[Objective] The aim was to explore effects of occurrence frequency of freezing injury on rapeseed production and remedial measures. [Method] The re- search utilized three turns of freezing injury during the growth per...[Objective] The aim was to explore effects of occurrence frequency of freezing injury on rapeseed production and remedial measures. [Method] The re- search utilized three turns of freezing injury during the growth period of winter-sown rapeseed in 2013, analyzed the freezing injury resistibility and the remedial mea- sures of ten varieties（combination）. [Result] The results showed that for different va- rieties （combinations） of rapeseed, compared cutting ones with non-cutting ones, the plant silique, seeds number and seed weight increased in diverse level, ＂however, the plant yield remained the same. Correlation analysis suggested that freezing in- jury had the greatest impact on plant silique. [Conclusion] After cutting processing, yield traits were able to partially recover and showed kind of positive correlation with Plant yield.展开更多
Lidar （light detection and ranging） is a relatively new technology that is being used in many aspects of geology and engineering, including researching the potential for rock falls on highway rock cuts. At Missouri ...Lidar （light detection and ranging） is a relatively new technology that is being used in many aspects of geology and engineering, including researching the potential for rock falls on highway rock cuts. At Missouri University of Science and Technology, we are developing methods for measuring joint orientations remotely and quantifying the raveling process. Measuring joint orientations remotely along highways is safer, more accurate and can result in larger and more accurate data sets, including measurements from otherwise inaccessible areas. Measuring the nature of rock raveling will provide the data needed to begin the process of modeling the rock raveling process. In both cases, terrestrial lidar scanning is used to generate large point clouds of coordinate triplets representing the surface of the rock cut. Automated algorithms have been developed to organize the lidar data, register successive images without survey control, and removal of vegetation and non-rock artifacts. In the first case, we look for planar elements, identify the plane and calculate the orientations. In the second case, we take a series of scans over time and use sophisticated change detection algorithms to calculate the numbers and volumes of rock that has fallen off the rock face.展开更多
Existing water hazard detection methods usually fail when the features of water surfaces are greatly changed by the surroundings, e.g., by a change in illumination. This paper proposes a novel algorithm to robustly de...Existing water hazard detection methods usually fail when the features of water surfaces are greatly changed by the surroundings, e.g., by a change in illumination. This paper proposes a novel algorithm to robustly detect different kinds of water hazards for autonomous navigation. Our algorithm combines traditional machine learning and image segmentation and uses only digital cameras, which are usually affordable, as the visual sensors. Active learning is used for automatically dealing with problems caused by the selection, labeling and classification of large numbers of training sets. Mean-shift based image segmentation is used to refine the final classification. Our experimental results show that our new algorithm can accurately detect not only ‘common’ water hazards, which usually have the features of both high brightness and low texture, but also ‘special’ water hazards that may have lots of ripples or low brightness.展开更多
基金Supported by Rapeseed Industry System Construction of Yunnan Agricultural Department~~
文摘[Objective] The aim was to explore effects of occurrence frequency of freezing injury on rapeseed production and remedial measures. [Method] The re- search utilized three turns of freezing injury during the growth period of winter-sown rapeseed in 2013, analyzed the freezing injury resistibility and the remedial mea- sures of ten varieties（combination）. [Result] The results showed that for different va- rieties （combinations） of rapeseed, compared cutting ones with non-cutting ones, the plant silique, seeds number and seed weight increased in diverse level, ＂however, the plant yield remained the same. Correlation analysis suggested that freezing in- jury had the greatest impact on plant silique. [Conclusion] After cutting processing, yield traits were able to partially recover and showed kind of positive correlation with Plant yield.
文摘Lidar （light detection and ranging） is a relatively new technology that is being used in many aspects of geology and engineering, including researching the potential for rock falls on highway rock cuts. At Missouri University of Science and Technology, we are developing methods for measuring joint orientations remotely and quantifying the raveling process. Measuring joint orientations remotely along highways is safer, more accurate and can result in larger and more accurate data sets, including measurements from otherwise inaccessible areas. Measuring the nature of rock raveling will provide the data needed to begin the process of modeling the rock raveling process. In both cases, terrestrial lidar scanning is used to generate large point clouds of coordinate triplets representing the surface of the rock cut. Automated algorithms have been developed to organize the lidar data, register successive images without survey control, and removal of vegetation and non-rock artifacts. In the first case, we look for planar elements, identify the plane and calculate the orientations. In the second case, we take a series of scans over time and use sophisticated change detection algorithms to calculate the numbers and volumes of rock that has fallen off the rock face.
基金Project supported by the National Natural Science Foundation of China (Nos. 60505017 and 60534070)the Natural Science Foundation of Zhejiang Province, China (No. 2005C14008)
文摘Existing water hazard detection methods usually fail when the features of water surfaces are greatly changed by the surroundings, e.g., by a change in illumination. This paper proposes a novel algorithm to robustly detect different kinds of water hazards for autonomous navigation. Our algorithm combines traditional machine learning and image segmentation and uses only digital cameras, which are usually affordable, as the visual sensors. Active learning is used for automatically dealing with problems caused by the selection, labeling and classification of large numbers of training sets. Mean-shift based image segmentation is used to refine the final classification. Our experimental results show that our new algorithm can accurately detect not only ‘common’ water hazards, which usually have the features of both high brightness and low texture, but also ‘special’ water hazards that may have lots of ripples or low brightness.
