基于捕获速度的设置选择器
本章节将根据您从触发采集到获得点云的时间预算来提供有关最佳相机设置的详细说明。同时,我们还会考虑您的PC规格,因为数据传输和点云处理也取决于此。我们通过优化3D捕获的设置来获得良好的点云,以及通过优化2D捕获的设置来获得良好的彩色图像。
在这之前,您已确定选择哪款Zivid相机用于您的单品拣选应用,并且已正确安装和定位它。下一步是根据您的PC规格选择满足您的周期时间要求的相机设置。如果您还没有准备好PC,本文也介绍了如何结合使用的设置找到满足您的捕获时间要求的PC规格。
3D设置
我们根据场景的复杂性将单品拣选应用分为两类。对于每个类别,我们指定并推荐满足给定成像要求和捕获速度要求的设置。
消费品(Consumer Goods)
如果您的场景不包含非常明亮、反光和深色的物体,您可以选择适用于单品拣选的快速设置(Fast settings)来节省大量的循环时间。快速设置(Fast settings)覆盖了较窄的动态范围,但能够提供更快的捕获。这里有一个适合使用快速设置的场景示例。如您所见,里面没有导致强烈直接反射、高光和饱和度的物体,也没有颜色非常暗的物体。
备注
如果场景中没有明亮、反光和深色的物体,请选择快速设置。
通过消费品的质量设置(Quality settings),相机覆盖了相当宽的动态范围,对各种物体都能提供良好的点云。在这种情况下,场景可以包含从明亮和反光的塑料包装物体和装载塑料袋中的物品到深色吸收材料中的任何物体。下图描绘了一个典型的需要质量设置的复杂消费品场景。
备注
如果您希望确保相机不会丢失任何物体的数据,请选择质量设置(Quality settings)。
设置选择表
下表是一个基于所需捕获时间预算的设置选择器工具。这张表格同时显示了可以满足您的捕获速度要求的 PC 的性能和成本。你可以转到 推荐的工业 PC 来查看高端、中端和低端PC配置的示例。
If you notice color Inconsistency in form of random color tint in your color images, choose the presets for the grid frequency in your region (50 Hz or 60 Hz). If the ambient light is unproblematic, select Off for optimal performance.
应用 |
捕获时间(2D + 3D) |
相机设置 |
||
---|---|---|---|---|
高端电脑 |
中端电脑 |
低端电脑 |
||
消费品(质量/Quality) |
~700 ms |
~900 ms |
~1200 ms |
|
消费品(快速/Fast) |
~180 ms |
~300 ms |
~500 毫秒 |
|
To download the desired settings file, you can also connect to the camera (your specific model) in Zivid Studio, select the preset settings, turn on Ambient Light Adaption, and export the settings.
小心
The capture time with settings adapted for ambient light frequency might be longer.
应用
相机设置
消费品(质量/Quality)
消费品(快速/Fast)
To download the desired settings file, you can also connect to the camera (your specific model) in Zivid Studio, select the preset settings, turn on Ambient Light Adaption, and export the settings.
小心
The capture time with settings adapted for ambient light frequency might be longer.
应用
相机设置
消费品(质量/Quality)
消费品(快速/Fast)
为了证实能够达到上述单品拣选应用的要求,我们在多种不同规格的PC上使用Zivid相机运行基准捕获程序(benchmark capture programs)。下表显示了其结果。
包裹分拣
根据场景复杂性和捕获时间,包裹分拣设置也分为两种设置。
Parcels(包裹) Fast settings are designed to achieve the shortest cycle times. These settings have a limited dynamic range but are good enough for objects that are relatively straightforward for imaging, for example:
纸板箱
白色信封
亮光塑料袋
备注
If you image only boxes, parcels, satchels, etc., choose Parcels Fast settings.
小技巧
Try increasing the exposure time for more data coverage on dark specular objects or switch to Parcels Quality presets.
For more challenging scenes, you should try out Parcels(包裹) Quality settings. These settings have larger dynamic range and are capable of getting good surface coverage on objects such as:
黑色塑料袋
深色塑料袋
深色气泡膜
小技巧
如需减少捕获时间,可以将引擎从 Omni 切换为 Stripe, 但是请注意,这样可能对黑色包裹的成像产生影响。
设置选择表
If you experience color Inconsistency in form of random color tint in your color images or artifacts in the form of ripples/waves across the whole point cloud, choose 50/60 Hz to select presets adapted to the ambient light (grid) frequency. If the ambient light is unproblematic, select Off for optimal performance.
应用 |
捕获时间(2D + 3D) |
相机设置 |
||
---|---|---|---|---|
高端电脑 |
中端电脑 |
低端电脑 |
||
包裹(质量/反光) |
~ 200毫秒 |
~350 毫秒 |
~500 毫秒 |
|
包裹(快速/哑光) |
~100 ms |
~ 200毫秒 |
~300 ms |
|
To download the desired settings file, you can also connect to the camera (your specific model) in Zivid Studio, select the preset settings, turn on Ambient Light Adaption, and export the settings.
