sources (radar and optical) can improve the detection of altered area. Radar data do not depend on the sun and atmospheric conditions and has thus gained much attention. In fact, radar data provide information on the spatial and geometrical characteristics of the geographical features, while optical sensors are sensitive to the reflectance of different surfaces at visible and infrared wavelengths.Therefore, the surface reaction is different in optical and radar data. Application of radar data in urban regions is limited merely due to the dependence of the intensity data (i) on the incidence angle and the speckle noise.On the other hand, independent application of optical data cannot produce accurate results in urban regions due to the spectral similarity of materials. And since the nature of these two types of images is different, it seems that their fusion improves and increases the accuracy of the information collectedfrom urban areas.
 Materials and Methodology
Considering thebenefits of optical and radar data integrationas well as the application of unsupervised techniques in change detection studies, the present research has developed an unsupervised method for the integration of optical and radar data in order to detect changes. The area under study is a region located in the northwestof Mashhad city in northeastern Iran which has experienced considerable changes in its land cover from 2016 to 2018. Optical and radar dataare used toevaluate the proposed method. Optical data consists of a pair of multispectral imagesacquired from Sentinel-2 in 9/2016 and 9/2018. Radar data consists of a pair of SAR imagesacquired from Sentinel-1 in 9/2016 and 9/2018. The proposed method was used to integrate radar and optical data with the aim of obtaining a single band image with a higher information content. This method is an effective solution used to integrate data and reduce data dimensions from n to one dimension. In this method, necessary preprocessing was first performed on the radar and optical data, and then the characteristics extracted from optical and radar images were integratedpixel-to-pixel.
technique was used to integrate these characteristics and detect changes. Generally in this method, input is divided into two categories of radar and optical data. The optical characteristics include spectral indices calculated from different bands at t1 and t2. These indices include NDVI, ARVI, SAVI, NDWI, NDBI, which are efficient for studying and identifying three types of land cover: vegetation, water and residential areas. In fact, to reduce the effects of topography and image brightness and to increase the possibility of detecting and segregating geographical features, the spectral indices were used as the input of optical part. Normalized ratio images obtained from the VV and VH polarizations of the radar images at t1 and t2 were considered as the input of radar data part. Then, a weight was estimated for each feature entering the segment using the PSO algorithm. Since the present study seeks to estimate the optimal weight of characteristics extracted from optical and radar images and ultimately to combine these features and obtain a single-band image, each particle in this algorithm contains the n weight of the extracted features from the images. OTSU thresholding techniquewhich is the relation used for inter-class variance maximization is also used as thecost function to assess the particles. In this function, the weight of each characteristic should be selected in a way that the inter-class (two classes of altered and unaltered regions)variancereaches its maximum value and the most optimal threshold limit can be estimated. The output of the proposed method will be a single-band image with higher information content. After applying the OTSU threshold limit, two classesof altered and unaltered regions are formed. The proposed method was also compared with other unsupervised change detection methods.
 Results
Findings of the present study indicate high efficiency and accuracy of the method developed for changedetection. In this method, the ratio of pixels wronglydetected to the total number of evaluated pixels was 9.21% which is the lowest value. The overall accuracy and Kappa coefficients of the classification were respectively 90.79 and 0.819, which were the highest values compared to the other methods used in the present study.
 Conclusion
Considering the benefits of optical and radar data integration, as well as unsupervised techniques application in change detection study, the present research has developed an unsupervised method for integration of optical and radar data andchangedetection. This unsupervised method for data integration is usedto achieve a single band image with higher information content. The technique makes it possible to integrate the optical and radar data and reduce data dimensions from n to one. For all input characteristics entering section, a weight was estimated using PSO algorithm. Since the proposed method is unsupervised, OTSU thresholding technique which is the relation used for inter-class variance maximization, is also used to assess the particles. The results have revealed high capability of the proposed method todetectchanges witha higher accuracy.

