A method for counting the number of people in construction elevator cars based on multi-information fusion
A construction hoist and multi-information fusion technology, applied in the field of computer vision, can solve the problems of image sticking, low resolution, inaccurate statistics of the number of people in the construction hoist cage, and achieve the effect of high algorithm recognition accuracy and good real-time performance.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0068] The actual collected images of a construction site are as follows: Figure 4 , the red background is also marked in the figure, the number 1 is a yellow helmet, and the number 2 is a red helmet. Taking the red helmet as an example for analysis, Figure 5 Segment the binarized image for the image, Image 6 It is the final analysis and processing result of the present invention. Depend on Figure 5 It can be seen that after the binary segmentation, the yellow helmet is filtered out first, and there are 6 connected domains after color extraction, among which, connected domain 4 (red door frame), connected domain 5 (red background), connected domain 6 (red background) It can be directly excluded by using the area feature; the aspect ratio of the connected domain 3 is 2, but it is excluded because the duty ratio of 0.63 does not meet the target threshold; the connected domain 1 has a duty ratio of 0.82 and an aspect ratio of 1.81. The number of targets in domain 1 is 2; f...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


