A Multi Moving Target Recognition Algorithm Based on Remote Sensing Video

The Earth observation remote sensing images can display ground activities and status intuitively,which plays an important role in civil and military fields.However,the information obtained from the research only from the perspective of images is limited,so in this paper we conduct research from the perspective of video.At present,the main problems faced when using a computer to identify remote sensing images are:They are difficult to build a fixed regular model of the target due to their weak moving regularity.Additionally,the number of pixels occupied by the target is not enough for accurate detection.However,the number of moving targets is large at the same time.In this case,the main targets cannot be recognized completely.This paper studies from the perspective of Gestalt vision,transforms the problem ofmoving target detection into the problem of salient region probability,and forms a Saliency map algorithm to extract moving targets.On this basis,a convolutional neural network with global information is constructed to identify and label the target.And the experimental results show that the algorithm can extract moving targets and realize moving target recognition under many complex conditions such as target’s long-term stay and small-amplitude movement.

The Relationship between Melt Season Sea Ice over the Bering Sea and Summer Precipitation over Mid-Latitude East Asia

Independent datasets consistently indicate a significant correlation between the sea ice variability in the Bering Sea during melt season and the summer rainfall variability in the Lake Baikal area and Northeastern China.In this study,four sea ice datasets(HadISST1,HadISST2.2,ERA-Interim and NOAA/NSIDC)and two global precipitation datasets(CRU V4.01 and GPCP V2.3)are used to investigate co-variations between melt season(March−April−May−June,MAMJ)Bering Sea ice cover(BSIC)and summer(June−July−August,JJA)East Asian precipitation.All datasets demonstrate a significant correlation between the MAMJ BSIC and the JJA rainfall in Lake Baikal−Northeastern China(Baikal−NEC).Based on the reanalysis datasets and the numerical sensitivity experiments performed in this study using Community Atmospheric Model version 5(CAM5),a mechanism to understand how the MAMJ BSIC influences the JJA Baikal−NEC rainfall is suggested.More MAMJ BSIC triggers a wave train and causes a positive sea level pressure(SLP)anomaly over the North Atlantic during MAMJ.The high SLP anomaly,associated with an anti-cyclonic wind stress circulation anomaly,favors the appearance of sea surface temperature(SST)anomalies in a zonal dipole-pattern in the North Atlantic during summer.The dipole SST anomaly drives a zonally orientated wave train,which causes a high anomaly geopotential height at 500 hPa over the Sea of Japan.As a result,the mean East Asian trough moves westward and a low geopotential height anomaly occurs over Baikal−NEC.This prevailing regional low pressure anomaly together with enhanced moisture transport from the western North Pacific and convergence over Baikal−NEC,positively influences the increased rainfall in summer.