Search

Salient object detection has made substantial progress due to the exploitation of multi-level convolutional features. The key point is how to combine these convolutional features effectively and efficiently. Due to the step by step down-sampling operations in almost all CNNs, multi-level features usually have different scales. Methods based on fully convolutional networks directly apply bilinear up-sampling to low-resolution deep features and then combine them with high-resolution shallow features by addition or concatenation, which neglects the compatibility of features, resulting in misalignment problems. In this paper, to solve the problem, we propose an alignment integration network (ALNet), which aligns adjacent level features progressively to generate powerful combinations. To capture long-range dependencies for high-level integrated features as well as maintain high computational efficiency, a strip attention module (SAM) is introduced into the alignment integration procedures. Benefiting from SAM, multi-level semantics can be selectively propagated to predict precise salient objects. Furthermore, although integrating multi-level convolutional features can alleviate the blur boundary problem to a certain extent, it is still unsatisfactory for the restoration of a real object boundary. Therefore, we design a simple but effective boundary enhancement module (BEM) to guide the network focus on boundaries and other error-prone parts. Based on BEM, an attention weighted loss is proposed to boost the network to generate sharper object boundaries. Experimental results on five benchmark datasets demonstrate that the proposed method can achieve state-of-the-art performance on salient object detection. Moreover, we extend the experiments on the remote sensing datasets, and the results further prove the universality and scalability of ALNet. [ABSTRACT FROM AUTHOR]

In this article, we theoretically designed and simulated a silicon core fiber for the simultaneous detection of temperature and refractive index. We first discussed the parameters of the silicon core fiber for near single-mode operation. Second, we designed and simulated a silicon core-based fiber Bragg grating and applied it for simultaneous sensing of temperature and environmental refractive index. The sensitivities for the temperature and refractive index were 80.5 pm/°C and 208.76 dB/RIU, respectively, within a temperature range of 0 to 50 °C and a refractive index range of 1.0 to 1.4. The proposed fiber sensor head can provide a method with simple structure and high sensitivity for various sensing targets. [ABSTRACT FROM AUTHOR]

An automatic colorization algorithm can convert a grayscale image to a colorful image using regression loss functions or classification loss functions. However, the regression loss function leads to brown results, while the classification loss function leads to the problem of color overflow and the computation of the color categories and balance weights of the ground truth required for the weighted classification loss is too large. In this paper, we propose a new method to compute color categories and balance the weights of color images. In this paper, we propose a new method to compute color categories and balance weights of color images. Furthermore, we propose a U-Net-based colorization network. First, we propose a category conversion module and a category balance module to obtain the color categories and to balance weights, which dramatically reduces the training time. Second, we construct a classification subnetwork to constrain the colorization network with category loss, which improves the colorization accuracy and saturation. Finally, we introduce an asymmetric feature fusion (AFF) module to fuse the multiscale features, which effectively prevents color overflow and improves the colorization effect. The experiments show that our colorization network has peak signal-to-noise ratio (PSNR) and structure similarity index measure (SSIM) metrics of 25.8803 and 0.9368, respectively, for the ImageNet dataset. As compared with existing algorithms, our algorithm produces colorful images with vivid colors, no significant color overflow, and higher saturation. [ABSTRACT FROM AUTHOR]

Highly accurate measurements of infrared systems cannot be achieved without precise radiometric calibrations. In order to correctly interpret and process infrared images and monitor the performance of infrared cameras, their radiometric calibration is also required periodically. In this paper, an equivalent calibration method is proposed based on an internal blackbody baffle. It is used for the replacement of a large surface-source blackbody covering the aperture for the field calibration of large-aperture equipment. Subsequently, the expressions of the equivalent calibration conversion function (ECCF) are derived based on the grayscale response of the camera and the calibration models of the two methods, and experimental measurements and fits are performed using a cooled mid-wave infrared camera. The results show that the measured functional form is consistent with the physical meaning. Moreover, in the target imaging experiments, the results of the inversion using the equivalent calibration conversion function and the results of the direct calibration of the external blackbody are largely consistent with the average error of 0.198% between the two, and the maximum error is within 1%. The maximum error between the inversion result of radiation brightness and the actual value of the target is 6.29%, and the accuracy fully meets the radiometric measurement requirements. [ABSTRACT FROM AUTHOR]