کلیدواژه‌ها [English]

  • Change detection
  • Data Integration
  • Unsupervised
  • C2VA
  • OTSU
1- اسدی، بنایان اول، جهان، فرید حسینی؛ سارا، محمد، محسن؛ علیرضا،1397، مقایسه شاخص‎های مختلف طیفی پوشش گیاهی برای ارزیابی از دور شاخص سطح برگ گندم زمستانه در مشهد.  بوم‌شناسی کشاورزی، 10 (3)،913-934.
2- اصغری سراسکانرود، جلیلیان، پیروزی نژاد، مددی، یادگاری؛ صیاد، روح اله، نوشین، عقیل؛ میلاد. 1399، ارزیابی شاخص‌های استخراج آب با استفاده از تصاویر ماهواره‌ای لندست (مطالعه موردی: رودخانه گاماسیاب کرمانشاه). نشریه تحقیقات کاربردی علوم جغرافیایی،20 (58) ، 53-70.
3- ایمانی، ابراهیمی، قلی نژاد، طهماسبی؛ جمال، عطاءالله، بهرام؛ پژمان، 1397، مقایسه دو شاخص NDVI و SAVI در سه جامعه گیاهی مختلف با شدت نمونه‌برداری متفاوت (مطالعه موردی: مراتع اطراف تالاب چغاخور چهارمحال و بختیاری). تحقیقات مرتع و بیابان ایران، 25(1)، 152-169.
4- شکرالهی، صاحبی، عبادی؛ مهین، محمودرضا، حمید؛ 1393، تلفیق داده‌های پلاریمتری SAR و ابرطیفی به منظور طبقه‌بندی پوشش زمین. پایان نامه کارشناسی ارشد، دانشگاه صنعتی خواجه نصیرالدین طوسی، دانشکده مهندسی نقشه برداری.
5- کریمی، رنگزن، اکبری‌زاده، کابلی‌زاده؛ دانیا، کاظم، غلامرضا، مصطفی؛ 1395، طبقه‌بندی تجمعی اهداف با استفاده از تلفیق تصاویر SAR و اپتیک. پایان‌نامه کارشناسی ارشد، دانشگاه شهید چمران اهواز، دانشکده علوم زمین.
6- مناطقی، ط.ولدان زوج، م. مقصودی مهرانی،ی. شناسایی تغییرات ساختمان‌ها پس از زلزله با استفاده از تلفیق تصاویر نوری و راداری. پایان نامه کارشناسی ارشد، دانشگاه صنعتی خواجه نصیرالدین طوسی، دانشکده مهندسی نقشه برداری.  
7- نجفی، حسنلو؛ امیر، مهدی، 1397، آشکارسازی تغییرات کاربری اراضی با استفاده از تصاویر تمام قطبیده راداری و روش‌های جبری، فاصله و شباهت ‌مبنا. مهندسی فناوری اطلاعات مکانی ،143-163.
8- نیمروزی، نوروز.1389، بررسی پیامد‌های حاشیه نشینی بر نظام فرهنگی مشهد. کنفرانس برنامه ریزی و مدیریت شهری مشهد، دانشگاه فردوسی،73-88.
9-Abdelaziz-Azzouzi, S., Pantaleoni, V, Adda-Bentounes, H., 2018, Monitoring desertification inBiskra, Algeria using Landsat 8 and Sentinel-1A images, IEEE Access,1-12.
10-Bovolo,F. Marchesi, S. Bruzzone,L.2012, A framework for automatic and unsupervised detection of multiple changes in multitemporal images. IEEE Trans. Geosci. Remote Sens, vol. 50, no. 6, pp. 2196–2212.
11-Chen, X., Chen, J., Shi, Y.,& Yamaguchi, Y.2012, An automated approach for updating land cover maps based on integrated change detection and classification methods. ISPRS Journal of Photogrammetry and Remote Sensing, 71, 86-95.
12-Engelbrecht, P,2007, Computational intelligence: an introduction. Wiley online library.
