Method for detecting dimension of box based on depth map

1. A method for detecting dimension of box based on depth map, comprising:

receiving a depth map generated by a camera, wherein the depth map corresponds to pixels of an image including a box;

performing a coordinate transformation to transform the depth map into camera coordinates of each of the pixels;

dividing some of the pixels into plural blocks, wherein each of blocks comprises a number of the pixels adjacent to each other;

statistically analyzing an average normal vector of each of the blocks according to the camera coordinates of the pixels of each of the blocks;

classifying the blocks into plural clusters according to the average normal vector of each of the blocks;

performing a plane extraction to obtain edge vectors according to plane formulas of the clusters;

obtaining vertexes of the box according to the edge vectors; and

obtaining a dimension of the box according the vertexes.

2. The method of claim 1 , further comprising:

performing a noise removal process on the depth map before performing the coordinate transformation.

3. The method of claim 1 , wherein the coordinate transformation is performed by using intrinsic parameters built in the camera.

4. The method of claim 1 , wherein each of some of the pixels to be divided is the pixel with valid depth value.

5. The method of claim 1 , wherein the average normal vector of one of the blocks is an average of normal vectors of plural defined planes, wherein each of the defined planes is composed by three of the pixels of the one of the blocks.

6. The method of claim 1 , further comprising:

performing a block outlier removal on the blocks before performing the plane extraction, wherein the block outlier removal is configured to remove the blocks located nearby edges of the box.

7. The method of claim 1 , wherein the plane extraction is performed to obtain at least three surfaces of the box, wherein the edge vectors are computed by the obtained surfaces.

8. The method of claim 1 ,

wherein the vertexes comprise a first vertex, a second vertex, a third vertex, and a fourth vertex;

wherein the second vertex is the vertex closest to the camera.

9. The method of claim 8 , wherein the second vertex is obtained by computing an intersection point of the edge vectors.

10. The method of claim 8 , wherein one of the first vertex, the third vertex, and the fourth vertex is obtained by, starting from the second vertex toward along one of edges of the box, scanning a shortest distance between the pixels and the one of the edges of the box.