Search

• A blind spot speckle suppression method based on a global awareness strategy is proposed to achieve self-supervised denoising of sonar images, which helps to reduce the noise interference to downstream tasks. • A hybrid contextual dynamic attention mechanism (HCDAM) is introduced to enhance and correct the locality map for salient region extraction to improve the reliability of segmented targets. • A co-training method for the joint speckle suppression task and the garbage instance segmentation task is presented, which facilitates the flexible execution of underwater garbage detection tasks. Sonar is widely used in marine water cleaning tasks, so sonar images have become an effective tool for garbage detection and underwater scene analysis. However, it is an extremely difficult task to achieve fully supervised denoising and garbage detection for sonar images. This is because sonar images are weakly annotated samples that are susceptible to noise interference and have no reference clean image. To this end, we propose a sonar image garbage instance segmentation model via global despeckling and dynamic attention graph optimization(GD-DAGO). Specifically, a self-supervised blind spot network denoising structure is presented in this paper. The proposed denoising model overcomes the defects of information loss in the traditional blind spot network structure and performs global awareness speckle suppression for the noise characteristics of sonar images themselves. In addition, a novel dynamic attention structure is employed to improve the target region estimation in the instance segmentation module and does not require supervision beyond image-level category labeling. Finally, in order to enhance the cooperative ability between the two tasks, we adopt a local perceptual loss strategy based on mask proposals guided by the downstream task, so that the whole model takes more into account the characteristics of sonar images and better serves the sonar garbage detection task. Experimental results on ARACATI 2017 and marine-debris-fls-datasets (MDFD) show that the proposed algorithm achieves a performance gain of 0.4218 and 4.2% in terms of denoising effect (ENL) and detection accuracy ( AP 25 ), respectively, compared with suboptimal algorithms. [ABSTRACT FROM AUTHOR]

During the process of steam thermal recovery of heavy oil, steam channeling seriously affects the production and ultimate recovery. In this study, fly ash was used as the plugging agent, and then a series of plugging experiments based on the results of two-dimensional (2D) experiments were conducted to study the effect of plugging the steam breakthrough channels. The experimental results show that the inorganic particle plugging agent made from the fly ash had a good suspension stability, consolidation strength, and injection performance. Because of these characteristics, it was migrated farther in the formation with a high permeability than in the formation with a low permeability, and the plugging rate was greater than 99%. After steam injection, it had a good anti-flush ability and stable plugging performance in the formation. In terms of the oil displacement effect, oil recovery in the formation with a low permeability was effectively improved because of plugging. The results show that the inorganic particle plugging agent could effectively control the steam channeling and it improved the development effect of the heavy oil reservoir. [ABSTRACT FROM AUTHOR]

Aiming to reduce the negative effect of steam channeling in the late stage of steam flooding applied in heavy oil reservoirs, experimental studies were carried out on selective plugging of solid particles, added to single-medium- and multimedia-assisted steam flooding. This work also explored the mechanisms of enhancing heavy oil recovery by applying plugging agent- and multimedia-assisted steam flooding and its optimized injection parameters. Through solid particle plugging experiments, this study clarifies the high-efficiency solid particle plugging mechanism, with an optimized slug size of 0.40 PV and plugging ratio of over 98%. Through single-medium- and multimedia-assisted steam flooding experiments, this study confirms that gas-assisted steam flooding has an effect of synergistic oil displacement and that a CO2 with urea solution-assisted steam flooding method achieves the best production performance. Its oil recovery factor is 10.7% higher than that of the steam flooding process. Parallel sand pack models with a permeability difference of more than 10 times were used to mimic a heavy oil reservoir with high-permeability channels, and the selective plugging of solid particles was carried out. The plugging ratio of high-permeability formation reached 91.20%, playing an effective plugging role. Solid particle plugging is less effective to the low-permeability formation, with the plugging ratio at only 32.39%. Based on the selective plugging of solid particles, a plugging agent- and multimedia-assisted steam flooding experiment was conducted, the high-permeability formation was effectively plugged, and the swept volume of the low-permeability formation increased significantly. The final recovery factor of the high-permeability formation was enhanced by 11%, and the recovery factor of the low-permeability formation increased by 3 times, reaching 36.38%. Therefore, solid particle plugging effectively alleviates the impact of high-permeability formation caused by permeability difference during steam flooding. [ABSTRACT FROM AUTHOR]

