Pedestrian attribute identification system and method based on multilayer feature learning

Abstract

The invention discloses a pedestrian attribute recognition system and method based on multi-layer feature learning, the system comprises a feature bottom-to-top extraction module, a bottom-to-top feature fusion module, a feature prediction module, a multi-layer prediction fusion module and a test module, and the method comprises the following specific steps: processing pictures layer by layer frombottom to top to obtain multi-layer features; fusing the features of the adjacent layers layer by layer from top to bottom, compressing the channel by the feature map obtained by the higher layer, carrying out feature fusion and channel dimension reduction on the compressed channel and the feature map sampled by the upper layer, and outputting the feature of the current layer; obtaining preliminary prediction results of different levels through a maximum pooling layer and a full connection layer according to the fused features and the extracted uppermost features; overlapping the preliminaryprediction results of different levels, and correspondingly endowing each attribute predicted by each level with a weight value to obtain a final prediction result; and extracting a prediction resultcorresponding to the picture, and calculating a result of each index. According to the method, a group of specific weights are learned for each attribute according to the predicted values obtained bythe fused features, so that each attribute can better utilize multi-layer features to obtain a better recognition effect.

Description

technical field [0001] The invention relates to the field of computer vision based on deep learning, in particular to a pedestrian attribute recognition system and method based on multi-layer feature learning. Background technique [0002] Pedestrian attribute recognition, also known as human body attribute recognition, is to identify the attributes of pedestrians in pictures, such as hair color, hair length, clothing type, clothing color, etc., which is a multi-label classification problem. Pedestrian attribute recognition is widely used in pedestrian re-identification and pedestrian detection under the monitoring system, and pedestrian attributes can be used to assist these tasks. In the field of pedestrian attribute recognition, most of the existing methods are based on the implementation of deep learning. For example, the attention mechanism is used to generate the attention map and applied to each layer of the neural network to obtain different features, that is, the at...

AI Technical Summary

Problems solved by technology

[0003] Existing technologies are not very good at learning the required features for each attribute, because the multi-layer feature fusion done in these works is only done at the feature level, and most of the operations are splicing feature vectors. It cannot make better use of and integrate multi-layer features, and there is no corresponding learning for each specific attribute to pay attention to the features of each layer

Images