Displays the dataset containing the image used for generating ground control points. It is not editable.

Selects the ground control point distribution mode. Two methods are provided: Conventional and Uniform. The default is Conventional.

• Conventional: Divides each scene into N*M sub-regions, and then selects n image blocks of size 512*512 from each sub-region for control point generation. The generated ground control points will try to cover the entire image as much as possible.
• Uniform: The generated ground control points will be evenly distributed across each scene image. The number of points is fewer than that of regular distribution, but the distribution is more uniform, which is suitable for situations where the internal distortion of the image is significant.

Available after selecting Conventional in Point Distribution Mode.

The number of blocks into which each scene image is divided in the column direction. The default value is 4.

Available after selecting Conventional in Point Distribution Mode.

The number of blocks into which each scene image is divided in the row direction. The default value is 4.

Available after selecting Conventional in Point Distribution Mode.

Provides the following six matching methods to choose from based on data characteristics and requirements. Among them, the AFHORP and RIFT methods support multi-modal data matching; CASP and DEEPFT are based on deep learning and require additional AI model configuration and CUDA environment installation. Generally, MOTIF, CASP, or DEEPFT are recommended.

• MOTIF (Default): A template matching algorithm for multimodal imagery, characterized by its lightweight feature descriptors. MOTIF can overcome nonlinear radiometric distortions caused by differences between SAR and optical images.
• CASP: A novel cascade matching pipeline that benefits from integrating high-level features, helping to reduce the computational cost of low-level feature extraction. This pipeline decomposes the matching stage into two progressive phases. It first establishes one-to-many correspondences at a coarser scale as cascade priors. Then, leveraging these priors for guidance, it determines one-to-one matches at the target scale.^[1]
• DEEPFT: A deep learning-based image matching method.
• SIFT: A method for extracting distinctive invariant features from images, which can be used for reliable matching between objects or scenes under different viewpoints.
• RIFT: A feature matching algorithm robust to large-scale nonlinear radiometric distortions. It enhances the stability of feature detection and overcomes the limitations of feature description based on gradient information.
• AFHORP: A feature matching algorithm for multimodal imagery. AFHORP exhibits strong resistance to radiometric distortions and contrast differences in multimodal images, performing excellently in addressing issues of direction reversal and abrupt phase extremum changes.

Available after selecting Conventional in Point Distribution Mode.

The maximum number of points retained within each image block during image matching. The value range is [1,2048], and the default is 256.

Available after selecting Uniform in Point Distribution Mode.

Sets the number of seed points for conjugate point matching on each scene image. The value range is [64,6400], and the default is 512. When the image texture is poor, it is recommended to increase the number of ground control points to match enough points and improve subsequent imagery quality.

Available after selecting Uniform in Point Distribution Mode.

Sets the method for searching seed points. The default is Raster Center Point.

• Corner Point: Uses points with distinct features within the selected region as seed points.
• Raster Center Point: Uses the center point of the raster as the seed point. This search method is random.

Available after selecting Uniform in Point Distribution Mode.

Sets the interval size between seed points. The value range is [1,256], the default is 40, and the unit is px. A larger template leads to more reliable searched points but longer processing time.

Available after selecting Uniform in Point Distribution Mode.

Sets the search radius for seed points in image matching. The value range is [0,256], the default is 40, and the unit is px. A larger search radius increases the matching range but also increases the processing time.

Available after Semantic Culling of Non-Ground Points is checked.

Checked by default, meaning ground control points within cloud areas will be automatically culled based on the set dataset. If unchecked, ground control points in cloud areas will be retained. The dataset must contain an ImageName field, and the name must correspond to the image currently to be processed.

Displayed after "Cloud Area" is checked. Not editable.

For workflows related to DOM production, use the cloud amount data from Set the Image Path.

For workflows related to DSM production, use the cloud amount data from Set Image Path (dsm/dem).