Crack is a common concrete pavement distress that will deteriorate into severe problems without timely repair, which means the automated detection of pavement crack is essential for pavement maintenance. However, automatic crack detection and segmentation remain challenging due to the complex pavement condition. Recent research on pavement crack detection based on deep learning has laid a good foundation for automated crack segmentation, but there can still be improvements. This paper proposes an automatic concrete pavement crack segmentation framework with enhanced graph network branch. First, the nodes of the graph and nodes’ attributions are generated based on the image dividing. The edges of the graph are determined based on Gaussian distribution. Then, the graph from the image is input into the graph branch. The graph feature map of the graph branch output is fused with the image feature map of the encoder and then enters the decoder to recover the image resolution to obtain the crack segmentation result. Finally, the method is tested on a self-built 3D concrete pavement crack dataset. The proposed method achieves the highest F1 and IoU (Intersection over Union) in the comparison experiments. And the graph branch addition improves 0.08 on F1 and 0.06 on IoU compared with U-Net.

To analyze the steady-state temperature field, a three-factor orthogonal test was taken to study comprehensively how the load, speed and tire pressure can influence the tire temperature. The finite element simulation was carried out according to the uncoupled idea. Based on the single-factor analysis towards the speed factor, the actual convection coefficient of different boundaries was determined to calculate the steady-state temperature field at last. These analyses indicate that the tire temperature rise increase with the factor of load and speed, decrease with the increase of the initial tire pressure. The load has the biggest influence on the tire temperature rise, while the speed has the least. With the combination of steady-state temperature field and heat generation rate distribution, all these high-temperature regions can be explained clearly from the finite element perspective.

Dietary treatment is the basic therapy for diabetes, but how to do the right food intake is the biggest discouraging problem. We present a proposal for mobile phone diabetes food information display which can help determine the food composition and calories automatically from the clinical point of view with the mature communication technology. We analyzed the composite of the device, especially the key technical method, which is digital image recognition, three-dimensional image analysis, standard tables of food composition database and composite meals energy calculation auxiliary knowledge base. The device has technical feasibility and broad application prospects. It's combination of dietary treatment with smart mobile technology, which can provide great support to solve the problem of food energy assessment and analysis, not only for the single-ingredient food but also the composite meals. The proposal also provides further thinking about how to improve adherence to medical nutrition treatment in diabetes.

No abstract