A vision system that includes a specially designed video camera and an image-data-processing computer is under development as a prototype of robotic systems for visual inspection of the interior surfaces of pipes and especially of gas pipelines. The system is capable of providing both forward views and mosaicked radial views that can be displayed in real time or after inspection.

Figure 1. The Camera Is Aimed Along the Axis of a pipe, shown in (a) before insertion into the pipe and in (b) inside the pipe. LEDs provide the illumination needed to acquire video images of the inside pipe wall.

To avoid the complexities associated with moving parts and to provide simultaneous forward and radial views, the video camera is equipped with a wideangle (>165°) 'fish-eye' lens aimed along the axis of a pipe to be inspected. Nine white-light-emitting diodes (LEDs) placed just outside the field of view of the lens (see Figure 1) provide ample diffuse illumination for a high-contrast image of the interior pipe wall.

The video camera contains a 2/3-in. (1.7-cm) charge-coupled-device (CCD) photodetector array and functions according to the National Television Standards Committee (NTSC) standard. The video output of the camera is sent to an off-theshelf video capture board (frame grabber) by use of a peripheral component interconnect (PCI) interface in the computer, which is of the 400-MHz, Pentium II (or equivalent) class.

Prior video-mosaicking techniques are applicable to narrow-field-of-view (low-distortion) images of evenly illuminated, relatively flat surfaces viewed along approximately perpendicular lines by cameras that do not rotate and that move approximately parallel to the viewed surfaces. One such technique for real-time creation of mosaic images of the ocean floor involves the use of visual correspondences based on area correlation, during both the acquisition of separate images of adjacent areas and the consolidation (equivalently, integration) of the separate images into a mosaic image, in order to insure that there are no gaps in the mosaic image.

The data-processing technique used for mosaicking in the present system also involves area correlation, but with several notable differences: Because the wide-angle lens introduces considerable distortion, the image data must be processed to effectively unwarp the images (see Figure 2). The computer executes special software that includes an unwarping algorithm that takes explicit account of the cylindrical pipe geometry. To reduce the processing time needed for unwarping, parameters of the geometric mapping between the circular view of a fisheye lens and pipe wall are determined in advance from calibration images and compiled into an electronic lookup table. The software incorporates the assumption that the optical axis of the camera is parallel (rather than perpendicular) to the direction of motion of the camera. The software also compensates for the decrease in illumination with distance from the ring of LEDs.

Figure 2. A Picture Taken Looking Along a Pipe is distorted (warped) by the combined effects of the lens and the viewing geometry (left). The image data are processed to unwarp the image (right), yielding an undistorted radial view.

The potential advantages to be gained from the development of this system are best understood in comparison with visual pipeline-inspection systems in current use. Almost all of those systems offer unprocessed video images for viewing by humans in real time or in post-inspection playback. The fatigue induced by long viewing of mostly featureless images makes such inspection somewhat unreliable, and cost of labor for such inspection is high. If, as planned, the present system could be enhanced by use of additional computer vision techniques, then visual inspection of pipelines could be promoted to supervised inspection, which, in turn, could be a precursor to partly or totally automated inspection. According to one scenario, a system derived from the present one would provide enhanced graphical displays, possibly with highlights on potential defects, and could even provide audible alarms to alert operators. Operators could then concentrate their attention on pipeline sections most likely to contain defects. Reliability of pipeline inspection would thus be increased and the cost of labor reduced.

This work was done by Darby Magruder of Johnson Space Center and Chiun-Hong Chien of Hernandez Engineering. For further information, contact the Johnson Technology Transfer Office at (281) 483-3809. MSC-23075