A method and application of analog acquisition and acquisition of moving images

Abstract

The invention discloses a method and application for simulating and acquiring moving images, comprising the following steps: three-dimensional modeling software is built in the industrial computer to perform three-dimensional modeling of the target scene; ISET software is installed to obtain the target scene in the three-dimensional modeling Virtual picture; based on the experimental device, start the display screen, turn on the lighting and spotlights, and adjust the brightness; run the ISET software to generate and display the virtual picture training set of the target scene; the acquisition camera collects the virtual picture of the training set of the target scene displayed on the display screen in real time ; ELM adaptive fitting optimization is performed on the image training set; based on the optimized training set, the training of the deep learning algorithm is completed; based on the test set, the trained deep learning algorithm is tested to verify the test training set and ELM self Adapt to the fitting optimization algorithm. Through comparison, it can be seen that after eliminating the sensor data deviation, the verification error is significantly reduced.

Description

technical field [0001] The invention relates to the technical field of data acquisition, in particular to a method and application for acquiring a moving image by simulating acquisition. Background technique [0002] The effectiveness of computer vision algorithms based on deep neural networks is very dependent on the data set. In conventional machine learning or deep learning, it is often assumed that the distribution of the test set and the training set is the same, the model is trained on the training set, and then tested on the test set. , the test set is also a sample of the real working condition data set, which is used to check whether the trained algorithm can work normally and stably in the target real working condition. [0003] If in the actual problem, the quality of the training set is not high, it will be very different from the test set. At this time, there will be an overfitting problem: the model does not perform well on the test set. The similarities and d...

AI Technical Summary

Problems solved by technology

[0003] If in the actual problem, the quality of the training set is not high, it will be very different from the test set. At this time, there will be a problem of overfitting: the model does not perform well on the test set.

The similarities and differences between the training set and the test set here are mainly reflected in two parts: the first part is the content and quantity of the data set. Although the content of the actual training set collected here is no problem, the number of samples is too small, because the actual collection of data, processing Data, screening images, and manual labeling will be very time-consuming and laborious. A small team of three or five people cannot complete large-scale actual collection work. The content of the virtual network dataset is not targeted and the content quality is not high

The second part is the collection method of the data set, which is reflected in the actual sensing method. Different camera parameters (position, angle, aperture, focal length, collection frame rate, depth of field, etc.) have a greater impact on data collection. If the training set and the test set are collected by different sensing methods, there will be a deviation problem between the two data sets. When reflected in the actual working conditions, there will be an over-fitting problem, resulting in a larger verification error.

Images