小心
The capture time with settings adapted for ambient light frequency might be longer.
应用
相机设置
包裹(质量/反光)
包裹(快速/哑光)
To download the desired settings file, you can also connect to the camera (your specific model) in Zivid Studio, select the preset settings, turn on Ambient Light Adaption, and export the settings.
小心
The capture time with settings adapted for ambient light frequency might be longer.
应用
相机设置
包裹(质量/反光)
包裹(快速/哑光)
为了证明包裹预设设置能够达到上述要求,我们在各种 PC 上使用我们的相机不断运行基准捕获程序。下表显示了其结果。
测试3D设置
You can use Zivid Studio to test 3D settings.
可通过以下操作在Zivid Studio中导入设置:
点击 File → Import Capture Settings
导航到设置文件的位置
点击Open
您还可以将 YML 文件拖放到 Zivid Studio 中以导入设置。
You can also load the settings with the SDK.
const auto settings = Zivid::Settings(settingsFile);
var settings = new Zivid.NET.Settings(settingsFile);
settings = zivid.Settings.load(settings_file)
2D设置
We provide three options for acquiring 2D settings for your Piece Picking application:
Use settings presets
使用Zivid标定板和代码示例来自动获取2D设置
手动调整 2D 设置
The 3D settings presets also include the 2D settings. Therefore, we recommend using the same settings preset for 3D and 2D captures. If this does not provide satisfactory results, check out the following options.
自动 2D 设置
Run the auto_2d_settings.py sample to automatically find the acquisition settings for a 2D capture using a Zivid calibration board. Place the calibration board at either the top or bottom of the bin and run the sample by specifying the calibration board location and the desired focus range (bin height) as command line arguments. If you, for example, place the calibration board at the bin top and the bin height is 400 mm, run the sample as:
python auto_2d_settings.py --desired-focus-range 400 --checkerboard-at-start-of-range --use-projector --no-color-balance
如果将标定板放在料箱底部,请运行:
python auto_2d_settings.py --desired-focus-range 400 --checkerboard-at-end-of-range --use-projector --no-color-balance
手动调整 2D 设置
If 2D settings presets or automatic tuning does not provide sufficient 2D quality, you can manually tune the color settings by adjusting the color balance and gamma parameters. Gamma correction can be used to either darken or brighten the image. The color channel parameters makes the color image look more natural.
有关如何优化颜色的深入教程,请参阅 优化彩色图像 。
测试2D设置
要测试 2D 设置,您可以使用 Zivid Studio 中的 2D 捕获模式或运行我们的代码示例。
可通过以下操作在Zivid Studio中导入设置:
点击 File → Import Capture Settings
导航到设置文件的位置
点击Open
您还可以将 YML 文件拖放到 Zivid Studio 中以导入设置。
Our code sample CaptureWithSettingsFromYml
demonstrates how to load the 2D settings and capture a 2D image.
python capture_2d_with_settings_from_yml.py <path-to-2d-settings.yml>
auto camera = zivid.connectCamera();
const auto settings = Zivid::Settings(settingsFile);
const auto frame2D = camera.capture2D(settings);
var camera = zivid.ConnectCamera();
var settings = new Zivid.NET.Settings(settingsFile);
using (var frame2D = camera.Capture2D(settings))
camera = app.connect_camera()
settings = zivid.Settings.load(settings_file)
with camera.capture_2d(settings) as frame_2d:
After capturing the image can be saved.
const auto imageRGBA = frame.frame2D().value().imageRGBA();
const auto imageFile = "ImageRGB.png";
std::cout << "Saving 2D color image (linear RGB color space) to file: " << imageFile << std::endl;
imageRGBA.save(imageFile);
var imageRGBA = frame.Frame2D.ImageRGBA();
var imageFile = "ImageRGB.png";
Console.WriteLine("Saving 2D color image (linear RGB color space) to file: " + imageFile);
imageRGBA.Save(imageFile);
image_bgra = frame.frame_2d().image_rgba()
image_file = "ImageRGBA.png"
print(f"Saving 2D color image (linear RGB color space) to file: {image_file}")
image_bgra.save(image_file)
备注
我们在低环境光(~300 lx)和高环境光(~1000 lx)条件下测试了我们为上述典型场景推荐的3D和2D设置。我们已经完成了我们在相机选择器章节中指定的距离范围,以及场景中的所有项目的测试。因此,我们相信这些设置将适用于属于这些类别的大多数场景。但是,如果您确切地知道场景中的项目是什么,并且您是专业的相机使用者,则可以手动配置设置以针对您的情况来优化它们。您可以查看 捕获高质量的点云 来了解如何做到这一点。
在下一章节中,我们将介绍如何通过使用多线程来 优化机器人循环时间 。
版本历史
SDK |
变更 |
---|---|
2.12.0 |
Zivid One+ 已达到其生命周期的终点并且不再受支持。 |