CloudSoftwareHardware
Software Stack
DepthAI
OAK Apps
AI Models
Troubleshooting

ON THIS PAGE

  • NeuralDepthConfig
  • Configuration Options
  • Post-Processing
  • Algorithm Control
  • Reference

NeuralDepthConfig

This message is used to configure the NeuralDepth node. With this message you can set post-processing options like confidence threshold, edge threshold, temporal filtering, and used depth units.

Configuration Options

Post-Processing

  • confidenceThreshold: Confidence threshold for disparity calculation. Pixels with confidence above this value are considered valid. Valid range is [0, 255], default is 125.
  • edgeThreshold: Edge threshold for disparity calculation. Pixels with edge magnitude below this value are considered invalid. Valid range is [0, 255], default is 10.
  • temporalFilter: Temporal filtering with optional persistence to reduce noise over time.

Algorithm Control

  • depthUnit: Measurement unit for depth data (e.g., MILLIMETER, CENTIMETER, METER).
  • customDepthUnitMultiplier: Custom depth unit multiplier relative to 1 meter. A multiplier of 1000 means depth unit in millimeters.

Reference

class

dai::NeuralDepthConfig

#include NeuralDepthConfig.hpp
variable
AlgorithmControl algorithmControl
Controls the flow of stereo algorithm - left-right check, subpixel etc.
variable
Filtering postProcessing
Controls the postprocessing of disparity and/or depth map.
function
NeuralDepthConfig()
Construct NeuralDepthConfig message.
function
~NeuralDepthConfig()
function
NeuralDepthConfig & setConfidenceThreshold(uint8_t confThr)
Confidence threshold for disparity calculation
Parameters
  • confThr: Confidence threshold value 0..255
function
uint8_t getConfidenceThreshold()
Get confidence threshold for disparity calculation
function
NeuralDepthConfig & setEdgeThreshold(uint8_t edgeThr)
Set edge threshold for disparity calculation
Parameters
  • edgeThr: Edge threshold value 0..255
function
uint8_t getEdgeThreshold()
Get edge threshold for disparity calculation
function
NeuralDepthConfig & setDepthUnit(AlgorithmControl::DepthUnit depthUnit)
Set depth unit of depth map.
function
AlgorithmControl::DepthUnit getDepthUnit()
Get depth unit of depth map.
function
NeuralDepthConfig & setCustomDepthUnitMultiplier(float multiplier)
Set custom depth unit multiplier relative to 1 meter.
function
float getCustomDepthUnitMultiplier()
Get custom depth unit multiplier relative to 1 meter.
function
void serialize(std::vector< std::uint8_t > & metadata, DatatypeEnum & datatype)
function
struct

dai::NeuralDepthConfig::AlgorithmControl

variable
DepthUnit depthUnit
Measurement unit for depth data. Depth data is integer value, multiple of depth unit.
variable
float customDepthUnitMultiplier
Custom depth unit multiplier, if custom depth unit is enabled, relative to 1 meter. A multiplier of 1000 effectively means depth unit in millimeter.
function
enum

dai::DepthUnit DepthUnit

struct

dai::NeuralDepthConfig::Filtering

variable
uint8_t confidenceThreshold
Confidence threshold for disparity calculation, Confidences above this value will be considered valid. Valid range is [0,255].
variable
uint8_t edgeThreshold
Edge threshold for disparity calculation, Pixels with edge magnitude below this value will be considered invalid. Valid range is [0,255].
function

Need assistance?

Head over to Discussion Forum for technical support or any other questions you might have.