Feature reconstruction layer training method, image feature reconstruction method and related device

Abstract

The invention provides a feature reconstruction layer training method, an image feature reconstruction method and related devices, and relates to the field of pedestrian re-identification. The training method is applied to the electronic device and comprises the steps of obtaining a first feature vector according to a training image set; wherein the training image set comprises at least one training image; obtaining a second feature vector according to the fuzzy training set; wherein the fuzzy training set comprises at least one first feature map, and the first feature map is obtained by performing image feature suppression on the training image; obtaining reconstruction layer updating information according to the first feature vector and the second feature vector; and obtaining a featurereconstruction layer matched with the model convergence condition according to the reconstruction layer updating information. By use of the feature reconstruction layer obtained by the invention, no matter whether the image to be retrieved is a clear image or a blurred image, a better image feature can be obtained so as to reduce interference and influence of image blurring and the like on neuralnetwork features, and then pedestrian retrieval accuracy is improved.

Description

technical field [0001] The present application relates to the field of pedestrian re-identification, specifically, a method for training a feature reconstruction layer, a method for reconstructing image features, and related devices. Background technique [0002] Pedestrian re-identification is a very popular direction in computer vision research. At present, it has been widely used in the field of camera security. It mainly solves the problem of pedestrian recognition and retrieval in different scenarios across cameras. Traditional face recognition technology has defects such as narrow viewing angles. [0003] Pedestrian re-identification can be used as an important supplement to face recognition technology. It can perform cross-camera retrieval of pedestrians who cannot obtain clear faces, and improve the coverage and spatiotemporal continuity of security monitoring. However, in practical application scenarios, the detected pedestrian data is very complex and is often affe...

AI Technical Summary

Problems solved by technology

However, in practical application scenarios, the detected pedestrian data is very complex and is often affected by various objective factors, such as no frontal photos, strong lighting changes, clothing changes, posture changes, occlusions, inconsistent shooting angles, blurred pictures, etc. , these objective factors will greatly increase the difficulty of pedestrian re-identification

Images