目的提出一种结合C/S(Client/Server)架构和BRF(Boosted random ferns)算法的移动增强现实应用方案,以保证图像识别算法对于产品外包装的识别性能。方法 BRF是一种高效、鲁棒的特征匹配算法,但由于手机内存及处理器等硬件条件的制约,不...目的提出一种结合C/S(Client/Server)架构和BRF(Boosted random ferns)算法的移动增强现实应用方案,以保证图像识别算法对于产品外包装的识别性能。方法 BRF是一种高效、鲁棒的特征匹配算法,但由于手机内存及处理器等硬件条件的制约,不能直接适用于手机终端。将C/S模式与BRF算法相结合应用于图像特征匹配,并设计实验测试比较文中方案(CS-BRF)与ORB算法的识别速度和匹配精度。结果实验结果表明,相比ORB算法,CS-BRF在识别速度相近的前提下,具有更为优异的识别精度。结论 CS-BRF能够实时准确识别印刷品图像,良好适用于产品包装移动增强现实系统。展开更多
The Multi-angle imaging spectroradiometer(MISR) land-surface(LS) bidirectional reflectance factor(BRF) product(MILS_BRF) has unique semi-simultaneous multi-angle sampling and global coverage. However, unlike on-satell...The Multi-angle imaging spectroradiometer(MISR) land-surface(LS) bidirectional reflectance factor(BRF) product(MILS_BRF) has unique semi-simultaneous multi-angle sampling and global coverage. However, unlike on-satellite observations, the spatio-temporal characteristics of MILS_BRF data have rarely been explicitly and comprehensively analysed. Results from 5-yr(2011–2015) of MILS_BRF dataset from a typical region in central Northeast Asia as the study area showed that the monthly area coverage as well as MILS_BRF data quantity varies significantly, from the highest in October(99.05%) through median in June/July(78.09%/75.21%) to lowest in January(18.97%), and a large data-vacant area exists in the study area during four consecutive winter months(December through March). The data-vacant area is mainly composed of crop lands and cropland/natural vegetation mosaic. The amount of data within the principal plane(PP)±30°(nPP) or cross PP ±30°(nCP), varies intra-annually with significant differences from different view zeniths or forward/backward scattering directions. For example, multiple off-nadir cameras have nPP but no nCP data for up to six months(September through February), with the opposite occurring in June and July. This study provides explicit and comprehensive information about the spatio-temporal characteristics of product coverage and observation geometry of MILS_BRF in the study area. Results provide required user reference information for MILS_BRF to evaluate performance of BRDF models or to compare with other satellite-derived BRF or albedo products. Comparing this final product to on-satellite observations, what was found here reveals a new perspective on product spatial coverage and observation geometry for multi-angle remote sensing.展开更多
It is difficulties for the computer simulation method to study radiation regime at large-scale.Simplified coniferous model was investigated in the present study.It makes the computer simulation methods such as L-syste...It is difficulties for the computer simulation method to study radiation regime at large-scale.Simplified coniferous model was investigated in the present study.It makes the computer simulation methods such as L-systems and radiosity-graphics combined method(RGM) more powerful in remote sensing of heterogeneous coniferous forests over a large-scale region.L-systems is applied to render 3-D coniferous forest scenarios,and RGM model was used to calculate BRF(bidirectional reflectance factor) in visible and near-infrared regions.Results in this study show that in most cases both agreed well.Meanwhile at a tree and forest level,the results are also good.展开更多
Comparison and validation of canopy reflectance(CR)models are two important steps to ensure their reliability.Pure forest plantations are an ideal type of forest for validating CR models because of their simple backgr...Comparison and validation of canopy reflectance(CR)models are two important steps to ensure their reliability.Pure forest plantations are an ideal type of forest for validating CR models because of their simple background and the low variance in the crown structures which are usually assumed to be identical in most CR models.A Geometric Optical Model for Forest Plantations(GOFP)was compared using dataset in two radiation transfer model intercomparison exercise(RAMI)stands and validated using in situ dataset of detailed optical and structural data of two forest plantations in the Saihanba Forestry Center,China.The results show that(1)the tree distributions in stands described by the hypergeometric model in GOFP show good consistencies with the dataset in the two RAMI stands and measurements from the two Saihanba forest stands;and(2)the CRs simulated with GOFP are also compared well in the two RAMI stands and validated with measurements collected with unmanned aerial vehicles in the two Saihanba stands.GOFP shows a better consistency with the CR measurements than those from CR models for natual forestsbecause the tree distribution in forest plantations is described more reasonably in GOFP.展开更多
