Search

Current visual saliency detection algorithms based on deep learning suffer from reduced detection effect in complex scenes owing to ineffective feature expression and poor generalization. The present study addresses this issue by proposing a recurrent residual network based on dense aggregated features. Firstly, different levels of dense convolutional features are extracted from the ResNeXt101 network. Then, the features of all layers are aggregated under an Atrous spatial pyramid pooling operation, which makes comprehensive use of all possible saliency cues. Finally, the residuals are learned recurrently under a deep supervision mechanism to achieve continuous optimization of the saliency map. Application of the proposed algorithm to publicly available datasets demonstrates that the dense aggregation of features not only enhances the aggregation of effective information within a single layer, but also enhances external interactions between information at different feature levels. As a result, the proposed algorithm provides better detection ability than that of current state-of-the-art algorithms. [Display omitted] • An aggregation module is designed to aggregate densely connected features with different resolutions, which enables fully communication and fusion between different network layers. • An improved recurrent residual refinement mechanism is proposed, in which the residuals are learned recurrently under deep supervision to achieve continuous optimization of the saliency map. • Extensive experiments prove the advantages of DAF-RRN over the state-of-the-arts. [ABSTRACT FROM AUTHOR]

Statistically motivated approaches, such as the active appearance model (AAM), have been widely used for non-rigid objects registration and tracking. As an extension of AAM, sequential AAM (SAAM) was proposed, in which both an incremental updated component and a reference component were employed simultaneously in the fitting scheme. To make SAAM more adaptive to facial context variations during tracking, a regression-based online reference appearance model (ORAM) is presented to update the subject-specific appearance of the SAAM. The spatial map between scattered local feature correspondences and structured landmark correspondences is learned via Kernel Ridge Regression (KRR). Additionally, a shape deformation and appearance model evaluation strategies help to improve the accuracy and efficiency of the algorithm. The approach is experimentally validated by tracking face videos with improved fitting accuracy. [ABSTRACT FROM AUTHOR]

Abstract: The Active Appearance Model (AAM) is receiving considerable attention in the field of facial analysis as a powerful method for modeling and segmenting deformable visual objects. Several extensions and improvements have been proposed on the original AAM, but AAMs maintain their dependence on the good initialization of model parameters to achieve accurate fitting results. AAMs are usually used directly in video tracking by searching on each subsequent frame that employs the fitting result of the previous frame for initialization. However, this model sometimes fails when large movements exist between two frames. This mechanism occurs when frames are dropped from the video due to the use of a lossy multimedia network. A regression-based approach for automatic AAM initialization is presented in this paper. After undergoing a scattered feature correspondence based on a dual-threshold matching strategy, the AAM shape points are initialized by the spatial map between local-landmark (L2L) correspondences. The map is learned based on Kernel Ridge Regression (KRR). The proposed method can successfully track the frames that are not identified with the general AAM trackers by establishing spatial relationship between local and landmark points. The initialization is robust to disturbances, which enables it to outperform key-feature-tracking or detection-based methods. We demonstrate the efficacy of the approach on two challenging facial videos with different training data and report a detailed quantitative evaluation of its performance. [Copyright &y& Elsevier]

The present describes a porous electrode for electrical discharge machining (EDM) that can decrease the concentration of corrosion products in the discharge gap. The electrode is prepared by high-temperature sintering of copper particles. A large number of red copper particles become connected together through sintering necks to form a structure with a large number of pores that act as flushing channels. By exploring the preparation method, material, sintering temperature, and holding time, a porous electrode is prepared such that copper particles do not fall off during the discharge process. The flow of the flushing medium is simulated in the porous electrode, and the action of the flushing flow field in the discharge gap on erosion products is identified. In agreement with the simulation results, experimental results for the EDM of the titanium alloy Ti6Al4V show that the material removal rate with a porous electrode is 3 times higher than that for traditional EDM with a solid electrode. Moreover, the electrode wear is lower due to the effective discharge of the corrosion products by the flushing liquid. Experimental results when rough machining a complex semi-closed cavity show that the porous electrode can greatly shorten the machining time by 47 %, which demonstrates that a porous electrode improves the machining of a complex cavity in a titanium alloy. [ABSTRACT FROM AUTHOR]

Near-dry electrical discharge machining (EDM) is an environmentally friendly method that uses a two-phase atomized medium composed of gas and water as the discharge dielectric. The relevant research literature shows that the material removal rate (MRR) of steel materials processed by near-dry EDM with air medium (Air-NEDM) is higher than that of near-dry EDM with inert gas medium. However, the results of this present show that when argon is used as the gas medium for near-dry EDM (Ar-NEDM) to process titanium alloy, the MRR is more than 80% higher than that of Air-NEDM. Therefore, the material removal mechanism of near-dry EDM in air medium and argon medium is studied by single-pulse discharge experiment. Then, the effects of processing parameters such as current, pulse width, and gas pressure on MRR, relative electric wear rate (REWR), surface roughness (SR), and recast layer thickness (RLT) were studied through a one-factor-at-a-time approach. The results of single-pulse discharge experiment show that the discharge gap of Ar-NEDM is larger than that of Air-NEDM, and the discharge crater is also larger. The experimental results show that compared to Air-EDM, Ar-NEDM cannot only obtain higher MRR, but also can obtain a micro-surface without obvious microcracks and micropores, smaller SR, and thinner RLT, but its REWR is relatively high. [ABSTRACT FROM AUTHOR]

Abstract: A non-linear method, iterative learning control (ILC), is proposed to control the electro-hydraulic feeding process of a new slotting machine. The method attempts to acquire high precision of feeding length and trapezoid feedrate, whereas the complexity of iterative learning control algorithm does not increase much more than that of industrial PID controller. After an analysis of the two-way proportional feeding system, a non-linear dynamical mathematic model with system delay, saturation and dead-zone is developed. The computer flowrate control and the ILC controller are investigated in detail. PID controller, ILC of displacement and ILC of feedrate are compared with the dynamical model under the same desired trajectory. It is experimentally found that the proposed control scheme is more effective to improve the tracking accuracy of hydraulic feeding system of the slotting machine than that of fuzzy PID controller. [Copyright &y& Elsevier]