Background Determining how an image is visually appealing is a complicated and subjective task. This motivates the use of a machine-learning model to evaluate image aesthetics automatically by matching the aesthetics ...Background Determining how an image is visually appealing is a complicated and subjective task. This motivates the use of a machine-learning model to evaluate image aesthetics automatically by matching the aesthetics of the general public. Although deep learning methods have successfully learned good visual features from images,correctly assessing the aesthetic quality of an image remains a challenge for deep learning. Methods To address this, we propose a novel multiview convolutional neural network to assess image aesthetics assessment through color composition and space formation(IAACS). Specifically, from different views of an image––including its key color components and their contributions, the image space formation, and the image itself––our network extracts the corresponding features through our proposed feature extraction module(FET) and the Image Net weight-based classification model. Result By fusing the extracted features, our network produces an accurate prediction score distribution for image aesthetics. The experimental results show that we have achieved superior performance.展开更多
To carry out the deep space exploration tasks near Sun-Earth Libration point L2, the CRTBP dynamic model was built up and the numerical conditional quasi-periodic orbit （Lissajons orbit） was computed near L2. Then, ...To carry out the deep space exploration tasks near Sun-Earth Libration point L2, the CRTBP dynamic model was built up and the numerical conditional quasi-periodic orbit （Lissajons orbit） was computed near L2. Then, a formation controller was designed with linear matrix inequality to overcome the difficuhy of parameter tuning. To meet the demands of formation accuracy and present thruster＇s capability, a threshold scheme was adopted for formation control. Finally, some numerical simulations and analysis were completed to demonstrate the feasibility of the proposed control strategy.展开更多
基金Supported by the National Key R&D Program of China (No:2018YFB1403202)the National Natural Science Foundation of China(62172366)。
文摘Background Determining how an image is visually appealing is a complicated and subjective task. This motivates the use of a machine-learning model to evaluate image aesthetics automatically by matching the aesthetics of the general public. Although deep learning methods have successfully learned good visual features from images,correctly assessing the aesthetic quality of an image remains a challenge for deep learning. Methods To address this, we propose a novel multiview convolutional neural network to assess image aesthetics assessment through color composition and space formation(IAACS). Specifically, from different views of an image––including its key color components and their contributions, the image space formation, and the image itself––our network extracts the corresponding features through our proposed feature extraction module(FET) and the Image Net weight-based classification model. Result By fusing the extracted features, our network produces an accurate prediction score distribution for image aesthetics. The experimental results show that we have achieved superior performance.
文摘To carry out the deep space exploration tasks near Sun-Earth Libration point L2, the CRTBP dynamic model was built up and the numerical conditional quasi-periodic orbit （Lissajons orbit） was computed near L2. Then, a formation controller was designed with linear matrix inequality to overcome the difficuhy of parameter tuning. To meet the demands of formation accuracy and present thruster＇s capability, a threshold scheme was adopted for formation control. Finally, some numerical simulations and analysis were completed to demonstrate the feasibility of the proposed control strategy.
