Techniques are provided for generation of synthetic 3-dimensional object image variations for training of recognition systems. An example system may include an image synthesizing circuit configured to synthesize a 3D image of the object (including color and depth image pairs) based on a 3D model. The system may also include a background scene generator circuit configured to generate a background for each of the rendered image variations. The system may further include an image pose adjustment circuit configured to adjust the orientation and translation of the object for each of the variations. The system may further include an illumination and visual effect adjustment circuit configured to adjust illumination of the object and the background for each of the variations, and to further adjust visual effects of the object and the background for each of the variations based on application of simulated camera parameters.

Techniques are provided for generation of synthetic 3-dimensional object image variations for training of recognition systems. An example system may include an image synthesizing circuit configured to synthesize a 3D image of the object (including color and depth image pairs) based on a 3D model. The system may also include a background scene generator circuit configured to generate a background for each of the rendered image variations. The system may further include an image pose adjustment circuit configured to adjust the orientation and translation of the object for each of the variations. The system may further include an illumination and visual effect adjustment circuit configured to adjust illumination of the object and the background for each of the variations, and to further adjust visual effects of the object and the background for each of the variations based on application of simulated camera parameters.

A client device executes a display layout application that receives a size of each display item included in a set of display items. The set of display items is associated with a first frame included in a bounding box associated with a display screen. The display layout application determines a reference size based on the sizes of the set of display items. The display layout application determines a size of the first frame based on the reference size. The display layout application determines a position for a first display item included in the set of display items based on a position of the first frame within the bounding box. The display layout application generates a layout for display on the display screen, where the layout includes the first display item.

A client device executes a display layout application that receives a size of each display item included in a set of display items. The set of display items is associated with a first frame included in a bounding box associated with a display screen. The display layout application determines a reference size based on the sizes of the set of display items. The display layout application determines a size of the first frame based on the reference size. The display layout application determines a position for a first display item included in the set of display items based on a position of the first frame within the bounding box. The display layout application generates a layout for display on the display screen, where the layout includes the first display item.

Embodiments of the present invention disclose a binocular image matching method, apparatus, device, and storage medium. The method comprises: performing target detection on a first image to obtain a first bounding box of a target in the first image; determining a second bounding box corresponding to the first bounding box in a second image; and obtaining a third bounding box of the target in the second image by regressing the second bounding box. The technical solutions realize accurate matching of targets in a binocular image without requiring performing target detection on both images in the binocular image, and then use a matching algorithm to match the targets detected in the two images, thereby greatly reducing the calculation overhead of target matching in the binocular image.

Embodiments of the present invention disclose a binocular image matching method, apparatus, device, and storage medium. The method comprises: performing target detection on a first image to obtain a first bounding box of a target in the first image; determining a second bounding box corresponding to the first bounding box in a second image; and obtaining a third bounding box of the target in the second image by regressing the second bounding box. The technical solutions realize accurate matching of targets in a binocular image without requiring performing target detection on both images in the binocular image, and then use a matching algorithm to match the targets detected in the two images, thereby greatly reducing the calculation overhead of target matching in the binocular image.

The disclosure provides a calibration system, a calibration method, and a calibration device. The calibration method for obtaining a transformation of coordinate systems between a vision sensor and a depth sensor includes the following steps. (a) A first coordinate group of four endpoints of a calibration board in a world coordinate system is created. (b) An image of the calibration board is obtained by the vision sensor, and a second coordinate group of the four endpoints of the calibration board in a two-dimensional coordinate system is created. (c) A third coordinate group of the four endpoints of the calibration board in a three-dimensional coordinate system is created according to the first and second coordinate groups. (d) The third coordinate group is transformed to a fourth coordinate group corresponding to the depth sensor to obtain the transformation of the coordinate systems according to at least three target scanning spots.

The disclosure provides a calibration system, a calibration method, and a calibration device. The calibration method for obtaining a transformation of coordinate systems between a vision sensor and a depth sensor includes the following steps. (a) A first coordinate group of four endpoints of a calibration board in a world coordinate system is created. (b) An image of the calibration board is obtained by the vision sensor, and a second coordinate group of the four endpoints of the calibration board in a two-dimensional coordinate system is created. (c) A third coordinate group of the four endpoints of the calibration board in a three-dimensional coordinate system is created according to the first and second coordinate groups. (d) The third coordinate group is transformed to a fourth coordinate group corresponding to the depth sensor to obtain the transformation of the coordinate systems according to at least three target scanning spots.

Various systems and methods for selectively expanding a digital canvas are described. A slice line having a begin point and an end point may be defined within the digital canvas. The canvas may then be selectively expanded by moving drawing or other elements that project on slice line in a selected direction.

Various systems and methods for selectively expanding a digital canvas are described. A slice line having a begin point and an end point may be defined within the digital canvas. The canvas may then be selectively expanded by moving drawing or other elements that project on slice line in a selected direction.