Water gauge water line image detection method and device suitable for night light supplement condition and storage medium
A water level and water gauge technology, applied in image analysis, image enhancement, image data processing and other directions, can solve problems such as large amount of calculation and difficult practical application, achieve small amount of calculation, overcome the influence of similar grayscale of foreign objects, and be very reliable. awesome effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0071] This embodiment introduces a water gauge water level image detection method suitable for supplementary light conditions at night, including:
[0072] Obtain the image to be detected that contains the target water gauge under the condition of supplementary light at night;
[0073] Use the pre-trained faster-RCNN target detection network to detect the approximate area of the water gauge, and obtain the image of the approximate area of the water gauge according to the detection results;
[0074] Perform Gaussian blur processing on the approximate area image of the water gauge to obtain a blurred image;
[0075] The blurred image is processed by a recursive OTSU algorithm to segment the water gauge from the background to obtain an image of the water gauge part;
[0076] Binarize the image of the water gauge part to obtain a binarized water gauge image;
[0077] Count all the pixels in the binarized water gauge image with a pixel gray value of 255, perform trapezoidal ...
Embodiment 2
[0117] Based on the same inventive concept as Embodiment 1, this embodiment introduces a water gauge water level image detection device, including:
[0118] The image acquisition module is configured to acquire the image to be detected that includes the target water gauge under the condition of supplementary light at night;
[0119] The preliminary detection module of the water gauge area is configured to detect the approximate area of the water gauge using the pre-trained faster-RCNN target detection network, and obtain an image of the approximate area of the water gauge according to the detection result;
[0120] The fuzzy processing module is configured to perform Gaussian fuzzy processing on the general area image of the water gauge to obtain a fuzzy image;
[0121] The image segmentation module is configured to process the fuzzy image using a recursive OTSU algorithm to segment the water gauge from the background to obtain an image of the water gauge part;
[0122] T...
Embodiment 3
[0127] Based on the same inventive concept as Embodiments 1 and 2, this embodiment introduces a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the water level of the water gauge as described in the embodiment is realized. The content of the line image detection method.
[0128] In summary, the present invention has the following advantages and progress:
[0129] 1) Strong environmental adaptability. The present invention uses the difference between the water gauge and the background under the condition of supplementary light at night to segment the binarized water gauge image through the recursive OTSU algorithm, performs calculus processing on the segmented binary water gauge image, and calculates the variance and mean value of the segmented data Combined with the set threshold, the background noise in the binarized water gauge image can be filtered to obtain the position of the water level line. ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More