A double-flow network pedestrian re-identification method combining the apparent characteristics and the temporal-spatial distribution

Abstract

The invention discloses a double-flow network pedestrian re-identification method combining the apparent characteristics and the temporal-spatial distribution. The method mainly comprises the following steps of extracting the apparent characteristics of the pedestrian images by using a depth neural network and calculating the apparent similarity of image pairs; learning the spatio-temporal distribution model of a training dataset by Gaussian smoothing based statistical method; obtaining the final similarity by calculating the apparent similarity and the spatio-temporal probability with the joint measurement method based on logical smoothing; sorting the final similarity to get the result of pedestrian re-recognition. The main contributions comprises proposing a pedestrian re-identificationframework based on dual-stream network which combines the apparent features and spatial-temporal distribution; (2) proposing a new spatio-temporal learning method based on Gaussian smoothing; (3) proposing a new joint similarity measurement method based on logical smoothing. The experimental results show that the can be applied to the accuracy of Rank1 of the proposed method on the DukeMTMC-reIDand Market1501 datasets are respectively increased from 83.8% and 91.2% to 94.4% and 98.0%, and a significant performance improvement is realized over other methods.

Description

technical field [0001] The invention belongs to the technical field of pedestrian re-identification in computer vision, and specifically relates to a double-stream network pedestrian re-identification method combining appearance features and time-space distribution. Background technique [0002] In recent years, video surveillance has played an important role in the field of public security, and pedestrian re-identification technology is a very critical step in video surveillance, which plays a key role in assisting the police to track criminals and maintain social stability. In recent years, due to the excellent performance of deep neural network in extracting image features, pedestrian re-identification technology has made great breakthroughs. [0003] The current research on pedestrian re-identification mainly focuses on the optimization of neural network structure and the optimization of loss function. However, the effect of improving the model purely from the neural ne...

AI Technical Summary

Problems solved by technology

However, the speed of pedestrians in the real world is often uncertain.

Therefore, the existing space-time constraint model cannot be well applied in the real world

Constructing a robust spatiotemporal model has the following two challenges: (1) There are often multiple time difference peaks between two cameras in the real world, because there may be many different roads, so constructing a robust spatiotemporal model is very important. difficult

(2) Even if we build a relatively robust spatio-temporal model, since the speed and state of pedestrians are unpredictable, for example, if we want to track a thief, his speed will often be very fast and the path will be very strange

Images