Power transmission line construction machinery detection method based on Android system and embedded platform
An Android system and transmission line technology, applied in neural learning methods, character and pattern recognition, computer components, etc., can solve problems such as manpower consumption, untimely alarms, and delays in the safe operation of power grids, so as to improve efficiency, solve costs, and Realize the effect of intelligent management
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0026] Such as Figure 1-3 As shown, the transmission line construction machinery detection method based on Android system and embedded platform of the present invention comprises the following steps:
[0027] a. The embedded monitoring camera installed with Android system captures images within the range of the transmission line at regular intervals;
[0028] b. Convert the lightweight transmission line construction machinery hidden danger detection model into a tflite model, use TensorflowLite technology to transplant it into the embedded surveillance camera installed with Android system, load the model parameters, detect the newly captured images of the surveillance camera, analyze the detection results and deal with.
[0029] Specifically, step b includes the following detailed steps:
[0030] b1: Transform the lightweight transmission line construction machinery hidden danger detection model into a tflite model;
[0031] b2: Use TensorflowLite technology to transplant ...
Embodiment 2
[0038] On the basis of Example 1, a certain province based on the Android system and the embedded platform transmission line construction machinery detection system, the embedded monitoring camera installed with the Android system captured 14,000 pictures in a certain period of time during the capture process of the transmission line area On-site pictures, including 10475 pictures containing hidden construction machinery and 3525 pictures not containing construction machinery, use the construction machinery detection method proposed by the present invention, and use the embedded monitoring camera installed with the Android system to capture pictures locally and detect them in real time Finally, the false positive rate of construction machinery hidden danger identification is 11.2%, the false positive rate of identification is 12.7%, and the accuracy rate is 76.1%.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


