Feature-aided pose estimation approach based on variational auto-encoder structure for spacecrafts

Real-time 6 Degree-of-Freedom(DoF)pose estimation is of paramount importance for various on-orbit tasks.Benefiting from the development of deep learning,Convolutional Neural Networks(CNNs)in feature extraction has yielded impressive achievements for spacecraft pose estimation.To improve the robustness and interpretability of CNNs,this paper proposes a Pose Estimation approach based on Variational Auto-Encoder structure(PE-VAE)and a Feature-Aided pose estimation approach based on Variational Auto-Encoder structure(FA-VAE),which aim to accurately estimate the 6 DoF pose of a target spacecraft.Both methods treat the pose vector as latent variables,employing an encoder-decoder network with a Variational Auto-Encoder(VAE)structure.To enhance the precision of pose estimation,PE-VAE uses the VAE structure to introduce reconstruction mechanism with the whole image.Furthermore,FA-VAE enforces feature shape constraints by exclusively reconstructing the segment of the target spacecraft with the desired shape.Comparative evaluation against leading methods on public datasets reveals similar accuracy with a threefold improvement in processing speed,showcasing the significant contribution of VAE structures to accuracy enhancement,and the additional benefit of incorporating global shape prior features.

A NEW APPROACH TO ESTIMATE KINETIC DECOMPOSITION FROM TG-DTG OR DSC CURVE

This paper reports a new approach to estimate kinetic parameters for the thermal decomposition of the solid state from TG-DTG or DSC curve.Reduced equations are derived for the first tlme.The validity of these equations was demonstrated employing data obtained from the dehydration process of calcium oxalate monohydrate.

Study on daily surface evapotranspiration with SEBS in Tibet Autonomous Region

The estimation of surface evapotranspiration （ET） with satellite dataset is one of the main subjects in the understanding of climate change, disaster monitoring and the circulation of water vapor and energy in Tibet Autonomous Region （TAR）. This research selects satellite images on January 11, April 6, July 31 and October 19 in 2010 as the representative of winter, spring, summer and autumn respectively, estimates the distribution of daily surface ET based on the surface energy balance system （SEBS） along with potential evapotranspiration （PET） and ET derived from Penman-Monteith （P-M） method. The results are obtained as follows. （1） The seasonal distribution of ET and PET basically decreases from the southeast part to the northwest part of TAR. Although ET and PET have similar spatial distributions, there are still some differences to estimate the extreme values especially the maximum value in the middle and southeastern parts of TAR. No matter what kind of methods we adopted, the maximum value of ET and PET always appears in summer, followed by autumn or spring while that in winter is the smallest. （2） In order to better understand the accuracy of SEBS model in the estimation of ET, we compared the ET from SEBS and the ET obtained from P-M method. Results show that the ET from SEBS could estimates the variation trend of actual ET, but it slightly underestimates or overestimates the value of ET as a whole, especially for those areas with thick forest. （3） The spatial distribution of Normalized Difference Vegetation Index （NDVI） exhibits a decreasing trend from the southeast part to the northwest part of TAR which displays remarkable consistency of distributions between ET and vegetation index. ET is well positively related to NDVI, minimum, mean, maximum air temperature and sunshine duration in different seasons while negatively related to precipitation, relative humidity and wind speed in summer.