Abstract
The main challenge of person re-identification (re-id) lies in the strikingly discrepancy between different camera views, including illumination, background and human pose. Existing person re-id methods rely mostly on implicit solutions, such as seeking robust features or designing discriminative distance metrics. Compared to these methods, human solutions are more straightforward. That is, imagine the appearance of the target person under different camera views before matching target person. The key idea is that human can intuitively implement viewpoint transfer, noting the association of the target person under different camera views but the machine failed. In this paper, we attempt to imitate such human behavior that transfer person image to certain camera views before matching. In practice, we propose a conditional transfer network (cTransNet) that conditionally implement viewpoint transfer, which transfers image to the viewpoint with the biggest domain gap through a variant of Generative Adversarial Networks (GANs). After that, we obtain hybrid person representation by fusing the feature of original image with the transferred image then perform similarity ranking according to cosine distance. Compared with former methods, we propose a human-like approach and obtains consistent improvement of the rank-1 precision over the baseline in Market-1501, DukeMTMC-ReID and MSMT17 dataset by 3%,4%,4%, respectively.
Highlights
There is a famous fable in China, which is The Blind Men and The Elephant
We propose a modified StarGAN [14] to learn the style for each camera view, we measure the domain gap for the style of each camera viewpoint, we translate the image to the camera viewpoint with the largest domain gap
PERSON RE-IDENTIFICATION BASED ON DEEP LEARNING Considering that the method we proposed is based on the image-based person re-id, in this part, we mainly focus on the works of image-based person re-id
Summary
RUI SUN 1,2,3, WEIMING LU 1,2,3, YE ZHAO 1,2, JUN ZHANG 1,2, AND CAIHONG KAI 2, (Member, IEEE).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.