Pedestrian re-identification method and device based on global features and coarse granularity local features

Abstract

The invention, which belongs to the field of image processing and identification, discloses a pedestrian re-identification method and device based on global features and coarse granularity local features. The method comprises: detecting a pedestrian image in a query image as a global image, detecting a body key point of the pedestrian, and dividing the body of the pedestrian to obtain a local partregion; extracting global feature description of the global image and local feature description of the local part region, carrying out fusion of the global feature description and the local feature description to obtain global-local feature description; and carrying out associated analysis and combined indexing on all images in a pedestrian database, carrying out pedestrian retrieving on the processed images from the coarse granularity to fine granularity according to the global-local feature description, and determining the identity of the pedestrian in the query image. According to the invention, coarse granularity division is carried out on the body in the image, so that the good robustness is realized; and because the global features and regional local features are combined, accuratematching of the pedestrian images and pedestrian identity identification are realized.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

This technology divides an image by small grains that have stronger connections with each other compared to larger ones. It then analyzes it for both strong visual cues like grayscale or color patterns associated with people's faces instead of just looking at them separately from background noise. By combining these two techniques together, this system can accurately match footprint data without requiring too much computing power. Additionally, there will be more efficient ways to recognize objects based only on their own appearance rather than relying solely on its surroundings.

Problems solved by technology

This patented technical problem addressed by this patents relates to identifying humans from footprinted areas (images) captured through cameras or sensors that capture their movements without obstructive clothing. Current methods involve analyzing large amounts of pixel values representing these feetwear patterns with complicated algorithms requiring significant computing power.

Images