This paper presents a novel No-Reference Video Quality Assessment (NR-VQA) model that utilizes proposed 3D steerable wavelet transform-based Natural Video Statistics (NVS) features as well as human perceptual features. Additionally, we proposed a novel two-stage regression scheme that significantly improves the overall performance of quality estimation. In the first stage, transform-based NVS and human perceptual features are separately passed through the proposed hybrid regression scheme: Support Vector Regression (SVR) followed by Polynomial curve fitting. The two visual quality scores predicted from the first stage are then used as features for the similar second stage. This predicts the final quality scores of distorted videos by achieving score level fusion. Extensive experiments were conducted using five authentic and four synthetic distortion databases. Experimental results demonstrate that the proposed method outperforms other published state-of-the-art benchmark methods on synthetic distortion databases and is among the top performers on authentic distortion databases. The source code is available at https://github.com/anishVNIT/two-stage-vqa. 相似文献
The efficiency of training visual attention in the central and peripheral visual field was investigated by means of a visual detection task that was performed in a naturalistic visual environment including numerous, time-varying visual distractors. We investigated the minimum number of repetitions of the training required to obtain the top performance and whether intra-day training improved performance as efficiently as inter-day training. Additionally, our research aimed to find out whether exposure to a demanding task such as a microsurgical intervention may cancel out the effects of training.
Results showed that performance in visual attention peaked within three (for tasks in the central visual field) to seven (for tasks in the periphery) days subsequent to training. Intra-day training had no significant effect on performance. When attention training was administered after exposure to stress, improvement of attentional performance was more pronounced than when training was completed before the exposure. Our findings support the implementation of training in situ at work for more efficient results.
Practitioner Summary: Visual attention is important in an increasing number of workplaces, such as with surveillance, inspection, or driving. This study shows that it is possible to train visual attention efficiently within three to seven days. Because our study was executed in a naturalistic environment, training results are more likely to reflect the effects in the real workplace. 相似文献
ABSTRACTThis paper proposes a novel tracking method to deal with fast changes of solar irradiation and power limit change in order to increase tracking efficiency. This goal is achieved by estimating (i) next operating mode and (ii) next step point with the use of tangent rule in triangle. After every fast response to sudden changes, accurate response phase starts in order to track desired power in each operating mode by adaptive step size. Drift problem in defining next operating mode is eliminated in proposed method by estimating next operating mode, and settling time is decreased to about 25 percent of settling time of other methods by estimating next step point. Simulation and experimental results show the performance of proposed method. 相似文献
In this paper, an experimental study of the conventional solar still (CSS), the conventional solar still with glass cooling (CSSGC), the conventional solar still with basin heating (CSSBH), and the conventional solar still with glass cooling and basin heating (CSSGCBH) was carried out on the basis of the distilled water production, the energy efficiency (EnE), the exergy efficiency (ExE), and economic analysis. The CSSGC and CSSBH contain Peltier modules for cooling the glass and heating the basin. The evaporative heat transfer coefficient for all the experimental stills was calculated. The values of daily distilled water production from the CSSGCBH, CSSBH, CSSGC, and CSS were 4.56, 3.79, 2.49, and 1.89 kg/m2, respectively. The daily distilled yield of the CSSBH and CSSGCBH were increased by 58.55% and 50.13%, respectively, as compared with the CSS. Moreover, the daily EnE and ExE of the CSSGCBH were 27.03% and 3.5%, respectively, whereas the EnE and ExE of the CSS were 10.88% and 1.3%, respectively. Furthermore, the cost of distilled water production was found to be 0.26, 0.35, 0.53, and 0.64 $/day for the CSS, CSSGC, CSSBH, and CSSGCBH, respectively, if the selling price of the distilled water was Rs10. 相似文献
An extensive evaluation of low-cost dust sensors was performed using an exponentially decaying particle concentration. A total of 264 sensors including 27 sensors with light-emitting diodes (LEDs) and 237 sensors with laser lighting sources were tested. Those tested sensors were classified into 4 groups based on the deviation from the reference data obtained by a reference instrument. The response linearities of all the tested samples for PM1, PM2.5, and PM10 were in excellent agreement with the reference instrument, except a few samples. For the measurements of PM1 and PM2.5, the lighting source, that is, LED or laser, did not show any significant difference in overall sensor performance. However, LED-based sensors did not perform well for PM10 measurements. The 32, 24, and 16% of all the tested sensors for PM1, PM2.5, and PM10 measurement, respectively, are in the category of Class 1 (reference instrument reading ± 20%) requirement. The performance of the low-cost dust sensors for PM10 measurement was relatively less satisfactory. 相似文献