Adaptive visual target detection and tracking using weakly supervised incremental appearance learning and RGM-PHD tracker

Multiple visual target tracking is a challenging problem due to various uncertainties including occlusion, miss-detection and noisy measurement. Most tracking approaches utilize an object-specific detector, pre-trained on many labeled images, to provide suitable measurements for their tracking system. In this paper, we use a simple background subtraction detector which only needs the background image to localize targets independent of their shape or type. In order to cope with the uncertainties resulted by the detector, we propose an adaptive appearance model and develop an incremental appearance learning algorithm to learn the target appearances in time. The proposed method employs the background information and our defined keypoints’ miss-matched history to adapt the target appearances within different frames. Furthermore, we combine Refined Gaussian Mixture Probability Hypothesis Density (RGM-PHD) tracker with the detectors to keep target trajectories and handle uncertainties. The experiments conducted on several video datasets show the effectiveness of our proposed method.     

Effect of color temperature on appearance of paintings exhibited under LED lighting

Colour of light modulates the appearance of displayed artifacts in exhibition. To understand the effect of light on appearance of paintings, few studies have experimented to establish a relation between pleasantness with the correlated colour temperature (CCT) of light. However, some studies have found that CCT has no significant effect on pleasant appearance of painting. Therefore, in this article, an experiment with a qualitative (questionnaire on semantic differential scale, N = 30) approach was designed to understand the effect of CCT on appearance of paintings exhibited under LED lights. The findings from the experimental result depict that the appearance of paintings changes due to different CCTs of LEDs having the same illuminance. In addition, the result reveals that for both mediums of paintings considered in this study, in comparison to warm white LED and artificial daylight LED, cool white LED has appeared to be more pleasant having moderately warm feelings to the viewers.     

Physical indices for judging appearance harmony of materials

In visual design, harmony refers to the similarity among objects and the components of these objects that appear as if they belong together. Harmony is related to the body, mind, and emotions as we relate to our living space, which means that the harmony of real objects is an important characteristic. Although the appearance harmony in specific materials has been investigated, harmony among different materials has not received adequate attention. In a previous study, we investigated the appearance harmony among various materials by psychophysical experiments. In this study, we correlated the psychophysical evaluations obtained from the experiments and the physical properties of the materials. By analyzing the relationship between psychophysical evaluations and the physical measurements for each material pairs based on cluster analysis, we found that the property of texture represented by the anisotropy histogram and that of reflectance obtained from the data of the bidirectional reflectance distribution function are important indices that can be used to judge the harmony of materials. In particular, the texture properties were more effective in judging the appearance harmony of material pairs in the fixed condition for illumination and viewing angles, and the reflectance properties were superior for the material pairs in the variable condition for illumination and viewing angles.     

Investigation of metallic color perception using real‐world materials

Metallic colors have a unique appearance of glossiness with features such as highlights, contrast, and reflections on their surface, and therefore, metallic objects are very attractive to humans. Especially, gold, silver, and copper colors are familiar metals used as decorative materials, coins, and other furnishings. However, the mechanism and condition of metallic perception have not been fully investigated. There are a few studies for investigating metallic perception using rendered patches or images, but there is no study using real‐world objects. In our previous study, we developed a simple representation technique that made real objects appear to be made of gold by projecting a solid color onto a target nonmetallic object. By using the representation technique, in this study, we have further investigated the perception of metallic appearance such as gold, silver, and copper using real‐world materials, and analyzed the difference between these metallic perceptions. Our results indicate that the perception of the metallic object is different for gold, silver, and copper. Our new findings are as follows: the glitter required for the perception of gold and silver becomes an obstacle to the perception of copper; the metallic perception reveals that learning experience might be strongly affecting; and luminance adjustment is sensitive to the perception of metallic objects.     

Testing the performance of CIECAM02 from 100 to 3500 cd/m2

Color appearance models were developed to characterize the color attributes of stimuli under different viewing conditions based on data collected through magnitude estimation or color matching experiments. Although human beings experience very high light levels under daylight and the reproduction of colors under daylight is important in the color and imaging industries, the existing color appearance models were developed based on the data that were collected under the conditions with luminance levels below 700 cd/m² due to the lack of facilities to produce stable illumination at high light levels. A recent study investigating color preference of an artwork under a wide range of light levels from 20 to 15 000 lx suggested that CIECAM02 cannot accurately characterize the color appearance under extremely high light levels. This study was designed to directly test the performance of CIECAM02 from 100 to 3500 cd/m². Human observers performed color match for four hues under a series pairs of adapting conditions with a haploscopic viewing condition. It was found that CIECAM02 had the best performance in characterizing the hue angles but the worse performance in characterizing the brightness with a maximum underprediction around 200% across a wide range of luminance. This was mainly due to the fact that CIECAM02 was developed based on the data collected under relatively low adapting luminance levels. The color appearance model that was proposed to use the adapting luminance levels in characterizing the cone compression in the postadaptation process was found to have a much better performance in characterizing the brightness.     

