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
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.
