Bruce Maxwell, Director of Research at Tandent Vision Science, presents the “A Physics-based Approach to Removing Shadows and Shading in Real Time” tutorial at the May 2018 Embedded Vision Summit. Shadows cast on ground surfaces can create false features and modify the color and appearance of real features, masking important information used by autonomous vehicles, […]
Lina Karam, Professor and Computer Engineering Director at Arizona State University, presents the “Generative Sensing: Reliable Recognition from Unreliable Sensor Data” tutorial at the May 2018 Embedded Vision Summit. While deep neural networks (DNNs) perform on par with – or better than – humans on pristine high-resolution images, DNN performance is significantly worse than human
June 19, 2018 — Today we are releasing TensorRT 4 with capabilities for accelerating popular inference applications such as neural machine translation, recommender systems and speech. You also get an easy way to import models from popular deep learning frameworks such as Caffe 2, Chainer, MxNet, Microsoft Cognitive Toolkit and PyTorch through the ONNX format.
NVIDIA Releases TensorRT 4 Read More +
June 19, 2018 — Today at the Computer Vision and Pattern Recognition Conference in Salt Lake City, Utah, NVIDIA is kicking off the conference by demonstrating an early release of Apex, an open-source PyTorch extension that helps users maximize deep learning training performance on NVIDIA Volta GPUs. Inspired by state-of-the-art mixed precision training in translational
Introducing Apex: PyTorch Extension with Tools to Realize the Power of Tensor Cores Read More +
June 19, 2018 — Today at Computer Vision and Pattern Recognition (CVPR) conference, we’re making available new libraries for data augmentation and image decoding. NVIDIA DALI: A GPU-accelerated data augmentation and image loading library for optimizing data pipelines of deep learning frameworks NVIDIA nvJPEG: A high-performance GPU-accelerated library for JPEG decoding Computer vision applications powered
Announcing NVIDIA DALI and NVIDIA nvJPEG Read More +
Anirudh Koul, Senior Data Scientist, and Jin Yamamoto, Principal Program Manager, both from Microsoft, present the “Infusing Visual Understanding in Cloud and Edge Solutions Using State Of-the-Art Microsoft Algorithms” tutorial at the May 2018 Embedded Vision Summit. Microsoft offers its state-of-the-art computer vision algorithms, used internally in several products, through the Cognitive Services cloud APIs.
Basler introduces a new ace U camera, the only one in the market that enables a 1:1 replacement of cameras that use Sony's ICX618 CCD sensor. The ace U has the same optical format, resolution, speed and pixel size as the cameras that include the popular but discontinued sensor ICX618 from Sony. Ahrensburg, June 21,
Paul Maria Zalewski, Product Line Manager at Allied Vision Technologies, presents the “A New Generation of Camera Modules: A Novel Approach and Its Benefits for Embedded Systems” tutorial at the May 2018 Embedded Vision Summit. Embedded vision systems have typically relied on low-cost image sensor modules with a MIPI CSI-2 interface. Now, machine vision camera
Tuesday, June 19, 2018 — FLIR today announced the upcoming release of a first-of-its-kind, free machine learning thermal dataset for Advanced Driver Assistance Systems (ADAS) and self-driving vehicle researchers, developers, and auto manufacturers. The starter dataset features a compilation of more than 10,000 annotated thermal images of people, cars, other vehicles, bicycles and dogs in
Free FLIR Starter Thermal Dataset for Autonomous Vehicle Testing Read More +
This blog post was originally published at NVIDIA's website. It is reprinted here with the permission of NVIDIA. Researchers from NVIDIA developed a deep learning-based system that can produce high-quality slow-motion videos from a 30-frame-per-second video, outperforming various state-of-the-art methods that aim to do the same. The researchers will present their work at the annual
Transforming Standard Video Into Slow Motion with AI Read More +
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.
Berkeley Design Technology, Inc.
PO Box #4446
Walnut Creek, CA 94596
