This paper proposed a novel multi-view interactive behavior recognition method based on local self-similarity descriptors and graph shared multi-task learning. First, we proposed the composite interactive feature repr...This paper proposed a novel multi-view interactive behavior recognition method based on local self-similarity descriptors and graph shared multi-task learning. First, we proposed the composite interactive feature representation which encodes both the spatial distribution of local motion of interest points and their contexts. Furthermore, local self-similarity descriptor represented by temporal-pyramid bag of words(BOW) was applied to decreasing the influence of observation angle change on recognition and retaining the temporal information. For the purpose of exploring latent correlation between different interactive behaviors from different views and retaining specific information of each behaviors, graph shared multi-task learning was used to learn the corresponding interactive behavior recognition model. Experiment results showed the effectiveness of the proposed method in comparison with other state-of-the-art methods on the public databases CASIA, i3Dpose dataset and self-built database for interactive behavior recognition.展开更多
In order to develop further the application of high temperature heat pipe in hypersonic vehicles thermal protection, the principles and characteristics of high temperature heat pipe used in hypersonic vehicles thermal...In order to develop further the application of high temperature heat pipe in hypersonic vehicles thermal protection, the principles and characteristics of high temperature heat pipe used in hypersonic vehicles thermal protection were introduced. The methods of numerical simulation, theory analysis and experiment research were utilized to analyze the frozen start-up and steady state characteristic of the heat pipe as well as the machining improvement for fabricating irregularly shaped heat pipe which is suitable for leading edge of hypersonic vehicles. The results indicate that the frozen start-up time of heat pipe is long （10 min） and there exists large temperature difference along the heat pipe （47 ℃/cm）, but the heat pipe can reduce the temperature in stagnation area of hypersonic vehicles from 1 926 to 982 ℃ and work normally during 1 000-1 200℃. How to improve the maximum heat transfer capability and reduce the time needed for start-up from frozen state of the heat pipe by optimizing thermostructure such as designing of a novel wick with high performance is the key point in hypersonic vehicles thermal protection of heat pipe.展开更多
In order to obtain better carbonation effect, extraction behavior of slag batch is necessary to study. Relevant parameters like selective extraction yield were originally discussed. The relationship between selective ...In order to obtain better carbonation effect, extraction behavior of slag batch is necessary to study. Relevant parameters like selective extraction yield were originally discussed. The relationship between selective extraction yield and conversion ratio was systemically focused on. The results show that alkaline earth metal conversion ratio is changed with leaching time and NH4CI concentration by first order exponential, and the maximum conversion for calcium keeps about 68% at 120 min in 0.4 mol/L NH4C1 solution, while leaching temperature and particle size have a linear effect on conversion ratio. Selective extraction yield of calcium is more than 93%, and the value of Mg is less than 5%. Apparent layer bands of silicon and calcium appear in the surface area through morphology detection of slag after leaching, and the case for 38-75 μm slag batch is more obvious than 75 150 μm slag and slag with larger particle size when leaching in 0.4 mol/L NH4Cl solution for 90 rain at 60 ℃.展开更多
The accurate estimation of road traffic states can provide decision making for travelers and traffic managers. In this work,an algorithm based on kernel-k nearest neighbor(KNN) matching of road traffic spatial charact...The accurate estimation of road traffic states can provide decision making for travelers and traffic managers. In this work,an algorithm based on kernel-k nearest neighbor(KNN) matching of road traffic spatial characteristics is presented to estimate road traffic states. Firstly, the representative road traffic state data were extracted to establish the reference sequences of road traffic running characteristics(RSRTRC). Secondly, the spatial road traffic state data sequence was selected and the kernel function was constructed, with which the spatial road traffic data sequence could be mapped into a high dimensional feature space. Thirdly, the referenced and current spatial road traffic data sequences were extracted and the Euclidean distances in the feature space between them were obtained. Finally, the road traffic states were estimated from weighted averages of the selected k road traffic states, which corresponded to the nearest Euclidean distances. Several typical links in Beijing were adopted for case studies. The final results of the experiments show that the accuracy of this algorithm for estimating speed and volume is 95.27% and 91.32% respectively, which prove that this road traffic states estimation approach based on kernel-KNN matching of road traffic spatial characteristics is feasible and can achieve a high accuracy.展开更多
The art of cricket bowling is complex and arduous owing to the run-up and ball release time energy requirement to achieve speed and variations. Therefore, human bowlers cannot bowl for extended periods and numerous me...The art of cricket bowling is complex and arduous owing to the run-up and ball release time energy requirement to achieve speed and variations. Therefore, human bowlers cannot bowl for extended periods and numerous mechanical bowling machines have been built to help batsmen improve their skills during practice sessions. However, most of these existing machines are designed for spherical balls ignoring the distinguishing physical feature of a cricket ball: the raised equatorial seam, which makes it less of a sphere. The bowlers are known to often benefit from this seam in their pursuit to taking the batsmen's wicket by imparting swing, spin and bounce variations along-with other bowling variables. This lack of the seam consideration creates a void between human and mechanical bowling. In this work, we present design and development of an automatic bowling machine termed as ROBOWLER to make mechanical bowling more realistic. This machine ensures ball seam position as well as fulfills other constraints. Ball pitching and seam position accuracy results underscore the suitability of this design to enhance the capabilities of mechanical bowling.展开更多
基金Project(51678075)supported by the National Natural Science Foundation of ChinaProject(2017GK2271)supported by Hunan Provincial Science and Technology Department,China
文摘This paper proposed a novel multi-view interactive behavior recognition method based on local self-similarity descriptors and graph shared multi-task learning. First, we proposed the composite interactive feature representation which encodes both the spatial distribution of local motion of interest points and their contexts. Furthermore, local self-similarity descriptor represented by temporal-pyramid bag of words(BOW) was applied to decreasing the influence of observation angle change on recognition and retaining the temporal information. For the purpose of exploring latent correlation between different interactive behaviors from different views and retaining specific information of each behaviors, graph shared multi-task learning was used to learn the corresponding interactive behavior recognition model. Experiment results showed the effectiveness of the proposed method in comparison with other state-of-the-art methods on the public databases CASIA, i3Dpose dataset and self-built database for interactive behavior recognition.
