Abstract
Vehicle re-identification plays an important role in cross-camera tracking and vehicle search in surveillance videos. Large variance in the appearance of the same vehicle captured by different cameras and high similarity of different vehicles with the same model poses challenges for vehicle re-identification. Most existing methods use a center proxy to represent a vehicle identity; however, the intra-class variance leads to great difficulty in fitting images of the same identity to one center feature and the images with high similarity belonging to different identities cannot be separated effectively. In this paper, we propose a sampling strategy considering different viewpoints and a multi-proxy constraint loss function which represents a class with multiple proxies to perform different constraints on images of the same vehicle from different viewpoints. Our proposed sampling strategy contributes to better mine samples corresponding to different proxies in a mini-batch using the camera information. The multi-proxy constraint loss function pulls the image towards the furthest proxy of the same class and pushes the image from the nearest proxy of different class further away, resulting in a larger margin between decision boundaries. Extensive experiments on two large-scale vehicle datasets (VeRi and VehicleID) demonstrate that our learned global features using a single-branch network outperforms previous works with more complicated network and those that further re-rank with spatio-temporal information. In addition, our method is easy to plug into other classification methods to improve the performance.
Highlights
As people attach importance to traffic surveillance and public safety, there is an ever-increasing need to retrieve the same vehicles across cameras
In contrast to the above approaches, we propose a multi-proxy constraint loss (MPCL) function to deal with both intra-class variance and inter-class similarity problem in this paper
We propose a sampling strategy considering viewpoints and the multi-proxy constraint loss function that deals with the intra-class variance and inter-class similarity problems
Summary
As people attach importance to traffic surveillance and public safety, there is an ever-increasing need to retrieve the same vehicles across cameras. Lou et al [5] designed a distance adversarial scheme to generate similar hard negative samples, aiming at facilitating the discriminative capability They neglected the influence of intra-class variance, resulting in the inability to learn a compact feature embedding space. As for metric learning, Chu et al [11] adopted different matrices to evaluate the similarity of vehicle images according to whether the viewpoints are similar These methods need additional labeling and prediction process. We propose a novel sampling strategy considering different viewpoints, effectively selecting the samples captured by different cameras This sampling strategy contributes to sample the images corresponding to different proxies in a mini-batch.
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.