Search

Specular highlight removal is a challenging task in the field of image enhancement, while it can significantly improve the quality of image in highlight regions. Recently, deep learning-based methods have been widely adopted in this task, demonstrating excellent performance by training on either massive paired data, wherein both the highlighted and highlight-free versions of the same image are available, or unpaired datasets where the one-to-one correspondence is inapplicable. However, it is difficult to obtain the corresponding highlight-free version of a highlight image, as the latter has already been produced under specific lighting conditions. In this paper, we propose a method for weakly supervised specular highlight removal that only requires highlight images. This method involves generating highlight-free images from highlight images with the guidance of masks estimated using non-negative matrix factorization (NMF). These highlight-free images are then fed consecutively into a series of modules derived from a Cycle Generative Adversarial Network (Cycle-GAN)-style network, namely the highlight generation, highlight removal, and reconstruction modules in sequential order. These modules are trained jointly, resulting in a highly effective highlight removal module during the verification. On the specular highlight image quadruples (SHIQ) and the LIME datasets, our method achieves an accuracy of 0.90 and a balance error rate (BER) of 8.6 on SHIQ, and an accuracy of 0.89 and a BER of 9.1 on LIME, outperforming existing methods and demonstrating its potential for improving image quality in various applications.

The trends exhibited by the parameters that describe the mechanical behaviour of major ampullate gland silk fibers spun by Argiope bruennichi spiders is explored by performing a series of loading-unloading tests at increasing values of strain, and by the subsequent analysis of the true stress-true strain curves obtained from these cycles. The elastic modulus, yields stress, energy absorbed, and energy dissipated in each cycle are computed in order to evaluate the evolution of these mechanical parameters with this cyclic straining. The elastic modulus is observed to increase steadily under these loading conditions, while only a moderate variation is found in the yield stress. It is also observed that a significant proportion of the energy initially absorbed in each cycle is not only dissipated, but that the material may recover partially from the associated irreversible deformation. This variation in the mechanical performance of spider silk is accounted for through a combination of irreversible and reversible deformation micromechanisms in which the viscoelasticity of the material plays a leading role.

The projected increase in temperature and water scarcity represents a challenge for winegrowers due to changing climatic conditions. Although heat and drought often occur concurrently in nature, there is still little known about the effects of water stress (WS) on grapevines in hot environments. This study aimed to assess whether the grapevine’s physiological and spectral responses to WS in hot environments differ from those expected under lower temperatures. Therefore, we propose an integrated approach to assess the physiological, thermal, and spectral response of two grapevine varieties (Vitis vinifera L.), Grenache and Shiraz, to WS in a hot environment. In a controlled environment room (CER), we imposed high-temperature conditions (TMIN 30 °C–TMAX 40 °C) and compared the performance of well-watered (WW) and WS-ed potted own-rooted Shiraz and Grenache grapevines (SH_WW, SH_WS, GR_WW, and GR_WS, respectively). We monitored the vines’ physiological, spectral, and thermal trends from the stress imposition to the recovery after re-watering. Then, we performed a correlation analysis between the physiological parameters and the spectral and thermal vegetation indices (VIs). Finally, we looked for the best-fitting models to predict the physiological parameters based on the spectral VIs. The results showed that GR_WS was more negatively impacted than SH_WS in terms of net photosynthesis (Pn, GR-WS = 1.14 μmol·CO2 m−2·s−1; SH-WS = 3.64 μmol·CO2 m−2·s−1), leaf transpiration rate (E, GR-WS = 1.02 mmol·H2O m−2·s−1; SH-WS = 1.75 mmol·H2O m−2·s−1), and stomatal conductance (gs, GR-WS = 0.04 mol·H2O m−2·s−1; SH-WS = 0.11 mol·H2O m−2·s−1). The intrinsic water-use efficiency (WUEi = Pn/gs) of GR_WS (26.04 μmol·CO2 mol−1 H2O) was lower than SH_WS (34.23 μmol·CO2 mol−1 H2O) and comparable to that of SH_WW (26.31 μmol·CO2 mol−1 H2O). SH_WS was not unaffected by water stress except for E. After stress, Pn, gs, and E of GR_WS did not recover, as they were significantly lower than the other treatments. The correlation analysis showed that the anthocyanin Gitelson (AntGitelson) and the green normalised difference vegetation index (GNDVI) had significant negative correlations with stem water potential (Ψstem), Pn, gs, and E and positive correlation with WUEi. In contrast, the photochemical reflectance index (PRI), the water index (WI), and the normalised difference infrared index (NDII) showed an opposite trend. Finally, the crop water stress (CWSI) had significant negative correlations with the Ψstem in both varieties. Our findings help unravel the behaviour of vines under WS in hot environments and suggest instrumental approaches to help the winegrowers managing abiotic stress.

