Vision-based measurement for rotational speed by improving Lucas–Kanade template tracking algorithm

Abstract

Rotational angle and speed are important parameters for condition monitoring and fault diagnosis of rotating machineries, and their measurement is useful in precision machining and early warning of faults. In this study, a novel vision-based measurement algorithm is proposed to complete this task. A high-speed camera is first used to capture the video of the rotational object. To extract the rotational angle, the template-based Lucas-Kanade algorithm is introduced to complete motion tracking by aligning the template image in the video sequence. Given the special case of nonplanar surface of the cylinder object, a nonlinear transformation is designed for modeling the rotation tracking. In spite of the unconventional and complex form, the transformation can realize angle extraction concisely with only one parameter. A simulation is then conducted to verify the tracking effect, and a practical tracking strategy is further proposed to track consecutively the video sequence. Based on the proposed algorithm, instantaneous rotational speed (IRS) can be measured accurately and efficiently. Finally, the effectiveness of the proposed algorithm is verified on a brushless direct current motor test rig through the comparison with results obtained by the microphone. Experimental results demonstrate that the proposed algorithm can extract accurately rotational angles and can measure IRS with the advantage of noncontact and effectiveness.

Instantaneous Rotational Speed Measurement Using Image Correlation and Periodicity Determination Algorithms

“…With rapid advances in imaging sensors and image processing algorithms in recent years, imaging based techniques provide a promising alternative to rotational speed measurement [13][14][15][16][17][18][19][20][21]. The imaging technique is potentially suitable for applications in a hostile environment because of its sensing principle.…”

“…For the image series of a moving object, the intensity variation of pixels is the reflection of the motion of the object [23]. Existing speed measurement systems based on the imaging principle are normally implemented by exploiting the intensity distribution difference between two consecutive frames with the aid of camera calibration techniques [13][14][15][16][17][18]. An instantaneous rotational speed measurement system using a high-speed camera and a well-designed varying-density fringe pattern was proposed by Zhong et al [13,14].…”

Structural Low-Level Dynamic Response Analysis Using Deviations of Idealized Edge Profiles and Video Acceleration Magnification

“…Structural high-frequency motions can be recorded in a high-speed video file, and noises from frame interpolation are technically avoided in subsequent image processing. Valuable motion signals hidden in video frames can be extracted by combining image processing algorithms, such as optical flow [11,12] and image correlation [13,14] (including digital image correlation (DIC)). Therefore, motion estimation from a sequence of video has become a popular problem in the computer vision field.…”

Structural dynamic response analysis using deviations from idealized edge profiles in high-speed video

“…Therefore, motion estimation from a sequence of video images has become a popular problem in computer vision area. Regardless of the technology involved, the most common motion estimation approaches can be grouped as optical flow [12][13][14] and image template matching methods [15][16][17][18] (including digital image correlation). Studies on these algorithms have shown various potential applications in fields, such as modal parameter analysis, [19][20][21] deformation extraction, 22 and fault diagnosis.…”