Vehicle re-identification is to recognize the same vehicle through vehicle images from different perspectives shot by multiple cameras. At present, the most of vehicle re-identification methods uses convolutional neural network to extract image features but lack the subtle feature discrimination ability. Therefore, we propose a novel vehicle re-identification methods called MSMG Net (Multi-Scale and Multi-Granularity) to solve this problem. We use ResNet-50 as the backbone network, and we design the multi-scale method to extract features of multi-granularity, which is from convolutional layer 3 to convolutional layer 5. For convolutional layer 3, we make the feature map to be divide global feature and local feature of three parts which dimension is 256. For convolutional layer 4, we make the feature map as layer 3 but has only one difference is two parts of local feature. For convolutional layer 5, we extract the global feature from global pooling which dimension is 256. Finally, we fuse these above eight features and get the 2048-dimension to compute the triplet loss and cross-entropy loss. Experiments on the Veri-776 dataset show that the proposed method achieves better performance, and good retrieval results have been achieved on the mAP(74.67%) and Rank-1(94.87%) evaluation index.
The structure of concrete bridge is usually large in dimension and the structural state information is heavily impacted by
many complicated factors. Especially, the influence of temperature to the structural responses is very significant and
this influence varies distinctly with the sun shine, sharp descent of temperature and season changing. Consequently, the
existence of temperature effect will result in a greatly complicated variation of the structural responses, adding great
difficulty in the effective extraction of structural health information for safety assessment of bridges. In this paper, In
order to realize the effective assessment of the structural safety of concrete bridges, according to the correlating
characteristic between temperature and structural response (such as strain or deflection) of the bridge, the experiential
regressive equation is decided by regressive analysis of temperature and structural response, and further more the
temperature effect is separated from the total response. Finally, an application example is given out for demonstration.
The results indicate that the response residual after elimination of temperature effect remains only the effect of
structural variety under loads (including dead load and live load), which can be used as the foundation information for
structural safety assessment of concrete bridges.
KEYWORDS: Bridges, Probability theory, Information fusion, Data fusion, Artificial neural networks, Associative arrays, Silicon, Information technology, Data modeling, Optoelectronics
As the damage diagnosis of bridge structure is highly nonlinear in nature, it is difficult to develop a comprehensive model taking into account all of the independent variables, such as the structural and environmental properties, using conventional modeling techniques. In this study, a method was introduced for damage diagnosis of bridge structure by integration of BP artificial neural network (ANN) and information fusion based on D-S evidential theory. The basic probability assignment functions for data fusion were constructed according to the demand of the damage diagnosis and the real conditions of the bridge structure. And an application example of the proposed method was demonstrated. The results showed that the integration of the two strategy can remove the shortcoming of BP ANN with remaining of its advantages and promote the identified veracity of the whole diagnosis system.
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.