基金Project(51076062) supported by the National Natural Science Foundation of China
文摘In order to develop further the application of high temperature heat pipe in hypersonic vehicles thermal protection, the principles and characteristics of high temperature heat pipe used in hypersonic vehicles thermal protection were introduced. The methods of numerical simulation, theory analysis and experiment research were utilized to analyze the frozen start-up and steady state characteristic of the heat pipe as well as the machining improvement for fabricating irregularly shaped heat pipe which is suitable for leading edge of hypersonic vehicles. The results indicate that the frozen start-up time of heat pipe is long （10 min） and there exists large temperature difference along the heat pipe （47 ℃/cm）, but the heat pipe can reduce the temperature in stagnation area of hypersonic vehicles from 1 926 to 982 ℃ and work normally during 1 000-1 200℃. How to improve the maximum heat transfer capability and reduce the time needed for start-up from frozen state of the heat pipe by optimizing thermostructure such as designing of a novel wick with high performance is the key point in hypersonic vehicles thermal protection of heat pipe.
基金Project(2006BAE03A07)supported by National Key Technology Research and Development Program of 11th Five-year Plan of China
文摘In order to obtain better carbonation effect, extraction behavior of slag batch is necessary to study. Relevant parameters like selective extraction yield were originally discussed. The relationship between selective extraction yield and conversion ratio was systemically focused on. The results show that alkaline earth metal conversion ratio is changed with leaching time and NH4CI concentration by first order exponential, and the maximum conversion for calcium keeps about 68% at 120 min in 0.4 mol/L NH4C1 solution, while leaching temperature and particle size have a linear effect on conversion ratio. Selective extraction yield of calcium is more than 93%, and the value of Mg is less than 5%. Apparent layer bands of silicon and calcium appear in the surface area through morphology detection of slag after leaching, and the case for 38-75 μm slag batch is more obvious than 75 150 μm slag and slag with larger particle size when leaching in 0.4 mol/L NH4Cl solution for 90 rain at 60 ℃.
基金Projects(LQ16E080012,LY14F030012)supported by the Zhejiang Provincial Natural Science Foundation,ChinaProject(61573317)supported by the National Natural Science Foundation of ChinaProject(2015001)supported by the Open Fund for a Key-Key Discipline of Zhejiang University of Technology,China
文摘The accurate estimation of road traffic states can provide decision making for travelers and traffic managers. In this work,an algorithm based on kernel-k nearest neighbor(KNN) matching of road traffic spatial characteristics is presented to estimate road traffic states. Firstly, the representative road traffic state data were extracted to establish the reference sequences of road traffic running characteristics(RSRTRC). Secondly, the spatial road traffic state data sequence was selected and the kernel function was constructed, with which the spatial road traffic data sequence could be mapped into a high dimensional feature space. Thirdly, the referenced and current spatial road traffic data sequences were extracted and the Euclidean distances in the feature space between them were obtained. Finally, the road traffic states were estimated from weighted averages of the selected k road traffic states, which corresponded to the nearest Euclidean distances. Several typical links in Beijing were adopted for case studies. The final results of the experiments show that the accuracy of this algorithm for estimating speed and volume is 95.27% and 91.32% respectively, which prove that this road traffic states estimation approach based on kernel-KNN matching of road traffic spatial characteristics is feasible and can achieve a high accuracy.
文摘The art of cricket bowling is complex and arduous owing to the run-up and ball release time energy requirement to achieve speed and variations. Therefore, human bowlers cannot bowl for extended periods and numerous mechanical bowling machines have been built to help batsmen improve their skills during practice sessions. However, most of these existing machines are designed for spherical balls ignoring the distinguishing physical feature of a cricket ball: the raised equatorial seam, which makes it less of a sphere. The bowlers are known to often benefit from this seam in their pursuit to taking the batsmen's wicket by imparting swing, spin and bounce variations along-with other bowling variables. This lack of the seam consideration creates a void between human and mechanical bowling. In this work, we present design and development of an automatic bowling machine termed as ROBOWLER to make mechanical bowling more realistic. This machine ensures ball seam position as well as fulfills other constraints. Ball pitching and seam position accuracy results underscore the suitability of this design to enhance the capabilities of mechanical bowling.