13-İlsever, M., & Ünsalan, C.2012, Two-Dimensional Change Detection Methods, (No. Ed. 1), Springer, London.
14-Jantz,C.J.,S.J.Goetz,A.J.Smith, and M. Shelly .2003, Using the SLEUTH Urban growth model to simulate the impacts of future policy scenarios on land us e in the Baltimore - Washingt on metropolit an area, Environm ent and Planning.
15-Jat, M. K., Garg, P. K., Khare, D.2008, Monitoring and modelling of urban sprawl using remote sensing and GIS techniques. International journal of Applied Earth Observation and Geoinformation,10(1), 26-43.
16-Karnieli, A.; Qin, Z.; Wu, B.; Panov, N.; Yan, F.2004, Spatio-Temporal Dynamics of Land-Use and LandCover in the Mu Us Sandy Land, China, Using the Change Vector Analysis Technique. Remote Sens, 9316-9339.
17-Kuncheva, Ll., Whitaker, C. J. 2003, Measures of diversity in classifier ensemble and their relationship with the ensemble accuracy, Machine Learning, 51(2), pp. 181-207.
18-Kuncheva, L.2004,Combining Pattem Classifiers methods and algorithms, A john Wiley&sons, INC. publication, Hoboken, New jersey. Canada.
19-Luo, H.; Liu, C.; Wu, C.; Guo, X. 2018, Urban Change Detection Based on Dempster–Shafer Theory forMultitemporal Very High-Resolution Imagery. Remote Sens, 10, 980.
20-Malila, W. A. ,1980, Change Vector Analysis:An Approach for Detecting Forest Changeswith Landsa, Proceedings, 6th AnnualSymposium on Machine Processing ofRemotely Sensed Data, Purdue University, 326-335.
21-Mhangara, P.,& Odindi, J. 2013, Potential of texture-based classification in urban landscapes using multispectral aerial photos. South African Journal of Science, 109, 1-8.
22-Mishra B,Susaki J , 2014, OPTICAL AND SAR DATA INTEGRATION FOR AUTOMATIC CHANGEPATTERN DETECTION, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial InformationSciences,39-46.
23.-Otsu, N,1979, A threshold selection method from gray-level histogram”, IEEE Trans. Systems Man Cybernet, vol. 9, pp. 62-66.
24-Poli, Kennedy,j, and Blackwell, T,2007, Particle swarm optimization”, Swarm intelligence, vol. 1, No. 1, pp. 33–57.
25-Radke, R. J., Andra, S., Al-Kofahi, O.,& Roysam, B.2005, Image change detection algorithms: a systematic survey. Image Processing, IEEE Transactions on, 14(3), 294-307.
26-Sallaba, F. 2009, Potential of a Post-Classification Change Detection Analysis to Identify Land Use and Land Cover Changes. A Case Study in Northern Greece.
27-Xie, M.,& Fu, M.2011, The temporal dynamics of urban heat islands derived from thermal remote sensing data by local indicator of spatial association in Shenzhen, China. Paper presented at the International Conference on Photonics and Image in Agricultural Engineering.
28-Xu, H., Wang, X., Xiao, G.2000, A remote sensing and GIS integrated study on urbanization with its impact on arable lands: Fuqing City, Fujian Province, China. Land Degradation & Development, 11(4), 301-314.
29-Xue, J. Su, B. 2017, Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications, Journal of Sensors,  2017(1), 1-17.
30-Yousif O, Ban Y, 2017, Fusion of SAR and Optical Data for Unsupervised Change Detection: A Case Study inBeijing,Joint Urban Remote Sensing Event (JURSE).
31-Zha, y. Gao, j. ni, s. 2003, Use of normalized difference built-up index in automatically mapping urban areas from TM imagery, International Journal of Remote Sensing,24(3), 583-594.
32--Zhang, B.Chen,K. Zhou,Y. Xie,M. Zhang,H ,2010, Research on Change Detection in Remote Sensing Images by using 2D-Fisher Criterion Function Method”, ISPRS TC VII Symposium.