In this paper, we focus on the radio resource planning in the uplink of licensed Orthogonal Frequency Division Multiple Access (OFDMA) based Internet of Things (IoT) networks. The average behavior of the network is considered by assuming that active sensors and collectors are distributed according to independent random Poisson Point Process (PPP) marked by channel randomness. Our objective is to statistically determine the optimal total number of Radio Resources (RRs) required for a typical cell. On one hand, the allocated bandwidth should be sufficiently large to support the traffic of the devices and to guarantee a low access delay. On the other hand, the over-dimensioning is costly from an operator point of view and induces spectrum wastage. For this sake, we propose statistical tools derived from stochastic geometry to evaluate, adjust and adapt the allocated bandwidth according to the network parameters, namely the required Quality of Service (QoS) in terms of rate and access delay, the density of the active sensors, the collector intensities, the antenna configurations and the transmission modes. The optimal total number of RRs required for a typical cell is then calculated by jointly considering the constraints of low access delay, limited power per RR, target data rate and network outage probability. Different types of networks are considered including Single Input Single Output (SISO) systems, Single Input Multiple Output (SIMO) systems using antenna selection or Maximum Ratio Combiner (MRC), and Multiuser Multiple Input Multiple Output (MU-MIMO) systems using Zero-Forcing decoder. [ABSTRACT FROM AUTHOR]

A relatively simple method to improve the image resolution of light field based on a liquid crystal (LC) microlens doped with multi-walled carbon nanotubes (MWCNTs) was developed and evaluated. As the nanoparticles were doped in LC, its electro-optical features could enhance, leading to a short response time compared to the pure LC microlens. With the maximum use of the proposed LC microlens, a method combining aperiodicity extraction and weighted average algorithm was adopted to realize the high-resolution light field imaging. The aperiodicity extraction method was proposed, which could effectively improve resolution of view angle image. For synthesizing the full resolution image at 0 Vrms and the extracted view angle image of light field imaging at 2.0 Vrms, the final high-resolution light field imaging could be obtained in a short time by weighted average algorithm. In this way, the common problem of low resolution in light field imaging could be solved. This proposed method was in good agreement with our experimental results. And it was also in line with the development of the trend of the smart imaging sensor combining algorithm with hardware. [ABSTRACT FROM AUTHOR]

Strengthening existing reinforced concrete (RC) columns using a partial wrapping strengthening technique (PWST) by fiber-reinforced polymer (FRP) strips has been widely implemented. However, compared with the confinement mechanism of confined concrete in columns strengthened with the FRP full wrapping strengthening technique (FWST), the confinement mechanism of confined concrete in FRP partially wrapped columns is less understood. This paper presents the results of an experimental investigation into the behavior of confined concrete in FRP partially wrapped square columns under axial compression. The effects of FRP strip width and thickness on stress–strain behavior were thoroughly investigated. The novel particle image velocimetry (PIV) non-contact strain sensing technique was adopted to measure the strain in the specimens. Results show that the axial strains as well as the hoop strains are generally larger at the mid-plane of adjacent FRP strips than those at the mid-plane of each FRP strip, and considerable variation in hoop strains along the height of the specimens was observed. Comparisons between the experimental results and predictions by existing design-oriented stress–strain models were carried out to examine the accuracy of the models. A new design-oriented stress–strain model is proposed for confined concrete in FRP partially wrapped square columns and the comparisons between laboratory results and predictions from the proposed model show that the proposed model is superior to the existing models. [ABSTRACT FROM AUTHOR]