Investigation of Background Pattern for the Outdoor Application of the BOS Method

Author(s):  
B. S. Rinkevichyus ◽  
N. M. Skornyakova ◽  
E. M. Mikhaleva ◽  
A. S. Mikhalev ◽  
A. Yu. Poroykov ◽  
...  
Animals ◽  
2021 ◽  
Vol 11 (4) ◽  
pp. 1071
Author(s):  
Zuzanna Plichta ◽  
Jarosław Kobak ◽  
Rafał Maciaszek ◽  
Tomasz Kakareko

An ornamental freshwater shrimp, Neocaridina davidi, is popular as an aquarium hobby and, therefore, a potentially invasive species. There is a growing need for proper management of this species to determine not only their optimum breeding conditions, but also their ability to colonise novel environments. We tested habitat preferences of colour morphs (brown, red, white) of N. davidi for substratum colour (black, white, grey shades, red) and fine or coarse chess-board patterns to recognise their suitable captivity conditions and predict their distribution after potential release into nature. We conducted laboratory choice experiments (n = 8) with three individuals of the same morph exposed for two hours to a range of backgrounds. Shrimp preferred dark backgrounds over light ones irrespective of their own colouration and its match with the background colour. Moreover, the brown and red morphs, in contrast to the white morph, preferred the coarse background pattern over the finer pattern. This suggests that the presence of dark, uniform substrata (e.g., rocks, macrophytes) will favour N. davidi. Nevertheless, the polymorphism of the species has little effect on its total niche breadth, and thus its invasive potential.


2018 ◽  
Vol 2018 ◽  
pp. 1-11
Author(s):  
Yan-Guo Zhao ◽  
Feng Zheng ◽  
Zhan Song

Sliding-window based multiclass hand posture detections are often performed by detecting postures of each predefined category using an independent detector, which makes it lack efficiency and results in high postures confusion rates in real-time applications. To tackle such problems, in this work, an efficient cascade detector that integrates multiple softmax-based binary (SftB) models and a softmax-based multiclass (SftM) model is investigated to perform multiclass posture detection in parallel. The SftB models are used to distinguish the predefined postures from the background regions, and the SftM model is applied to discriminate among all the predefined hand posture categories. Another usage of the cascade structure is that it could effectively decompose the complexity of background pattern space and therefore improve the detection accuracy. In addition, to balance the detection accuracy and efficiency, the HOG features of increasing resolutions will be adopted by classifiers of increasing stage-levels in the cascade structure. The experiments are implemented under various scenarios with complicated background and challenging lightings. Results show the superiority of the proposed SftB classifiers over the traditional binary classifiers such as logistic regression, as well as the accuracy and efficiency improvements brought by the softmax-based cascade architecture compared with the noncascade multiclass softmax detectors.


2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Alessia Quitadamo ◽  
Valerie Massardier ◽  
Marco Valente

Blends based on high-density polyethylene (HDPE) and poly(lactic) acid (PLA) with different ratios of both polymers were produced: a blend with equal amounts of HDPE and PLA, hence 50 wt.% each, proved to be a useful compromise, allowing a high amount of bioderived charge without this being too detrimental for mechanical properties and considering its possibility to biodegradation behaviour in outdoor application. In this way, an optimal blend suitable for producing a composite with cellulosic fillers is proposed. In the selected polymer blend, wood flour (WF) was added as a natural filler in the proportion of 20, 30, and 40 wt.%, considering as 100 the weight of the polymer blend matrix. There are two compatibilizers to modify both HDPE-PLA blend and wood-flour/polymer interfaces, i.e., polyethylene-grafted maleic anhydride and a random copolymer of ethylene and glycidyl methacrylate. The most suitable percentage of compatibilizer for HDPE-PLA blends appears to be 3 wt.%, which was selected also for use with wood flour. In order to evaluate properties of blends and composites tensile tests, scanning electron microscopy, differential scanning calorimetry, thermogravimetric analyses, and infrared spectroscopy have been performed. Wood flour seems to affect heavy blend behaviour in process production of material suggesting that future studies are needed to reduce defectiveness.


2013 ◽  
Vol 2013 ◽  
pp. 1-8 ◽  
Author(s):  
Mohamad Zaki Abdullah ◽  
Yakubu Dan-mallam ◽  
Puteri Sri Melor Megat Yusoff

The main objective of this research is to investigate the effect of environmental degradation on the mechanical properties of kenaf/PET fiber reinforced POM hybrid composite. Kenaf and PET fibers were selected as reinforcements because of their good mechanical properties and resistance to photodegradation. The test samples were produced by compression molding. The samples were exposed to moisture, water spray, and ultraviolet penetration in an accelerated weathering chamber for 672 hours. The tensile strength of the long fiber POM/kenaf (80/20) composite dropped by 50% from 127.8 to 64.8 MPa while that of the hybrid composite dropped by only 2% from 73.8 to 72.5 MPa. This suggests that the hybrid composite had higher resistance to tensile strength than the POM/kenaf composite. Similarly, the results of flexural and impact strengths also revealed that the hybrid composite showed less degradation compared to the kenaf fiber composite. The results of the investigation revealed that the hybrid composite had better retention of mechanical properties than that of the kenaf fiber composites and may be suitable for outdoor application in the automotive industry.


Author(s):  
Kukjin Chun ◽  
Joonyeop Lee ◽  
Ji-hyuk Kim ◽  
Hyeon Kim ◽  
Kwang-jun Yoon ◽  
...  

Author(s):  
Bulganmaa Togookhuu ◽  
Wuyungerile Li ◽  
Yifan Sun ◽  
Junxing Zhang

Sign in / Sign up

Export Citation Format

Share Document