Pedestrian recognition method of camera network based on multi-level depth feature fusion

Abstract

The invention discloses a pedestrian identification method of a camera network based on multi-level depth feature fusion. A new network model is learnt on a pedestrian database by migrating parameters of a pre-training network to the pedestrian database, a plurality of multi-level depth features are extracted using the new network model, and then a Softmax classifier in the last layer of a convolutional neural network is replaced by an SVM classifier to achieve the purpose of making full use of the multi-layer depth features. Furthermore, the multi-level depth features are used for constructing a plurality of groups of SVM classifiers of binary classification and decision values of these binary classifiers are linearly weighted to obtain final classification results. The invention can effectively improve the accuracy of recognizing a pedestrian target by way of multi-level feature fusion in a decision-making layer of the SVM classifier.

Description

technical field [0001] The invention belongs to the technical field of computer vision monitoring, and in particular relates to a camera network pedestrian recognition method based on multi-level depth feature fusion. Background technique [0002] In recent years, camera networks have been increasingly used in video surveillance in public places such as airports, subway stations, squares, and banks. The problem of matching pedestrian targets between multiple cameras with no overlapping view fields is called the pedestrian recognition problem, and its purpose is to find one or several pedestrian targets of interest from the entire camera network. [0003] Pedestrian recognition has always been a research hotspot in the field of computer vision. Using this technology, pedestrians in surveillance videos can be automatically analyzed, thus changing the traditional way of manually monitoring a large amount of video data, greatly saving labor costs and improving video processing. ...

AI Technical Summary

Problems solved by technology

However, there is currently no effective method to fully utilize multi-level deep features for pedestrian recognition tasks.

On the one hand, in the actual monitoring scene, since the number of labeled pedestrian samples is often too small to fully train the deep network, it is difficult to extract robust deep features of pedestrian pictures; on the other hand, due to the convolutional neural network The last layer of the network is the Softmax classifier. Its limitation is that it can only classify the output of the previous layer as the input feature, and cannot make full use of the depth features of different levels.

Images