Abstract
In order to improve the intelligent level of trackless rubber-tyred vehicles and ensure the safety of moving personnel in the operation area, this paper proposes a personnel detection method based on infrared thermal imaging technology to solve the disadvantages of using visible light imaging in downhole applications. On this basis, the Lucas-Kanade method is improved by using the adaptive-size window and an improved Lucas-Kanade is designed and utilized to achieve motion feature extraction of moving target, and some simulations are provided to verify the excellent performance. Then, the composite feature information of moving target segmentation obtained by fuzzy C-means clustering algorithm and optical flow detection results are combined based on the morphological weighted voting method to realize the precise detection of moving personnel. Finally, the laboratory experiment and industrial test are carried out to evaluate the proposed method, which indicates the feasibility and superiority and shows considerable application prospects.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have