Target position identification method based on Haar features

Abstract

The invention discloses a target position identification method based on Haar features. The target position identification method comprises the steps: an initialization phase: acquiring a plurality of images including target positions as positive samples, and a plurality of images without target positions as negative samples, and extracting Haar features from all the positive samples and negative samples to obtain feature values; a training phase: utilizing the obtained feature values to train an Adaboost cascade classifier; and an identification cutting phase: acquiring the images to be identified, extracting Haar features, and utilizing the trained Adaboost cascade classifier to identify the images to be identified, wherein the feature matching region with the largest area is the target position. The target position identification method based on Haar features utilizes the Adaboost to learn and establish a multi-layer tree classifier, and utilizes a histogram statistical mode to accurately position the target at a later stage, thus eliminating the interference caused by different illumination environments and greatly improving the identification accuracy and speed, wherein the accuracy achieves more than 99.9%.

Description

technical field [0001] The invention relates to the technical field of target recognition, in particular to a target recognition method based on Haar characteristics. Background technique [0002] In the prior art, the general process of target recognition is as follows: the system inputs an image containing the target as a sample to be recognized, and matches the trained algorithm sample with the image of the sample to be recognized, thereby identifying the target in the image. [0003] When using the Hal feature for recognition, the appearance of the object to be recognized needs to be quite different, and the recognition effect depends on the result of the training. Since the target image itself does not have special features, and is affected by the hardware facilities of the shooting range, shooting conditions, cameras, Due to the influence of lens quality and other effects, the target image acquired by the bolt will produce slight geometric distortion. [0004] In orde...

AI Technical Summary

Problems solved by technology

[0004] In order to automatically obtain the target position in this kind of image, the existing processing method is: when the system is initialized, the parameters of the target position relative to the image are manually input. This method is cumbersome and cannot handle the deviation of the target position during the shooting process. Case

Images