Vinod Kathail, Distinguished Engineer and leader of the Embedded Vision team at Xilinx, presents the "Caffe to Zynq: State-of-the-Art Machine Learning Inference Performance in Less Than 5 Watts" tutorial at the May 2017 Embedded Vision Summit. Machine learning research is advancing daily with new network architectures, making it difficult to choose the best CNN algorithm […]
Before a still image or video stream can be analyzed, it must first be captured and transferred to the processing subsystem. Cameras, along with the interfaces that connect them to the remainder of the system, are therefore critical aspects of any computer vision design. This article provides an overview of camera interfaces, and discusses their
Camera Interfaces Evolve to Address Growing Vision Processing Needs Read More +
This is a reprint of a Xilinx-published white paper which is also available here (1 MB PDF). Xilinx INT8 optimization provide the best performance and most power efficient computational techniques for deep learning inference. Xilinx's integrated DSP architecture can achieve 1.75X solution-level performance at INT8 deep learning operations than other FPGA DSP architectures. ABSTRACT The
Deep Learning with INT8 Optimization on Xilinx Devices Read More +
Nagesh Gupta, Founder and CEO of Auviz Systems, presents the "Semantic Segmentation for Scene Understanding: Algorithms and Implementations" tutorial at the May 2016 Embedded Vision Summit. Recent research in deep learning provides powerful tools that begin to address the daunting problem of automated scene understanding. Modifying deep learning methods, such as CNNs, to classify pixels
Allen Rush, Fellow at AMD, presents the "How Computer Vision Is Accelerating the Future of Virtual Reality" tutorial at the May 2016 Embedded Vision Summit. Virtual reality (VR) is the new focus for a wide variety of applications including entertainment, gaming, medical, science, and many others. The technology driving the VR user experience has advanced
The substantial parallel processing resources available in modern graphics processors makes them a natural choice for implementing vision-processing functions. The rapidly maturing OpenCL framework enables the rapid and efficient development of programs that execute across GPUs and other heterogeneous processing elements within a system. In this article, we briefly review parallelism in computer vision applications,
Optimizing Computer Vision Applications Using OpenCL and GPUs Read More +
This introductory article discusses implementing machine learning algorithms on FPGAs, achieving significant performance improvements at much lower power. Newly available middleware IP, together with the SDAccel programming environment, enables software developers to implement convolutional neural networks (CNNs) in C/C++, leveraging an OpenCL platform model. Machine Learning in the Cloud: A Tipping Point The transformation of
Accelerating Machine Learning: Implementing Deep Neural Networks on FPGAs Read More +
The substantial resources available in modern programmable logic devices, in some cases including embedded processor cores, makes them strong candidates for implementing vision-processing functions. The rapidly maturing OpenCL framework enables the rapid and efficient development of programs that execute across programmable logic fabric and other heterogeneous processing elements within a system. As mentioned in the
OpenCL Streamlines FPGA Acceleration of Computer Vision Read More +
Nagesh Gupta, CEO and Founder of Auviz Systems, presents the "Trade-offs in Implementing Deep Neural Networks on FPGAs" tutorial at the May 2015 Embedded Vision Summit. Video and images are a key part of Internet traffic—think of all the data generated by social networking sites such as Facebook and Instagram—and this trend continues to grow.
Harris Gasparakis, OpenCV Manager at AMD, presents the "Understanding Adaptive Machine Learning Vision Algorithms and Implementing them on GPUs and Heterogeneous Platforms" tutorial at the May 2015 Embedded Vision Summit. Machine learning algorithms are pervasive in computer vision: from object detection to object tracking to full scene recognition, generative or discriminative learning dominates the space,
Here you’ll find a wealth of practical technical insights and expert advice to help you bring AI and visual intelligence into your products without flying blind.
1646 N. California Blvd.,
Suite 360
Walnut Creek, CA 94596 USA
