acldvppVpcBatchCropAndPasteAsync

Atlas 200/300/500 Inference Product

Atlas Training Series Product

• Input image resolution and format:
  • When the input image resolution is in the range of [10 × 6, 4096 × 4096], the input image formats described in Restrictions on Image Formats, Width and Height Alignment, and Buffers are supported.
  • When the width or height of the input image is within the range of (4096, 8192], the supported formats are as follows:
    The following enum values of acldvppPixelFormat are supported:

    PIXEL_FORMAT_YUV_SEMIPLANAR_420 = 1,       // YUV420SP NV12 8bit   
    PIXEL_FORMAT_YVU_SEMIPLANAR_420 = 2,       // YUV420SP NV21 8bit 

• For details about the output image resolution and format, see Restrictions on Image Formats, Width and Height Alignment, and Buffers.
• For details about the restrictions on the width and height alignment, buffer size, and image format, see Restrictions on Image Formats, Width and Height Alignment, and Buffers.
• A cropped image will be resized again if pasteArea and cropArea have different sizes. The high-order filtering algorithm developed by Huawei is used by default.

channelDesc

Input

Pointer to the channel description.

Must be the same as the channelDesc argument passed to the acldvppCreateChannel call.

srcBatchPicDescs

Input

Pointer to the description of batch input images.

• Call acldvppCreateBatchPicDesc to create an image description.
• Call acldvppGetPicDesc to obtain the description of a specified image.
• Call acldvppSetPicDesc series to set the image description (including the buffer address, buffer size, image format, and image resolution).

roiNums

Input

Pointer to the number of crop ROIs of each input image. The maximum number of crop ROIs is 256.

roiNums is an array. The sum of the elements is up to 256, which must be consistent with batchSize in the dstBatchPicDescs struct.

roiNums[0]+...+roiNums[size-1] <= 256

size

Input

Length of the roiNums array, up to 256.

dstBatchPicDescs

Input/Output

Pointer to the description of batch output images.

When dstBatchPicDescs is used as an input, the user needs to:

• Call acldvppCreateBatchPicDesc to create an image description.
• Call acldvppGetPicDesc to obtain the description of a specified image.
• Call acldvppSetPicDesc series to set the image description (including the buffer address, buffer size, image format, and image resolution).

cropAreas

Input

Pointer array for the crop ROIs.

• Call acldvppCreateRoiConfig to create an ROI configuration.
• The cropAreas or pasteAreas array length is the same as the value of batchSize in the dstBatchPicDescs struct.

pasteAreas

Input

Pointer array for the paste ROIs.

• Call acldvppCreateRoiConfig to create an ROI configuration.
• Round up the left offset of each paste ROI to the nearest multiple of 16.
• The cropAreas or pasteAreas array length is the same as the value of batchSize in the dstBatchPicDescs struct.

stream

Input

Stream.