Method for data collection and model generation of house

A computer-implemented method for data collection and model generation of a house, comprising:

• employing a processor that facilitates execution of computer executable instructions stored on a non-transitory computer readable medium to implement operations, the operations comprising:
• acquiring collected depth images and pictures of each of at least one functional space of a preset house;
• creating a virtual 3D model of the preset house according to the depth images of the at least one functional space, and generating a panoramic image of each of the at least one functional space according to the pictures of the functional space;
• and
• sending, when request information indicating displaying the preset house is received, the virtual 3D model of the preset house or a panoramic image of a target functional space corresponding to the request information, according to the request information,
• wherein acquiring the collected depth images and the pictures of each of the at least one functional space of the preset house comprises:
• for each of the at least one functional space, photographing the functional space by taking a plurality of photographing spots in the functional space as centers, respectively, to obtain the depth images and the pictures of the functional space;
• wherein photographing the functional space by taking the pluralityof photographing spots in the functional space as the centers, respectively, to obtain the depth images and the pictures of the functional space, comprises:
• predicting a next photographing spot based on a previous photographing spot where photographing has been performed, and photographing the functional space by taking the predicted next photographing spot as a center, to obtain a corresponding depth image and picture;
• wherein predicting the next photographing spot based on the previous photographing spot where photographing has been performed comprises:
• selecting a photographing spot from at least one previous photographing spot where photographing has been performed;
• regenerating a depth image at the selected photographing spot, based on a point cloud image corresponding to a depth image at the at least one previous photographing spot where photographing has been performed;
• determining whether there is a hole satisfying a predetermined condition in the regenerated depth image at the selected photographing spot;
• and
• selecting, when there is a hole satisfying the predetermined condition, a pixel point from an edge of the hole, and obtaining a position range where the next photographing spot is located, based on the position of the selected pixel point and the position of the selected photographing spot;
• wherein regenerating the depth image at the selected photographing spot, based on the point cloud image corresponding to the depth image at the at least one previous photographing spot where photographing has been performed, comprises:
• obtaining a point cloud image corresponding to the selected photographing spot, from the point cloud image corresponding to the depth image at the at least one previous photographing spot where photographing has been performed, and regenerating the depth image at the selected photographing spot from the point cloud image corresponding to the selected photographing spot;
• and
• wherein regenerating the depth image at the selected photographing spot from the point cloud image corresponding to the selected photographing spot comprises:
• mapping each point in the point cloud image corresponding to the selected photographing spot into a pixel matrix corresponding to the depth image;
• and
• determining, when there are a plurality of depth values corresponding to a same pixel point in the pixel matrix, a minimum depth value in the plurality of depth values as a depth value of the pixel point.