Marine target detection based on Marine-Faster R-CNN for navigation radar plane position indicator images

As a classic deep learning target detection algorithm,Faster R-CNN(region convolutional neural network)has been widely used in high-resolution synthetic aperture radar(SAR)and inverse SAR(ISAR)image detection.However,for most common low-resolution radar plane position indicator(PPI)images,it is difficult to achieve good performance.In this paper,taking navigation radar PPI images as an example,a marine target detection method based on the Marine-Faster R-CNN algorithm is proposed in the case of complex background(e.g.,sea clutter)and target characteristics.The method performs feature extraction and target recognition on PPI images generated by radar echoes with the convolutional neural network(CNN).First,to improve the accuracy of detecting marine targets and reduce the false alarm rate,Faster R-CNN was optimized as the Marine-Faster R-CNN in five respects:new backbone network,anchor size,dense target detection,data sample balance,and scale normalization.Then,JRC(Japan Radio Co.,Ltd.)navigation radar was used to collect echo data under different conditions to build a marine target dataset.Finally,comparisons with the classic Faster R-CNN method and the constant false alarm rate(CFAR)algorithm proved that the proposed method is more accurate and robust,has stronger generalization ability,and can be applied to the detection of marine targets for navigation radar.Its performance was tested with datasets from different observation conditions(sea states,radar parameters,and different targets).

Study on the Urban Heat Island Effects and Its Relationship with Surface Biophysical Characteristics Using MODIS Imageries

This study assesses surface urban heat island (UHI) and its associated surface physical characteristics using remote sensing approaches. TERRA/MODIS images acquired in 2005 in three different seasons were selected to generate land surface tem-perature and surface characteristics for the Changsha-Zhuzhou-Xiangtan metropolitan area in China. The intensity of urban heat is-land effects and its seasonal variations were examined. The result showed that UHI effects were significant both in the summer and the spring. Land surface temperatures in the city were 8 ℃ to 10℃ warmer than those in surrounding rural areas in the spring and the summer seasons. Although UHI effects exist in winter, they are not significant. Land surface temperature in the city was 4℃ warmer than that in surrounding rural areas in winter. This study uses normalized difference vegetation index (NDVI) and normal-ized difference built-up index (NDBI) as indicators of surface physical characteristics and investigates the relationship among land surface temperature (LST), NDVI and NDBI. The results from this study indicate that, while the relationship between LST and NDVI changes in different seasons, there is a strong positive linear relationship between NDBI and LST for all seasons. The amount of slope and intercept of the linear relationship between NDBI and LST can indicate the magnitude of UHI for different seasons. This finding suggests that NDBI provides an alternative physical indicator for analyzing LST quantitatively over different seasons, and therefore providing a useful way to study UHI effects using remote sensing.