A Pedestrian Re-Identification Method Based on Resolution Adaptive Feature Extraction and Fusion

Abstract

The invention discloses a pedestrian re-identification method for resolution self-adaptive feature extraction and fusion. The method fuses biological features and appearance features, uses the method of fusion of face features and appearance features to identify pedestrians, enhances the difference of features, and at the same time, according to the characteristics in The performance on different image scales, different pedestrian features will be compared on different scales; at the same time, the screening mechanism is used to filter the fusion features obtained by color features and contour features first, and then supplement the screening results with face features, and finally The texture features are extracted from the screened pedestrians, the color region features and weighted color features are greatly stabilized, and the extracted global features and local features are fused using an adaptive weighting method to obtain fusion features. The present invention can improve the accuracy of the method through adaptive fusion of biological features and appearance features. The complexity can be reduced by extracting appearance features and screening mechanisms at low scales.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a pedestrian re-identification method for resolution adaptive feature extraction and fusion. Background technique [0002] Person re-identification is a very important problem in video surveillance. Although many studies have focused on this field, person re-identification still faces many challenges. 1. At present, the resolution of pedestrian pictures captured in surveillance sites is low, and it is very difficult to extract clear biometric features for pedestrian re-identification. Second, the time when different pedestrians appear in the two camera scenes varies greatly, and it is very difficult to use time and space constraints to help pedestrians re-identify. Third, relying solely on appearance features to identify pedestrians is not stable, because pedestrian appearance features will be affected by posture, illumination, background and occlusion. Fourth, the l...

AI Technical Summary

Problems solved by technology

1. At present, the resolution of pedestrian pictures captured in surveillance sites is low, and it is very difficult to extract clear biometric features for pedestrian re-identification

2. The time when different pedestrians appear in the two camera scenes varies greatly, and it is very difficult to use time and space constraints to help pedestrians re-identify

Third, relying solely on appearance features to identify pedestrians is not stable, because pedestrian appearance features will be affected by posture, lighting, background and occlusion

4. The low calculation efficiency of pedestrian re-identification in large-scale video surveillance networks also brings great challenges to the application of pedestrian re-identification

The metric learning method will greatly improve the comparison effect by performing calibration training on a specific scene, but it is not universal and needs to be retrained for new scenarios. The training and calibration process is more complicated, and the space complexity of the method is High, it is still difficult to apply to the actual system

Images