Visual inspection plays a crucial role during the manufacturing of tires which are essential for safe driving. Due to complicated anisotropic multi-texture background and ambiguous defect in it, automated tire defect detection is facing huge challenges and high costs. In this study, a novel two-stage convolutional neural network (CNN) is proposed for tire inspection by combining an optimized YOLOv3 and improved pyramid scene parsing network. Comparative experiments are conducted with the-state-of-the-art to validate the effectiveness and superior performance of the proposed method. The proposed two-stage CNN method achieves an average precision of 91.39%, the defect semantic segmentation achieves a mean intersection over union of 87.86%. The average detection time for a tire is 1.158 s such that the method can be effectively implemented into the industrial workflow. It can also be easily applied to different visual inspection applications.
The algorithm for selecting and stitching the joint images of the conveyer belt with steel ropes in X-ray imaging system is studied. Detecting the state of conveyer belt is important in production process such as coal mine. And selecting the joint images is a primary task for further processing, especially for the on-line nondestructive detection of product line. Moreover, in order to make the better visual effect and analyze the whole joint effectively, it is necessary to stitch the joint images containing the same joint information. Based on the character of the conveyer belt X-ray images, an algorithm using the gray level histogram statistics for selecting and stitching the conveyer belt joint images is put forward in this paper. The practical application shows that the correct selection rate of the joint image is 100%, and the whole joint image is stitched inextenso and correctly. This algorithm for joint detecting can greatly improve the performance of processing, especially for the on-line nondestructive detection of product line. The results of practical application show that the algorithm we proposed is effective.
The course of the 5th National Peasant Games is the perfection process of its scale,events and social impact.And it has greatly promoted rural sports.In the retrospect to the history of National Peasant Games,the paper discusses and analyzes the influences of National Peasant Games on rural sports.The resulu shows that National Peasant Games has improved the organization and guidance of rural sports,promoted the exchange of rural culture,and brought about new sports means.The mission of future National Peasant Games is put forward in order to explore deeper into rural sports.
Accurate image semantic segmentation in atmosphere turbulence conditions is challenging due to the severe degradation effects introduced by the random refractive-index fluctuations of atmosphere. In this paper, we present an end-to-end trainable methodology for turbulence-degraded image semantic segmentation that is capable of digging the physical imaging mechanism in atmosphere turbulence conditions, in order to improve semantic estimates. First, we investigate the physical imaging mechanism in kinds of turbulence conditions, including the isotropic turbulence and the anisotropic turbulence. Physical turbulence parameters are considered, such as the anisotropic factor, turbulence inner and outer scales, refractive-index structure constant, general spectral power law and imaging distance. Second, based on the physical imaging model in various turbulence conditions and image processing algorithms, we construct the turbulence-degraded image datasets, including the turbulence-degraded Pascal VOC 2012 and ADE20K. The new datasets cover a wide range of turbulence scenes. Third, in order to obtain more accurate boundary information, we propose the Boundary-aware DeepLabv3+ network that is trained on the constructed turbulence-degraded image datasets for semantic segmentation in turbulence media. The proposed model extends DeepLabv3+ by adding simple yet effective Edge Aware Loss and Border Auxiliary Supervision Module, which is helpful to acquire precise boundary segmentation effect while confining the target in this boundary region. Finally, without any pre-processing, the semantic segmentation accuracy reached a performance of 87.95% mIoU on the Turbulence-degraded Pascal VOC 2012 Dataset.
Nacelle turbine generator systems are primarily used in the aviation field for hybrid electric propulsion systems of electric aircraft, requiring the turbine generators to have both high power density and high efficiency. To meet this requirement, based on the load characteristics of the nacelle turbine, this study conducts electromagnetic design research for a 290 kW turbine permanent magnet generator. Using finite element methods, an electromagnetic calculation model of the permanent magnet generator is established, analysing its no-load characteristics, load characteristics, and conducting loss and efficiency analysis, which proves the effectiveness of the design. The designed 290 kW generator achieves a power density of 4.9 kW/kg and a rated efficiency of 96%.
By analysing the relation of every particle,centre of mass,internal force and outside force,this paper explains that the quiescent rubforce is the ultimate reason of moving ahead,where the Newton's secend dynamic law is used.Secondly,using the princile of work and energy,it is revealed that the work done by the quiescent rubforce for centre of mass is the reason to gain kinetic energy for a person.
Vehicular Edge Computing (VEC) is a promising paradigm to enable huge amount of multimedia content to be cached in proximity to vehicles. Since vehicles are equipped with a certain amount of caching resource, they can be regarded as edge nodes to expand the caching capacity of the network edge. However, with much sensitive personal information, vehicles may be not willing to cache their content to an untrusted vehicle. Permission blockchain has the potential to address such an issue. In this paper, we utilize permissioned blockchain to design a secure content caching scheme between vehicles. Since high mobility of vehicles makes a dynamic caching environment, we exploit deep reinforcement learning approach to design the content caching scheme. Moreover, we propose a new block verifier selection metric, Proof-of-Utility (PoU), to enable a lightweight permissioned blockchain. Security analysis shows that our proposed blockchain empowered content caching can achieve security and privacy protection. Numerical results based on the Uber dataset indicate the DRL-inspired content caching scheme significantly outperforms two benchmark policies.
Multiview video plus depth (MVD) is a new 3D video format that would support 3D applications developed by MPEG. Such a format is a combination of texture video and associated depth maps. Consequently, for the efficient transmission of 3D video signals, the compression of texture video and also the depth maps is required. Since high computational complexity of jointly coding between the texture video and depth map is still an open question, this paper introduces a low complexity MVD coding algorithm that adaptively utilizes the texture and depth map correlation. Based on the correlation, we propose four efficient techniques, including depth information based fast mode size decision, adaptive disparity estimation in texture coding, motion vector sharing based on the texture image similarity correlation and the SKIP mode decision in depth coding. Experimental results show that the proposed algorithm can significantly reduce the computational complexity of MVD coding while improve the coding performance and achieve better rendering quality 1 .
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)