A digital character detection method for moving targets

Abstract

The invention discloses a digital character detection method for a moving target, and relates to the fields of small target detection and machine vision. The main scheme includes step 1: the first frame obtains the position and scale information of the moving target in the initial frame according to the existing moving target template; step 2: extracts the 31-dimensional fusion gradient histogram FHOG feature as a feature to predict the position and scale of the moving target in subsequent frames ; Step 3: For each frame, intercept the area where the moving target is located, use Structural Similarity (SSIM)-based scale pool traversal to detect the position and size of the target digital character, and loop to the last frame for detection. The present invention combines the SSIM algorithm with the scale pooling method, fully utilizes the condition that the background in a certain area around the target digital character (that is, in the moving block) is not easy to change, and can solve the problem of the number in the moving target under complex conditions such as illumination changes, scale changes, and background interference. Character detection has better accuracy and robustness.

Description

technical field [0001] The invention relates to the field of target detection based on vision, and more specifically relates to a detection method for digital characters of a moving target. Background technique [0002] Object detection is of great significance and value in the field of computer vision research. Its applications include intelligent video surveillance, traffic sign recognition in vehicle camera images, defect detection on material surfaces, and lesion detection and recognition in medical imaging images. At the same time, target detection is also an important prerequisite for many high-level visual processing and analysis tasks, such as behavior analysis, event detection, scene semantic understanding, lesion detection, etc., all require the use of image processing and pattern recognition technology to detect the targets in the image and determine these The semantic type of the target object, and the specific area of ​​the target object in the image is marked. ...

AI Technical Summary

Problems solved by technology

The digital character detection method on the moving target proposed in this scheme solves the problem that the existing methods are not robust to the digital character detection scene in the moving target, and it is difficult to balance the detection accuracy and detection speed.

Images