跳转到内容
STAGING SERVER
DEVELOPMENT SERVER

Depth Control#

The Depth Control feature allows you to control how the Stereo ace camera calculates the depth in images.

For details how the depth is calculated from the disparity image, see Processing Measurement Results.

Depth Parameters#

Depth Resolution#

Depth Resolution allows you to specify the resolution of the disparity images. Lower resolutions reduce the processing load and can increase the achievable frame rate.

Disparity means the displacement of an object point between the images of the right and of the left camera of the Stereo ace. The larger the disparity, the closer the object is to the camera.

The following resolutions are available:

  • Full: 5 MP
  • High: 1.3 MP
  • Low: 0.3 MP

To specify the depth resolution:

  1. 设置 BslDepthResolution parameter to the desired resolution.

Intensity Resolution#

Intensity Resolution allows you to specify the resolution of the intensity images provided by the producer.

The following resolutions are available:

  • Full: 5 MP
  • High: 1.3 MP
  • Low: 0.3 MP

To specify the intensity resolution:

  1. 设置 BslIntensityResolution parameter to the desired resolution.

The producer derives a suitable internal combination of camera binning, the legacy BslDepthQuality setting, and host-side 2D scaling from the BslDepthResolution and BslIntensityResolution values selected.

Fill#

This parameter allows you to fill holes in the disparity image by means of interpolation. The fill-in value is the maximum allowed difference in disparity on the border of the hole. Larger fill-in values can decrease the number of holes but the interpolated values may have larger errors. At most, 5 % of pixels are interpolated. Interpolation of small holes is preferable to interpolation of larger holes. The confidence for the interpolated pixels is set to a low value of 0.5. A fill-in value of 0 switches hole filling off.

To specify the fill-in value:

  1. 设置 BslDepthFill parameter to the desired value (0 to 4).

Segmentation#

This parameter allows you to specify the minimum number of pixels that a connected disparity region in the disparity image must contain. Isolated regions that are smaller are set to invalid in the disparity image. The value is related to the High Depth Resolution setting. You don't have to adjust it when you select a different depth resolution. Segmentation is useful for removing false disparity measurements. However, larger values may also cause real objects to be removed.

To specify the segmentation value:

  1. 设置 BslDepthSeg parameter to the desired value (0 to 4000).

Minimum Confidence#

You can specify a minimum confidence value to filter out potentially false disparity measurements. All pixels with a confidence lower than the value specified are set to invalid in the disparity image.

To specify the minimum confidence:

  1. 设置 BslDepthMinConf parameter to the desired value (0.0 to 1.0).

Minimum Depth#

The minimum depth is the shortest distance from the camera at which you want to start measuring. Higher values implicitly reduce the disparity range, which in turn reduces the computation time. The minimum distance is specified in meters.

To specify the minimum depth:

  1. 设置 BslDepthMinDepth parameter to the desired value (0.1 to 100.0).

Maximum Depth#

The maximum distance is the longest distance from the camera at which you want to stop measuring. Pixels with higher distance values are set to invalid in the disparity image. Maximum depth values at the end of the allowed range mean that, theoretically, the camera is measuring up to infinity. At such distances, however, it becomes difficult to distinguish whether an object point is 100 meters or 200 meters away. As a result, the measurements will be less reliable. The maximum distance is specified in meters.

To specify the maximum depth:

  1. 设置 BslDepthMaxDepth parameter to the desired value (0.1 to 100.0).

Maximum Depth Error#

This parameter allows you to filter out measurements that are too inaccurate. All pixels with a depth error larger than the value specified are set to invalid in the disparity image. The maximum depth error is specified in meters. The depth error generally grows quadratically with an object's distance from the camera.

To specify the maximum depth error:

  1. 设置 BslDepthMaxDepthErr parameter to the desired value (0.01 to 100.0).

Smoothing#

This option enables advanced smoothing of disparity values.

To enable or disable smoothing:

  1. 设置 BslDepthSmooth parameter to On 或 Off.

Static Scene#

This parameter averages 8 consecutive camera images before matching. This reduces noise, which in turn improves the stereo matching result. However, the latency increases significantly. The timestamp of the first image is used as the timestamp of the disparity image. This option only affects matching in Full 或 High depth resolution. It must only be enabled if the scene does not change during the acquisition of the 8 images.

To enable or disable static scene mode:

  1. 设置 BslDepthStaticScene parameter to On 或 Off.

Double Shot#

Enabling this parameter produces denser disparity images but increases processing time.

For scenes recorded in continuous acquisition mode with the projector in AlternateActive mode, holes caused by reflections of the projector are filled with depth information computed from the images without projector pattern. In AlternateActive mode, the Double Shot parameter must only be enabled if the scene does not change during image acquisition.

In AlwaysActive mode, enabling this parameter is fine. Holes are filled with depth information computed from a downscaled version of the same image.

To enable or disable double shot mode:

  1. 设置 BslDepthDoubleShot parameter to On 或 Off.

Exposure Adaptation Timeout#

Maximum time to wait after triggering until auto exposure has finished adjustments.