Resorting to the characteristic polynomial of Lax matrix for a Harry–Dym-type hierarchy, we define a trigonal curve, on which appropriate vector-valued Baker–Akhiezer function and meromorphic function are introduced. With the help of the theory of trigonal curve and three kinds of Abelian differentials, we obtain the explicit Riemann theta function representations of the meromorphic function, from which we obtain the quasi-periodic solutions for the entire Harry–Dym-type hierarchy.

Advanced persistent threat (APT) is a special attack method, which is usually initiated by hacker groups to steal data or destroy systems for large enterprises and even countries. APT has a long-term and multi-stage characteristic, which makes it difficult for traditional detection methods to effectively identify. To detect APT attacks requires solving some problems: how to deal with various uncertain information during APT attack detection, how to fully train the APT detection model with small attack samples, and how to obtain the interpretable detection results for subsequent APT attack forensics. Traditional detection methods cannot effectively utilize multiple uncertain information with small samples. Meanwhile, most detection models are black box and lack a transparent calculation process, which makes it impossible for managers to analyze the reliability and evidence of the results. To solve these problems, a novel detection method based on belief rule base (BRB) is proposed in this paper, where expert knowledge and small samples are both utilized to obtain interpretable detection results. A case study with numerical simulation is established to prove the effectiveness and practicality of the proposed method.

Heat stress (HS) and water stress (WS) pose severe threats to viticulture, and effective management solutions to counter their effects on grapevine performance must be examined. In this study, we evaluated the physiological and spectral responses of Vitis vinifera L. cv. Sauvignon blanc to individual (HS) and combined (HS + WS) stress under four different cooling and irrigation strategies. The treatments were: standard drip irrigation (SI), extra drip irrigation (SI+), extra sprinklers irrigation (SPRI), and sustained deficit irrigation (SDI; 50% of SI). Compared to the other treatments, in the early stages after the occurrence of HS, the vine water status of SPRI and SI+ improved, with high stomatal conductance (gs) (SPRI) and stem water potential (Ψstem; SPRI and SI+). All the physiological indicators measured were significantly lower after the end of HS in the SDI treatment. We also identified the spectral response of grapevine to HS and combined HS and WS (resulting from SDI). Consistent with the physiological analysis, the proximal spectral responses of leaves identified SPRI and SI+ as putative cooling strategies to minimize vine HS. The vines undergoing combined stress (SDI) showed greenness amelioration 10 days after stress, as revealed by the greenness vegetation indices (VIs), i.e., Green Index (GI), Normalized Difference Greenness Vegetation Index (NDGI), and Visible Atmospherically Resistant Index (VARI). However, their physiological recovery was not achieved within this time, as shown by the Simple Ratio Index (SRI), Transformed Chlorophyll Absorption Ratio Index (TCARI), and TCARI/Optimized Soil-Adjusted Vegetation Index (TCARI/OSAVI). A three-step band selection process allowed the identification of the spectral traits’ responsive to HS and combined stress, i.e., 1336–1340 nm, 1967–1971 nm, and 600–604 nm.

Tilt vibrations inevitably have negative effects on some precise engineering even after applying horizontal and vertical vibration isolations. It is difficult to adopt a traditional passive vibration isolation (PVI) scheme to realize tilt vibration isolation. In this paper, we present and develop a tilt active vibration isolation (AVI) device using a vertical pendulum (VP) tiltmeter and a piezoelectric transducer (PZT). The potential resolution of the VP is dependent on the mechanical thermal noise in the frequency bandwidth of about 0.0265 nrad, which need not be considered because it is far below the ground tilt of the laboratory. The tilt sensitivity of the device in an open-loop mode, investigated experimentally using a voltage controller, is found to be (1.63±0.11)×105 V/rad. To compensate for the hysteresis nonlinearity of the PZT, we experimentally established the multi-loop mathematical model of hysteresis, and designed a parallel controller consisting of both a hysteresis inverse model predictor and a digital proportional–integral–differential (PID) adjuster. Finally, the response of the device working in close-loop mode to the tilt vibration was tested experimentally, and the tilt AVI device showed a good vibration isolation performance, which can remarkably reduce the tilt vibration, for example, from 6.0131 μrad to below 0.0103 μrad.