Inspection methods for small bore pipes

1 . A video inspection method for an interior surface of a pipe, the method comprising the steps of:

a. defining geometrical size and shape of the interior surface of the pipe, wherein the pipe is a small bore pipe with an internal diameter or an internal size characterizing a cross-section of the pipe being 25 mm or smaller;

b. providing a videoscope sized to fit inside the pipe, wherein the videoscope is equipped with only a video camera and illuminating lights, and does not include any camera centering hardware, laser projection hardware, or any other sensor;

c. advancing the videoscope through the pipe while acquiring raw images from the video camera of the videoscope;

d. estimating the video camera pose for at least some of the raw images of step (c) by extracting and matching unique features from consecutive raw images using a Structure-from-Motion (SfM) technique;

e. sequentially building a pipe point cloud and a 3D textured model of the interior surface of the pipe from the raw images with adjustments for video camera poses, wherein building the pipe point cloud comprises:

i. building a first point cloud from the raw images;

ii. creating a virtual pipe using known pipe dimensions; and

iii. building a second pipe point cloud by fitting the virtual pipe to the first point cloud by minimizing an average of Euclidean distances between the virtual pipe and the first pipe point cloud;

followed by adjusting of image brightness based on a light distribution model and the video camera pose, wherein the light distribution model is that of a gradual decrease of lighting from a center of the video camera pose towards a periphery of the raw image;

f. unwrapping the raw images from step (e) using corresponding video camera poses and the second pipe point cloud to create unwrapped images of the interior surface of the pipe, wherein the unwrapping is performed using Depth-Image-Based-Rendering (DIBR) and ray tracing techniques, and further comprises creating an unwrapped image with multiple rays projected onto the virtual pipe in front of the video camera based on a pose thereof and using the second pipe point cloud; and

g. creating a panoramic image of the interior surface of the pipe by stitching the unwrapped images together, wherein creating the panoramic image comprises:

i. assigning a weight factor to at least some of the pixels on at least some of the raw images by gradually increasing the weight factor for each pixel from the periphery of the raw image towards a center thereof, thereby creating unwrapped and weighted images; and

ii. stitching the unwrapped and weighted images together with averaging of the pixels from related images with their respective calculated weight factors.

2 . The method as in claim 1 , wherein the point cloud is separated into individual slices in order to accommodate pipe bends, and the fitting procedure in step (e) (iii) is carried out by tuning the poses of the camera and fitted pipe slices.

3 . The method as in claim 1 , wherein the correlated points of the rays in step (f) are projected onto the raw 2D images to create images with ray projections.

4 . The method as in claim 1 , wherein the weight factor assigned in step (g) (i) is configured to reduce the contribution of unfocused pixels and increase the contribution of pixels with high focus and sharpness.