Abstract: Disclosed are a facial beauty prediction method and device based on multi-task migration. The method includes: performing similarity measurement based on a graph structure on a plurality of tasks to obtain an optimal combination of the plurality of tasks; constructing a facial beauty prediction model including a feature sharing layer based on the optimal combination; migrating feature parameters of an existing large-scale facial image network to the feature sharing layer of the facial beauty prediction model; inputting facial images for training to pre-train the facial beauty prediction model; and inputting a facial image to be tested to the trained facial beauty prediction model to obtain facial recognition results.

Abstract: Disclosed are a method and apparatus for SAR image data enhancement, and a storage medium. The method includes: processing an SAR target image by electromagnetic simulation to acquire an SAR electromagnetic simulation image; and processing the SAR electromagnetic simulation image and the SAR target image by a generative adversarial network to obtain a set of virtual samples of the SAR target image.

Abstract: Disclosed are a facial beauty prediction method and device based on multi-task migration. The method includes: performing similarity measurement based on a graph structure on a plurality of tasks to obtain an optimal combination of the plurality of tasks; constructing a facial beauty prediction model including a feature sharing layer based on the optimal combination; migrating feature parameters of an existing large-scale facial image network to the feature sharing layer of the facial beauty prediction model; inputting facial images for training to pre-train the facial beauty prediction model; and inputting a facial image to be tested to the trained facial beauty prediction model to obtain facial recognition results.

Abstract: A double attention network (DANet)-based drone patrol and inspection system for coastline floating garbage, including: an image acquisition module configured to shoot a video of a coastline in need of patrol and inspection by using a drone, and obtain an image from the video; a feature extraction module configured to extract shallow features and deep features, fuse the shallow features and the deep features to obtain a shared feature, and finally output a panoramic recognition result; a network training module configured to perform training on the labeled image so that the network can recognize the coastline and floating garbage; and a path correction module configured to adjust a flying direction of the drone.

Abstract: A method and system for mobile communication base station antenna measurement is disclosed. The method comprises steps of: acquiring a set of images containing antennas of a base station; processing the set of images with a model based on instance segmentation network, and generating visualized images corresponding to the set of images of antennas; calculating, from the visualized images, the quantity of antennas of the base station and separating data for each antenna; measuring parameters of each antenna by data fitting. The system comprises a processor and a memory storing program instructions thereon, the program instructions executable by the processor to cause the system to perform the steps of the method.

Abstract: A double attention network (DANet)-based drone patrol and inspection system for coastline floating garbage, including: an image acquisition module configured to shoot a video of a coastline in need of patrol and inspection by using a drone, and obtain an image from the video; a feature extraction module configured to extract shallow features and deep features, fuse the shallow features and the deep features to obtain a shared feature, and finally output a panoramic recognition result; a network training module configured to perform training on the labeled image so that the network can recognize the coastline and floating garbage; and a path correction module configured to adjust a flying direction of the drone.

Abstract: Disclosed are a method and an apparatus for multi-scale SAR image recognition based on attention mechanism. According to the method, a whole image recognition network is adjusted by training a SAR training image by an attention prediction subnet, a region-of-interest positioning subnet and an image classification subnet in combination with a network loss, which greatly improves a network performance; and in addition, an attention prediction map is generated by attention mechanism to position a most prominent feature part in the SAR image, which greatly eliminates a redundancy of image features in a machine vision, effectively determines a region-of-interest, reduces interference of image noises, greatly reduces an image processing time, improves a target recognition accuracy, is beneficial to next target positioning, and has a significant improvement on a network recognition speed integrally.

Abstract: Disclosed are method and apparatus for SAR image recognition based on multi-scale features and broad learning. A region of interest of an original SAR image is extracted by centroid localization, the image is rotated and added with noise for enhancing the data volume, the image is downsampled, LBP features and PPQ features are extracted, an LBP feature vector XLBP and an LPQ feature vector XLPQ are cascaded to achieve dimension reduction by principal component analysis to obtain a fusion feature data Xm, the fusion feature data Xm is input to a broad learning network for image recognition and a recognition result is output. By fusing the LBP features and the LPQ features, complementary information is fully utilized and redundant information is reduced. The broad learning network is used to improve the training speed and reduce the time cost. As a result, the recognition effect is more stable, robust and reliable.

Abstract: A method and system for mobile communication base station antenna measurement is disclosed. The method comprises steps of: acquiring a set of images containing antennas of a base station; processing the set of images with a model based on instance segmentation network, and generating visualized images corresponding to the set of images of antennas; calculating, from the visualized images, the quantity of antennas of the base station and separating data for each antenna; measuring parameters of each antenna by data fitting. The system comprises a processor and a memory storing program instructions thereon, the program instructions executable by the processor to cause the system to perform the steps of the method.

Abstract: Disclosed are a method and an apparatus for multi-scale SAR image recognition based on attention mechanism. According to the method, a whole image recognition network is adjusted by training a SAR training image by an attention prediction subnet, a region-of-interest positioning subnet and an image classification subnet in combination with a network loss, which greatly improves a network performance; and in addition, an attention prediction map is generated by attention mechanism to position a most prominent feature part in the SAR image, which greatly eliminates a redundancy of image features in a machine vision, effectively determines a region-of-interest, reduces interference of image noises, greatly reduces an image processing time, improves a target recognition accuracy, is beneficial to next target positioning, and has a significant improvement on a network recognition speed integrally.

Abstract: Disclosed are a method and apparatus for SAR image data enhancement, and a storage medium. The method includes: processing an SAR target image by electromagnetic simulation to acquire an SAR electromagnetic simulation image; and processing the SAR electromagnetic simulation image and the SAR target image by a generative adversarial network to obtain a set of virtual samples of the SAR target image.

Abstract: Disclosed are method and apparatus for SAR image recognition based on multi-scale features and broad learning. A region of interest of an original SAR image is extracted by centroid localization, the image is rotated and added with noise for enhancing the data volume, the image is downsampled, LBP features and PPQ features are extracted, an LBP feature vector XLBP and an LPQ feature vector XLPQ are cascaded to achieve dimension reduction by principal component analysis to obtain a fusion feature data Xm, the fusion feature data Xm is input to a broad learning network for image recognition and a recognition result is output. By fusing the LBP features and the LPQ features, complementary information is fully utilized and redundant information is reduced. The broad learning network is used to improve the training speed and reduce the time cost. As a result, the recognition effect is more stable, robust and reliable.