طبقه‌بندی پوشش‌های جنگلی با استفاده از داده‌های پلاریمتری فشرده

اخیرا رشد قابل توجهی در سیستمهای dualpolarimetry (dp) بهوجود آمده است که compact polarimetry (cp) نامیده میشود. cp یک سیستم تصویربرداریdp است که چندین مزیت مهم را نسبت به دیگر سیستم های چندپلاریزاسیون sar دارد. از جمله آنها میتوان به قابلیت کاهش پیچیدگی سیستم، هزینه، وزن و نرخ داده های سیستم sar اشاره کرد. یکی از زمینه های تحقیقاتی مورد توجه سنجش از دور راداری مطالعه جنگلها است، چراکه نقش مهمی را در کنترل آب و هوا بازی میکنند. در این تحقیق پتانسیل داده های cp در طبقه بندی مناطق جنگلی با استفاده از طبقه بندی کننده ویشارت مختلط و به دو صورت بررسی و ارزیابی شده است. یکبار با استفاده از ماتریسهای کواریانس 2 *2 دو مد pi/4و circular transmitlinear receive(ctlr)، و بار دیگر با بهکارگیری ماتریسهای کواریانس 3*3 بازسازی شده از این دو مد cp. سپس نتایج حاصل با نتیجه به دست آمده از مد full polarimetry (fp) مقایسه و ارزیابی شدند. نتایج نشان دادند که در طبقه بندی پوشش های جنگلی، مد pi/4 دقت کلی طبقه بندی بهتری را نسبت به مد ctlr فراهم میکند.

Forest Cover Classification Using Compact Polarimetry Data

Indeed, Full Polarimetry (FP) imaging system has proven its increased potential in various applications, but suffer from an increase in the Pulse Repetition Frequency (PRF) and the data rate over single polarization. Recently, there has been growing interest in Dual Polarimetry (DP) imaging system that is called Compact Polarimetry (CP). The CP is a new mode proposed in DP system which has several important advantages in comparison with the FP mode such as reduction ability in complexity, cost, mass, and data rate of a Synthetic Aperture RADAR (SAR) system. Moreover, this new mode not only can achieve a greater amount of information than standard DP modes, but also can cover a much greater swath widths compared to FP mode. For this reason, the CP data can be critical for monitoring applications, such as forest controlling and monitoring. Forest studying is the one of research areas that is attractive for RADAR remote sensing researchers, because it has an effective role in climate controlling. Therefore, forest cover classification is essential to manage natural resources and environment, land use plans and land potential. Despite the significant number of works carried out for CP SAR applications, very few researches have been performed to investigate the capability of CP data for forest cover classification. In this paper, the potential of CP data in forest area is investigated using complex Wishart classifier in two ways. First, we use 2×2 covariance matrices of the pi/4 and Circular TransmitLinear Receive (CTLR) CP modes simulated by RADARSAT2 FP mode which acquired over Petawawa research forest and second, 3×3 covariance matrices reconstructed from these modes were exploited. Next, we compare the results with the FP mode. Results of this study show that the pi/4 mode provide better overall accuracy in forest cover classification than the CTLR mode, as well as extending the CTLR mode via Souyris’s iteration model to generate the PQ_CTLR mode overally does not significantly affect the Wishart classification. However, construction of the PQ mode permits a direct comparison of the average scattering mechanisms. Therefore, in the next step, the CloudePottier alpha angle is considered and calculated for PQ and FP modes. The PQ_pi/4 mode shows that it is a better mode to estimate the alpha angle parameter compared to the PQ_CTLR mode. This study shows that although CP modes do not produce as good classification accuracies as produced by FP mode, they are an effective strategy when the polarimetric system resources are limited or not available. Also, they are compatible as an optional mode for a FP SAR system. Moreover, circular polarizations e.g. CTLR modes, will be less sensitive to Faraday rotation effects attached to low frequency propagation in the ionosphere. At the present, at least two earth observation satellites which provide CP modes are already in orbit or to be launched in next few years. These are Indian RISAT1, Japanese Advanced Land Observing Satellite2 (ALOS2), Canadian RADARSAT Constellation Mission (RCM) and Argentina SAR Observation & Communications Satellite (SAOCOM) that will able to collect the CP data in and CTLR modes.