Intelligent assignment system for plane mirror imaging experiment
A plane mirror and sub-system technology, applied in data processing applications, biological neural network models, resources, etc., can solve problems such as scoring points that cannot be scored, and achieve the effect of relieving pressure
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0049] see Figure 1~3 , an intelligent scoring system for plane mirror imaging experiments, the system includes
[0050] Image Acquisition Module: Obtain the image of the current experimental table from the top camera, decode the video according to the relevant codec protocol of the Haikang camera, and obtain image information that can be used for image processing. The size of the obtained normal image information will be changed from 2560 *1520 is scaled to 832*832 as the input of the deep detection network;
[0051] Image detection module: mainly composed of two parts, namely the YOLOv5 target detection network and the FLD line segment detection algorithm that can intelligently identify each experimental device in the experimental process;
[0052] Post-detection processing module: reprocess the detected line segment to determine the required line segment. According to the requirements of some scoring points, some line segments need to be stored in the form of pixels where...
Embodiment 2
[0070] see figure 2 , a method for using an intelligent scoring system for plane mirror imaging experiments, the system includes the following steps
[0071] Step 1. Camera video collection on the top of the experimental table: Obtain the operation video of the plane mirror imaging experiment from the top shooting angle of the experimental table, and obtain the information of each device itself and related operation actions;
[0072] Step 2. Video decoding: Decode the video of the plane mirror imaging experiment operation into a picture, and prepare to input it to the detection and recognition model after preprocessing;
[0073] Step 3. Target detection and target reprocessing: transfer the acquired pictures to the trained YOLOv5 network for real-time target detection; filter the detected target information and perform reprocessing by means of line segment detection and other means;
[0074] Step 4. Image target analysis and score judgment: Combine the processed target infor...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More