The traditional edge detection-based shoreline extraction method is severely disturbed by noise, and it is difficult to obtain a continuous coastline. In response to the above problems, we propose a coastline extraction method based on convolutional neural networks. Firstly, we replace the standard convolution with the Mini-Inception structure in the backbone network to extract multi-scale features of the object, and all the multi-scale features are concatenated. Then, we use the leaky-ReLU activation function instead of the ReLU activation function to avoid the problem that "dead" neurons cannot learn the effective features of remote sensing images. Finally, the network fully exploits multi-level information of objects to perform the image-to-image prediction. We carried out experiments on the remote sensing images of Jiaozhou Bay in Qingdao. The experimental results showed that our method could effectively extract the coastline automatically, and the producer’s accuracy and the user’s accuracy were higher than the comparison methods.
Aiming at the problems of the face image super-resolution reconstruction method based on convolutional neural network, such as single feature extraction scale, low utilization rate of features and blurred face images texture, a model combining convolutional neural network with self-attention mechanism is proposed. Firstly, the shallow features of the image are extracted by the cascaded 3 × 3 convolutional kernels, and then self-attention mechanism is combined with the residual blocks in depth residual network to extract the deep detail features of faces. Finally, the extracted features are fused globally by skip connections, which provide more high-frequency details for face reconstruction. Experiments on Helen, CelebA face datasets and real-world images showed that the proposed method could make full use of facial feature information, and its peak signal to noise ratio (PSNR) and structural similarity (SSIM) were both higher than the comparison methods with better subjective visual effects.
The Journal of Electronic Imaging (JEI), copublished bimonthly with the Society for Imaging Science and Technology, publishes peer-reviewed papers that cover research and applications in all areas of electronic imaging science and technology.
The explosion process of flake aluminum powder/air two-phase flow was experimentally studied in a large-scale long straight horizontal tube with a length of 32.4 m and an inner diameter of 0.199 m. The deflagration-to-detonation transition (DDT) of the aluminum powder/air mixture was analyzed after ignited by a 40 J electric spark, and the DDT of the mixture at different mass concentrations was compared. The results show that self-sustained detonation can be achieved in the range of 286 g/m3~532 g/m3 of flake aluminum powder concentration, , and the DDT process of aluminum powder/air mixture when the concentration is 409 g/m3 (optimal concentration) is analyzed in detail. The detonation velocity and detonation pressure of the optimal concentration are 1690 m/s and 58 bar, respectively. During the self-sustained detonation stage, the detonation overpressure of the multiphase fuel-air mixture exhibits a typical constant oscillation characteristic, while the detonation velocity remains stable. In addition, a double-headed mode helical detonation phenomenon was observed in the detonation wave front of the aluminum powder/air mixture. The structure of the detonation wave, the flow field parameters and the interaction between the shock wave and the three-wave point trajectory are analyzed. The detonation cell size at the optimal concentration is about 486...