1.'min_contrast' 最小对比度
Sets the minimum contrast of the object in the search images for the shape model ModelID. Thereby, the value of 'min_contrast' that was originally set, e.g. with create_shape_model, is overwritten for the shape model ModelID. Note that if the shape model ModelID was read from file and if this file should be changed as well, the shape model ModelID must again be written to file after the execution of the operator set_shape_model_param.
设置形状模型 ModelID 的搜索图像中对象的最小对比度。因此,最初设置的“min_contrast”值(例如,使用 create_shape_model)将被覆盖形状模型 ModelID。请注意,如果从文件中读取了形状模型 ModelID,并且还应更改此文件,则在执行运算符set_shape_model_param后,必须再次将形状模型 ModelID 写入文件。
2.'timeout' 超时时间/最大搜索时间(单位ms)
Sets the maximum runtime of the operators used to find the shape model ModelID (e.g. find_shape_model). This is especially useful in cases where a maximum cycle time has to be ensured. The 'timeout' must be given in milliseconds. The temporal accuracy depends on several factors including the size of the model, the speed of your computer, and the 'timer_mode' set via set_system. Be aware that the runtime of the search increases by up to 10 percent with activated timeout. To disable the timeout you can either use a negative value or 'false'.
设置用于查找形状模型 ModelID 的运算符的最大运行时间(例如 find_shape_model)。这在必须确保最大循环时间的情况下特别有用。“超时”必须以毫秒为单位。时间精度取决于几个因素,包括模型的大小、计算机的速度以及通过set_system设置的“timer_mode”。请注意,随着激活的超时,搜索的运行时间最多会增加 10%。要禁用超时,您可以使用负值或“false”。
3.'border_shape_models' 是否允许搜索图像以外区域(可取值true/false/system)
This parameter determines whether the shape model ModelID to be found with, e.g., find_shape_model, may lie partially outside the image (i.e., whether they may cross the image border). The value of 'border_shape_models' can be 'true', 'false', or 'system'. The value 'system' is the default behavior and uses the system-wide used value that was set by set_system for the parameter 'border_shape_models'.
该参数确定要找到的形状模型 ModelID(例如,find_shape_model)是否可能部分位于图像之外(即,它们是否可以越过图像边界)。
“border_shape_models”的值可以是“true”、“false”或“system”。
值“system”是默认行为,并使用set_system为参数“border_shape_models”设置的系统范围使用的值。
4.'use_clutter' 是否启用杂波参数
Disables or enables the use of clutter parameters for the shape model ModelID, which have been set previously using set_shape_model_clutter. The value of 'use_clutter' can be 'true' or 'false'. Note that the value of 'use_clutter' affects the expected number of entries in the input parameter MinScore of the find operators. Please refer to the documentation of the different find operators, e.g., find_shape_model.
For newly created shape models, the use of clutter parameters is disabled. After calling set_shape_model_clutter, the use of clutter parameters is enabled. Clutter parameters and the value of 'use_clutter' can be queried using get_shape_model_clutter.
禁用或启用形状模型 ModelID 的杂波参数,这些参数之前已使用 set_shape_model_clutter 进行设置。“use_clutter”的值可以是“true”或“false”。请注意,“use_clutter”的值会影响查找运算符的输入参数 MinScore 中的预期条目数。请参阅不同查找运算符的文档,例如 find_shape_model。
对于新创建的形状模型,将禁用杂波参数的使用。调用 set_shape_model_clutter 后,将启用待筛选参数的使用。可以使用get_shape_model_clutter查询待筛选邮件参数和“use_clutter”的值。
5.'model_cache' 是否启用内部缓存(默认情况下设置为true,嵌入式情况下,一般设置缓存状态为关闭,相应的搜索时间会加长)
Disables or enables the use of an internal cache based on temporary memory that is used by a shape model when it executes, e.g., find_shape_model. The size of the cache depends on whether the find operation needs a big search space with many discretization steps. This means that a small AngleStep and ScaleStep and a big AngleExtent and a big range given by ScaleMin and ScaleMax result in a big memory consumption. Switching the 'model_cache' off (by setting 'false') sometimes results in slightly longer execution times but constantly small memory footprint, particularly important in embedded applications. By default, this cache is switched on ('true').
禁用或启用基于临时内存的内部缓存,该内存在形状模型执行时使用,例如find_shape_model。缓存的大小取决于查找操作是否需要具有许多离散化步骤的大搜索空间。这意味着,较小的 AngleStep 和 ScaleStep 以及较大的 AngleExtent 以及 ScaleMin 和 ScaleMax 给出的大范围会导致大量内存消耗。关闭“model_cache”(通过设置“false”)有时会导致执行时间稍长,但内存占用量始终较小,这在嵌入式应用中尤为重要。默认情况下,此缓存处于打开状态 ('true')。
标签:set,param,shape,clutter,model,find,ModelID From: https://www.cnblogs.com/echo-efun/p/18071025