Turning a Digital Camera into an Absolute 2D Tele‐Colorimeter

We present a simple and effective technique for absolute colorimetric camera characterization, invariant to changes in exposure/aperture and scene irradiance, suitable in a wide range of applications including image‐based reflectance measurements, spectral pre‐filtering and spectral upsampling for rendering, to improve colour accuracy in high dynamic range imaging. Our method requires a limited number of acquisitions, an off‐the‐shelf target and a commonly available projector, used as a controllable light source, other than the reflected radiance to be known. The characterized camera can be effectively used as a 2D tele‐colorimeter, providing the user with an accurate estimate of the distribution of luminance and chromaticity in a scene, without requiring explicit knowledge of the incident lighting power spectra. We validate the approach by comparing our estimated absolute tristimulus values (XYZ data in ) with the measurements of a professional 2D tele‐colorimeter, for a set of scenes with complex geometry, spatially varying reflectance and light sources with very different spectral power distribution.     

Temperature and pretreatment effects on the drying of Hass avocado seeds

The objective of the present experimental work was to determine the influence of five different drying air temperatures (313, 323, 333, 343, and 353 K) on the drying kinetics and the degree of moisture evaporation from Hass avocado seeds. The drying experiments of the non-pretreated and pretreated (sliced and crushed) Hass avocado seeds were performed in a heating furnace, where the pretreatment process was found to accelerate the drying process. The obtained results suggested that increase in the operating air temperature stimulated the rate of moisture evaporation, but resulted in the charring of the seed surface. The drying air temperature of 313 K was concluded to be suitable for the reasonable drying of Hass avocado seeds. The slicing pretreatment process was found to be better indicative of the total moisture amount present in Hass avocado seeds. The drying process removed a maximum of 58% of the initial water mass of Hass avocado seeds. An additional investigation was performed where the physical appearance of Hass avocado seeds immersed in water at different temperatures (303, 318, 325.5, 333, and 348 K) was examined. The observed study suggested that the surrounding temperature higher than 313 K could damage the physical appearance and reduce the quality of Hass avocado seeds.     

LD4型电动刀架的故障诊断及维修

介绍了LD4型电动刀架的工作原理，针对其常见的几种故障现象进行分析并提出维修方法，以供参考。     

A comprehensive model of colour appearance for related and unrelated colours of varying size viewed under mesopic to photopic conditions

CIE has recommended two previous appearance models, CIECAM97s and CIECAM02. However, these models are unable to predict the appearance of a comprehensive range of colours. The purpose of this study is to describe a new, comprehensive colour appearance model, which can be used to predict the appearance of colours under various viewing conditions that include a range of stimulus sizes, levels of illumination that range from scotopic through to photopic, and related and unrelated stimuli. In addition, the model has a uniform colour space that provides a colour‐difference formula in terms of colour appearance parameters. © 2016 Wiley Periodicals, Inc. Col Res Appl, 42, 293–304, 2017     

Study on fibre laser spot welding of TRIP980 steel

A 980 MPa transformation induced plasticity (TRIP) steel was fibre laser spot welded by different Argon (Ar) shielding conditions, laser power (1000 up to 2500 W) and defocusing distances (?8 up to +8 mm). The surface appearance, cross-section macrostructure, microstructure, hardness, tensile shear properties and fatigue properties of laser spot welds were evaluated. The results showed that the welds with Ar shielding had larger weld appearance and bonding sizes, better tensile shear properties compared with the welds without Ar shielding. With the increase in laser power, the laser welding mode changed from conduction to keyhole, which improved the bonding size and mechanical properties. The bonding size and mechanical properties increased in the order of defocusing distances of +8, ?8, +4, ?4 and 0 mm. During the fatigue tests of laser spot weld, the fusion zone pullout and sheet transverse fracture failure modes were observed.