ReconstructAT - Aerotriangulation

Overview

The ReconstructAT interface is used to perform aerotriangulation (Aerotriangulation) and is the preferred interface for professional users who need fine control. This interface provides detailed parameter settings and supports advanced features such as camera grouping, POS import, and control point import.

Applicable Scenarios

• Need fine control of aerotriangulation parameters
• Need to check and optimize aerotriangulation results
• Multi-camera system reconstruction
• Need to integrate control points

Interface Invocation

Command Line Invocation

reconstruct_full_engine(.exe) -reconstruct_type 1 -task_json config_task.json

Parameter Description

• reconstruct_type: Fixed as 1 (represents ReconstructAT)
• task_json: Parameter file path

Parameter Details

Required Parameters

Parameter Name	Type	Description
working_dir	string	Working directory, saves intermediate files and final results
gdal_folder	string	GDAL data path (SDK external data folder)
coordinate_system	JSON	Coordinate system of input image positions
camera_meta_data	JSON Array	Camera metadata information, format see camera_meta_data
image_meta_data	JSON Array	Input image metadata information, format see image_meta_data

Optional Parameters

Parameter Name	Type	Default Value	Description
input_image_type	int	1	Image type: 1=RGB, 2=Multispectral, 3=Infrared

Data Structure Description

coordinate_system Object

Field Name	Type	Description	Example Value
type	int	Coordinate system type: 0=LocalENU, 1=Local, 2=Geographic, 3=Projected, 4=ECEF	2
type_name	string	Coordinate system type name (optional, auxiliary description)	"Geographic"
label	string	Coordinate system name (optional)	"WGS 84"
epsg_code	int	EPSG code (required for geographic/projected/geocentric coordinate systems)	4326
wkt	string	WKT string (optional, alternative to epsg_code)	"..."
origin_point	array[3]	Origin WGS84 coordinates [longitude, latitude, elevation] (required only when type=0 LocalENU)	[114.12, 22.12, 0]
offset	array[3]	Coordinate system origin offset (optional)	[0, 0, 0]

Camera Metadata

Field Name	Type	Required	Description
id	int	Yes	Camera unique ID
meta_data	object	Yes	Camera metadata, see table below for details

meta_data Sub-field Description:

Field Name	Type	Required	Description
projection_model	int	Yes	Lens model: 0-perspective lens (k1,k2,k3,p1,p2); 1-fisheye lens (k1,k2,k3,k4)
camera_name	string	Yes	Camera name
width	int	Yes	Sensor width (pixels)
height	int	Yes	Sensor height (pixels)
parameters	array	No	Camera internal parameter group (perspective camera order: fx, fy, cx, cy, k1, k2, k3, p1, p2; fisheye camera order: fx fy cx cy k1 k2 k3 k4)
constant_parameters	array	No	Array of parameter indices to fix camera internal parameters during AT solution, specified according to the parameter order in parameters (index starts from 0), e.g., for perspective camera, specifying [0,1,2,3,4,5,6,7,8] means fixing all parameters

普通镜头
"camera_meta_data": [
  {
    "id": 1,
    "meta_data": {
      "projection_model": 0,
      "camera_name": "common",
      "width": 5280,
      "height": 3956,
      "parameters": [
        3713.29,
        3713.29,
        2647.02,
        1969.28,
        -0.11257524,
        0.01487443,
        -0.00008572,
        1e-7,
        -0.02706411
      ]
    }
  }
]
Fisheye Lens
"camera_meta_data": [
  {
    "id": 1,
    "meta_data": {
      "camera_name": "fisheye",
      "projection_model": 1,
      "width": 3600,
      "height": 3600,
      "parameters": [
        982.7593599212141,
        982.7593599212141,
        1747.6373897301492,
        1806.4116030074354,
        0.03702410479839055,
        -0.016007338300982825,
        -1.0884582901480562e-05,
        -9.773097281093723e-05
      ]
    }
  }
]

Image Metadata

Field Name	Type	Required	Description
id	int	Yes	Image unique ID
path	string	Yes	Image absolute path
meta_data	object	Yes	Image metadata, see table below for details

[Important] Calling ReconstructAT must specify the meta_data field

meta_data Sub-field Description:

Field Name	Type	Required	Description
width	int	Yes	Image width (pixels)
height	int	Yes	Image height (pixels)
camera_id	int	Yes	Corresponding camera ID
focal_length_in_35mm	double	No	35mm equivalent focal length (millimeters)
pos	array[3]	No	POS position [longitude/X, latitude/Y, elevation/Z], must be specified for true-scale reconstruction
pos_sigma	array[3]	No	POS position accuracy (meters), RTK positioning: [0.03,0.03,0.06], regular GPS positioning: [2.0,2.0,5.0]. If RTK positioning data is used, it is strongly recommended to select RTK weight for highest accuracy
orientation	array[9]	No	3x3 rotation matrix (9 values, row-major order, unit vectors, rotation matrix from world coordinate system to camera coordinate system)
position_constant	bool	No	Whether to fix position (true/false), fixing position means AT will not optimize and change the image position, keeping the input value
relative_altitude	double	No	Relative flight altitude (meters)
pre_calib_param	array	No	Pre-calibration parameters (if available, fill in camera internal parameters)
dewarp_flag	bool	No	Distortion correction flag (if from DJI XMP data, true means already distortion-corrected)
mask_path	string	No	Semantic segmentation map, format tif or png, label meanings see below

