There are many object detection methods in terms of object recognition based on traditional methods, but they are not sufficient to meet the demand for accuracy and speed in real-life scenarios. And compared with mobile platform, cloud service is also not conducive to the use in practical scenarios. Therefor we optimize the YOLO (You Only Look Once, a method for real-time detection of objects) algorithm through renormalization processing, build the Chinese road sign dataset and perform random affine transformation, random blur, and brightness transformation processing on the dataset to enhance the generalization ability of the final model. The parameters of the model are fine-tuned to reduce the period required to train the model and improve the performance of deep learning. Finally, the deep learning model of object detection will be transplanted to iOS mobile terminal to meet the requirements of real-time and accuracy in automatic driving scenarios. We identifie three types of road objects. The detection accuracy of pedestrians on road scenes reaches 75.9%, and the average detection accuracy of buses, cars, bicycles, and motorcycles is 72%. The detection accuracy of road signs is 69%. Total accuracy is 74.31%. The average detection rate of running tests on mobile phones is 12.5 frames per second.
In this presentation, a lightweight metastructure is designed based on the prismatic tensegrity structure which enables uniquely coupled compressional and torsional waves. A prismatic tensegrity structure consists of elastic bars and cables with pre-stress to provide its stiffness and therefore, has very high strength-to-weight ratio. A theoretical model with coupled compressional-torsional stiffness matrix is developed to study the band structure of the proposed metastructure. Microstructure designs based on both Bragg scattering and local resonance mechanism are investigated for vibration isolations in different targeted frequency ranges. It is noticed that unit cell with opposite chirality can lead to broadband isolation for both compressional and torsional vibrations. Interesting wave mode mixing and selective wave mode transmission phenomena are also studied based on the proposed theoretical model. Moreover, tunable wave propagations and vibration suspension are achieved by two approaches: (i) harnessing the geometrically nonlinear deformation of the periodical tensegrity prisms under global torsional or/and compressional loads to achieve large-range and coarse adjustment of the band structure; (ii) modifying the pre-stress in the tension cables with active components, such as hydraulic actuators, for small-range and fine adjustment of the band structure. The proposed tensegrity metastructure could be useful for various engineering applications in the fields of space and civil engineering where high strength-to-weight ratio as well as broadband vibration suspension are in a high demand.
In this work, perfect elastic wave mode transmission and isolation in an anisotropic Pentamode Material (PM) slab sandwiched between two semi-infinite isotropic solids are first explored. Selective elastic wave mode filtering is achieved in a broad frequency range. Furthermore, elastic wave experiments are conducted, which are in good agreements with the full-wave finite element simulations. As a result, the anisotropic PM greatly expands the horizon of subwavelength elastic wave control with broadband advantage. Such filtering abilities can be very useful for underwater noise isolation and elastic wave manipulation devices.
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.