基金We thank Dr Qin Wenhan in SSAI/GSFC,NASA,USA for his directions and help in modeling RGMThis research was supported in part by the National Natural Science Foundation of China(No40371078,40571107)Special Funds for Major State Basic Research Project(G20000779)
文摘目的提出一种结合C/S(Client/Server)架构和BRF(Boosted random ferns)算法的移动增强现实应用方案,以保证图像识别算法对于产品外包装的识别性能。方法 BRF是一种高效、鲁棒的特征匹配算法,但由于手机内存及处理器等硬件条件的制约,不能直接适用于手机终端。将C/S模式与BRF算法相结合应用于图像特征匹配,并设计实验测试比较文中方案(CS-BRF)与ORB算法的识别速度和匹配精度。结果实验结果表明,相比ORB算法,CS-BRF在识别速度相近的前提下,具有更为优异的识别精度。结论 CS-BRF能够实时准确识别印刷品图像,良好适用于产品包装移动增强现实系统。
基金Under the auspices the Fundamental Research Funds for the Central Universities,China(No.2017TD-26)the Plan for Changbai Mountain Scholars of Jilin Province,China(No.JJLZ[2015]54)
文摘The Multi-angle imaging spectroradiometer(MISR) land-surface(LS) bidirectional reflectance factor(BRF) product(MILS_BRF) has unique semi-simultaneous multi-angle sampling and global coverage. However, unlike on-satellite observations, the spatio-temporal characteristics of MILS_BRF data have rarely been explicitly and comprehensively analysed. Results from 5-yr(2011–2015) of MILS_BRF dataset from a typical region in central Northeast Asia as the study area showed that the monthly area coverage as well as MILS_BRF data quantity varies significantly, from the highest in October(99.05%) through median in June/July(78.09%/75.21%) to lowest in January(18.97%), and a large data-vacant area exists in the study area during four consecutive winter months(December through March). The data-vacant area is mainly composed of crop lands and cropland/natural vegetation mosaic. The amount of data within the principal plane(PP)±30°(nPP) or cross PP ±30°(nCP), varies intra-annually with significant differences from different view zeniths or forward/backward scattering directions. For example, multiple off-nadir cameras have nPP but no nCP data for up to six months(September through February), with the opposite occurring in June and July. This study provides explicit and comprehensive information about the spatio-temporal characteristics of product coverage and observation geometry of MILS_BRF in the study area. Results provide required user reference information for MILS_BRF to evaluate performance of BRDF models or to compare with other satellite-derived BRF or albedo products. Comparing this final product to on-satellite observations, what was found here reveals a new perspective on product spatial coverage and observation geometry for multi-angle remote sensing.
基金the Chinese National Natural Science Foundation Project(40701124)the Chinese Hi-tech Research and Development Program Project(2006AA12Z114)
文摘It is difficulties for the computer simulation method to study radiation regime at large-scale.Simplified coniferous model was investigated in the present study.It makes the computer simulation methods such as L-systems and radiosity-graphics combined method(RGM) more powerful in remote sensing of heterogeneous coniferous forests over a large-scale region.L-systems is applied to render 3-D coniferous forest scenarios,and RGM model was used to calculate BRF(bidirectional reflectance factor) in visible and near-infrared regions.Results in this study show that in most cases both agreed well.Meanwhile at a tree and forest level,the results are also good.
基金funded by the National Natural Science Foundation of China(grant no.41701383,42071392,and 41801234)Anhui Provincial Natural Science Foundation(grant no.1808085QD105)+1 种基金the Fundamental Research Funds for the Central Universities of China(grant no.PA2020GDSK0083)the Fund of Key Laboratory of Information Perception and Systems forPublic Security of MIIT(Nanjing University of Science and Technology)(grant no.202003).
文摘Comparison and validation of canopy reflectance(CR)models are two important steps to ensure their reliability.Pure forest plantations are an ideal type of forest for validating CR models because of their simple background and the low variance in the crown structures which are usually assumed to be identical in most CR models.A Geometric Optical Model for Forest Plantations(GOFP)was compared using dataset in two radiation transfer model intercomparison exercise(RAMI)stands and validated using in situ dataset of detailed optical and structural data of two forest plantations in the Saihanba Forestry Center,China.The results show that(1)the tree distributions in stands described by the hypergeometric model in GOFP show good consistencies with the dataset in the two RAMI stands and measurements from the two Saihanba forest stands;and(2)the CRs simulated with GOFP are also compared well in the two RAMI stands and validated with measurements collected with unmanned aerial vehicles in the two Saihanba stands.GOFP shows a better consistency with the CR measurements than those from CR models for natual forestsbecause the tree distribution in forest plantations is described more reasonably in GOFP.