Semantic Label Meanings

Label Value	Label Meaning
0	Background
1	Water
2	Building
3	Vegetation
4	Road
5	Vehicle
6	Bare ground
7	Hard ground
33	Moving object
34	Sky
35	Power line
255	Invalid area

Typical Use Cases for Semantic Maps:

• (1) Pass the path of a Mask image marked with invalid areas, and the SDK will ignore invalid areas during feature extraction, dense point cloud computation, and texture mapping, improving efficiency and obtaining cleaner point cloud/mesh data
• (2) Pass the path of a Mask image marked with water areas, and the SDK will automatically repair water areas.

{
  "id": 1,                    // Image unique ID
  "path": "path/to/image.jpg", // Image absolute path
  "group": "camera_1",        // Camera group ID (optional)
  "meta_data": {              // Image information (required)
    "width": 6000,           // Image width (pixels)
    "height": 4000,          // Image height (pixels)
    "camera_id": 1,          // Corresponding camera ID (optional, if 'pre_calib_param' is provided, it will be overridden by camera metadata)
    "pos": [lon, lat, alt],  // Position [longitude, latitude, elevation]
    "pos_sigma": [1.0, 1.0, 2.0], // Position accuracy (meters)
    "orientation": [...],     // Rotation matrix (9 values, optional)
    "position_constant": false, // Whether to fix position
    "relative_altitude": 100.0, // Relative flight altitude (optional)
    "focal_length_in_35mm": 24, // 35mm equivalent focal length
    "pre_calib_param": [...],   // Pre-calibration parameters (optional, if 'focal_length_in_35mm' is provided, it will be overridden)
    "dewarp_flag": false        // Distortion correction flag (optional, from DJI XMP data)
  }
}

Complete Configuration Examples

Basic Aerotriangulation Configuration

{
  "working_dir": "C:/Projects/AT_Task",
  "gdal_folder": "C:/MipMap/SDK/data",
  "coordinate_system": {
    "type": 2,
    "epsg_code": 4326
  },
  "camera_meta_data": [
    {
      "id": 1,
      "meta_data": {
        "camera_name": "DJI FC6310",
        "width": 5472,
        "height": 3648
      }
    }
  ],
  "image_meta_data": [
    {
      "id": 1,
      "path": "C:/Images/DJI_0001.JPG",
      "meta_data": {
        "width": 5472,
        "height": 3648,
        "camera_id": 1,
        "pos": [114.123456, 22.123456, 100.5],
        "pos_sigma": [0.03,0.03,0.06]
      }
    },
    {
      "id": 2,
      "path": "C:/Images/DJI_0002.JPG",
      "meta_data": {
        "width": 5472,
        "height": 3648,
        "camera_id": 1,
        "pos": [114.123556, 22.123456, 100.8],
        "pos_sigma": [0.03,0.03,0.06]
      }
    }
  ]
}

Multi-Camera Group Configuration

{
  "working_dir": "C:/Projects/MultiCamera_AT",
  "gdal_folder": "C:/MipMap/SDK/data",
  "coordinate_system": {
    "type": 2,
    "epsg_code": 4326
  },
  "camera_meta_data": [
    {
      "id": 1,
      "meta_data": {
        "camera_name": "Camera_Nadir",
        "width": 6000,
        "height": 4000
      }
    },
    {
      "id": 2,
      "meta_data": {
        "camera_name": "Camera_Oblique",
        "width": 6000,
        "height": 4000
      }
    }
  ],
  "image_meta_data": [
    {
      "id": 1,
      "path": "nadir/IMG_0001.JPG",
      "group": "nadir",
      "meta_data": {
        "width": 6000,
        "height": 4000,
        "camera_id": 1,
        "pos": [114.123456, 22.123456, 200.0],
        "pos_sigma": [2.0, 2.0, 5.0]
      }
    },
    {
      "id": 2,
      "path": "oblique/IMG_0001.JPG",
      "group": "oblique_forward",
      "meta_data": {
        "width": 6000,
        "height": 4000,
        "camera_id": 2,
        "pos": [114.123456, 22.123456, 200.0],
        "pos_sigma": [2.0, 2.0, 5.0]
      }
    }
  ]
}

Error Handling

The interface returns an integer error code:

• 0: Success
• Non-zero: Various error conditions

For details, see Error Codes.

Next Steps

• Use Reconstruct3D for 3D reconstruction
• Use OptimizeAT to optimize aerotriangulation results with control points

---

Tip: ReconstructAT provides maximum flexibility but also requires more parameter settings. If you only need quick reconstruction, it is recommended to use ReconstructFull.