The advancement of lithography, mass spectrometry and other technologies is increasingly requiring the high-quality focusing of extreme ultraviolet (EUV) beams. Traditional transmissive optics are not suitable for focusing EUV beams due to the strong absorption of most materials. However, rapid developments of metasurfaces have led to breakthroughs in the research of EUV metalenses. Based on the hole-type unit structure proposed recently, we demonstrated the dual-wavelength achromatic metalens in the EUV working for wavelengths of 46.9 and 69.8 nm with a numerical aperture 0.05. Then the dispersion manipulation for the achromatic metalens is extended to three wavelengths 46.9, 60, and 69.8 nm. The simulation results suggest that the maximum relative focal shift from the designed focal length is 0.008 %, and the diffraction-limit focusing is achieved for all working wavelengths. This work could expand the means of the EUV optical field modulation. • Transmissive EUV metalens is designed for beam focusing. • The dual-wavelength achromatic metalens is demonstrated. • The dispersion manipulation for the metalens is extended to three wavelengths. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have obtained high accuracy results for pedestrian re-identification in the past few years. There is always a trade-off between high accuracy and computational time in CNNs. Training CNN is always very difficult as it may take a long time to produce high accuracy results. To overcome this limitation, a novel method parallel stochastic gradient descent (PSGD) is proposed to train a five-hierarchical parallel CNNs that is designed according to pedestrian attributes. Moreover, the momentum correction and adaptive adjustment of learning rate are applied during training process and the time interval for updating parameters is inspected during optimization of parameters selection. The results of this paper prove the effectiveness of proposed PSGD that successfully decreases the training process by five times and surpasses the state-of-the-art methods of pedestrian re-identification in terms of both accuracy and time. The minimum reported running time of the proposed method is 8.7 s which is minimum among all other state-of-the-art methods. These promising results show the efficiency and performance of the proposed model. [ABSTRACT FROM AUTHOR]

Classification for flowers is a very difficult task. Traditional methods need to built a classifier for each flower category, and obtain large number of flower samples to train these classifiers. In practice, many different types of flowers make the job become very difficult and boring. In this work, we present an attribute based approach for flowers recognition. Particularly, instead of training for a specific category of flowers directly based on manually designed features such as SIFT and HoG, we extract a series of visual attributes from a given set of flower images and generalize these to new images with possibly unknown flowers. A recently proposed sparse representations classification scheme is employed to predict the attributes of a given flower image from any category. In addition, we use a genetic algorithm to find the most discriminative attributes among others for better performance during the stage of flower classification. The effectiveness of the proposed method is validated on a publicly available flower classification database with promising results. [ABSTRACT FROM AUTHOR]

Weakly supervised temporal action localization (W-TAL) is designed to detect and classify all the action instances in an untrimmed video with only video-level labels. Due to the lack of frame-level annotations, the correlations learning between action snippets and the separation between action and background are the two key issues for accurate action localization. To mine the intrinsic correlations of space and time embodied in the occurrences of action in a video and identify the action and background in the snippets, a novel method based on spatial–temporal correlations learning and action-background jointed attention for W-TAL is proposed. In this method, the graph convolution and 1-D temporal convolution networks are constructed to learn the spatial and temporal features of the video, respectively, then fused to learn a fruitful spatial–temporal correlative feature map. This ensures more completed features representation for action localization. Next, different from the other methods, action-background jointed attention mechanism is presented to explicitly modelled background as well as action in a three-branch classification network. This classification network can distinguish action and background and realize the separation of action and background better, so as to promote more accurate action localization. Experiments conducted on Thumos14 and ActivityNet1.3 show that our method outperforms state-of-the-art methods, especially at some high t-IoU thresholds, which further validates the effectiveness of our method. [ABSTRACT FROM AUTHOR]

• Limited information in time domain results in limited performance of feature classification. • The particularity of EEG signal makes it difficult to measure. • The strong correlation of EEG signals makes it difficult to build feature extraction network. With the promotion of brain-computer interface technology, it is possible to study brain control system through EEG signals in recent years. In order to solve the problem of EEG signal classification effectively, a motor imagery classification algorithm based on recurrence plot convolution neural network is proposed. Firstly, EEG signals are preprocessed to enhance the signal intensity in the exercise interval. Secondly, time-domain and frequency-domain features are extracted respectively to construct the feature mode of recurrence plot. Finally, a new neural network is established to realize the accurate recognition of left and right movements. This research can also be transferred to other research fields. [Display omitted] [ABSTRACT FROM AUTHOR]

High dynamic range image (HDRI) which is combined with low dynamic range image (LDRI) needs to be mapped to a low dynamic area to display. In the process of mapping, it is impossible to determine the contribution of low dynamic image sequences in the display images, so that it results in a problem that the low dynamic images cannot be accurately selected. In this paper, for the first time, a contribution algorithm from LDRI to HDRI according to the corresponding response curve of the camera is proposed. [ABSTRACT FROM AUTHOR]

The use of polymer gel for water control and oil addition is a common technical method in oilfield development. The polymer and hydrated bentonite react under the action of an organic crosslinking agent to form a composite gel. The particle-size change and microstructure of the composite gel were analyzed via shear thinning, thixotropic, viscoelastic, and start-up stress rheology experiments. The experimental results show that the polyacrylamide/bentonite organic crosslinked composite gel was a gel system with bentonite as the core aggregate structure, and the large particle-size distribution was mostly increased with increasing crosslinker content. The composite gel presented shear thinning characteristics, the content of bentonite or crosslinking agent was increased, and the shear resistance was stronger at a high shear rate. The composite gel exhibited positive thixotropic properties, and the thixotropy increased with increasing bentonite content. The composite gel had good viscoelastic characteristics, the elastic characteristics of the composite gel showed more significantly with bentonite increases, and the viscosity of the composite gel showed its characteristics more significantly with the crosslinking agent increased. After loading at a rate on the composite gel, the shear stress increased significantly with time and reached its maximum value, and then the shear stress decreased and gradually stabilized. [ABSTRACT FROM AUTHOR]