![]() ![]() ![]() Kinect depth map inpainting using a multi-scale deep convolutional neural network. Batch normalization: Accelerating deep network training by reducing internal covariate shift. Mobilenets: Efficient convolutional neural networks for mobile vision applications. IEEE transactions on neural networks and learning systems, 28(10):2222-2232, 2016. In Proceedings of the 27th International Conference on Neural Information Processing Systems Volume 2, NIPS'14, pages 2672-2680, Cambridge, MA, USA, 2014. In Proceedings of the IEEE international conference on computer vision, pages 1440-1448, 2015. In 2013 IEEE International Conference on Body Sensor Networks, pages 1-6. Development of a wireless low-power multi-sensor network for motion tracking applications. A sensor-aided self coaching model for uncocking improvement in golf swing. In Multidisciplinary Digital Publishing Institute Proceedings, volume 2, page 265, 2018. The effect of ball wear on ball aerodynamics: An investigation using hawk-eye data. In Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems, pages 369-370. Field deployable realtime indoor spatial tracking system for human behavior observations. In Thirty-Second AAAI Conference on Artificial Intelligence, 2018. Ionet: Learning to cure the curse of drift in inertial odometry. Openpose: realtime multi-person 2d pose estimation using part affinity fields. Quantification of inertial sensor-based 3d joint angle measurement accuracy using an instrumented gimbal. In Proceedings of the 2017 ACM International Symposium on Wearable Computers, ISWC '17, pages 2-9, New York, NY, USA, 2017. Ball speed and spin estimation in table tennis using a racket-mounted inertial sensor. A quaternion-based motion tracking and gesture recognition system using wireless inertial sensors. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5167-5176, 2018. Posetrack: A benchmark for human pose estimation and tracking. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 7297-7306, 2018. Densepose: Dense human pose estimation in the wild. Our comprehensive experiment shows that proposed method outperforms other solutions and reaches 6.57 cm error in subject-dependent model and less than 10 cm error for unknow-subjects via a tailored conditional Generative Adversarial Networks (cGAN). tracking, analysis and assessment) in the wild. Condor could be implemented with edge devices such as a smart wristband and a smartphone, which are ubiquitously available, for accurate golf swing analytics (e.g. To overcome these limitations, we introduce Condor, a tailored deep neural networks to make use of sensor fusion to combine the advantages of these two sensor modalities, where IMUs are not affected by occlusion and can support high sampling rates and depth sensors produce more accurate motion measurements than those produced by IMU. This is due to commonly known issues with occlusion and low sampling rates generated by depth sensors and complex IMU noise models. Existing solutions based on these devices cannot produce consistent and accurate swing-tracking. We develop a novel solution to track a player's swing in threedimensional (3D) space using inexpensive tools such as depth sensors and Inertial Measurement Units (IMUs). This paper explores the possibility of incorporating sensor-rich and ubiquitously deployed mobile devices into sports analytics, particularly to the game of golf.
0 Comments
Leave a Reply. |