With the rise of smart city construction, the importance of vehicle re-identification based on video surveillance has become increasingly prominent. The task of vehicle re-identification mainly focuses on recognizing the same vehicle image under different cameras. In this paper, we propose a multi-label fusion framework for vehicle re-identification based on VIT network. We design a method of anti-angle distortion data augmentation to solve the problem that the performance of VIT is limited by the relative position relationship inside the vehicle structure and the angle deviation caused by the different relative positions of camera and vehicle. At the same time, the key position weight information module is inserted into the coding layer to improve the network's attention to key information. Finally, in view of the insufficient use of the location information between patches in the VIT network, we design a location code based on the Minkowski distance metric to add the relative location relationships within the vehicle individuals to the network. The experiment shows that under the same conditions, our vehicle weight recognition system is superior to most of the more advanced work in vehicle-ID and VERI776 datasets compared with the most advanced supervised vehicle weight recognition work.
KEYWORDS: Education and training, Data modeling, Image processing, Cameras, Feature extraction, Performance modeling, Machine learning, Video surveillance, Statistical modeling, Video
With the rise of command city construction, the importance of pedestrian re-identification based on video surveillance has become increasingly prominent. The person re-identification task mainly studies recognizing images of the same person under different cameras. Due to the high cost of labeling data in supervised learning in common methods, and the lack of guidance for labeling data in unsupervised learning, the experimental results are unsatisfactory. In this paper, we propose a new weakly supervised person re-identification problem framework: a human-computer interaction-based sample active push and auxiliary labeling method is designed to quickly obtain a small number of identity-related labels with low labor cost; At the same time, the weak supervision information that is easily obtained in the real scene is introduced into the pseudo-label generation process to improve the clustering method, aiming to solve the problem of insufficient initial labeling data of images in the label estimation stage and weakly supervised labels are not well utilized; Finally, in view of the insufficient utilization of weakly supervised labels in the model training process, a weakly supervised loss function WSP loss is designed and added to the training to optimize the overall loss function. Compared with the current state-of-the-art unsupervised and weakly supervised person re-identification work, this paper shows better performance under the same conditions and even using less labeled information.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.