DeepLens by @amazon is now in pre-sale: https://aws.amazon.com/en/deeplens/
Amazon Web Services, Inc.
AWS DeepLens – Deep learning enabled video camera for developers - AWS
AWS DeepLens helps put deep learning in the hands of developers, with a fully programmable video camera, tutorials, code, and pre-trained models designed to expand deep learning skills.
A new class from MIT to start with the practice of deep learning through the applied theme of building a self-driving car: https://selfdrivingcars.mit.edu/
Researchers at University of Illinois create adversarial face pattern that blocks neural network face detector (Faster RCNN): https://arxiv.org/abs/1712.02494
But our face model still perfectly works: http://www.vision-ary.net/2015/03/largest-boosted-cascades-opencv-lbp-haar-hog/
#deeplearning #machinelearning #ArtificialIntelligence
But our face model still perfectly works: http://www.vision-ary.net/2015/03/largest-boosted-cascades-opencv-lbp-haar-hog/
#deeplearning #machinelearning #ArtificialIntelligence
Vision-ary
HAAR LBP HOG Cascades for OpenCV – updated 2021 - Vision-ary
Introduction
In the last years, Haar LBP and HOG cascades for OpenCV became popular thanks to the even more satisfying detection capabilities of a wide range of objects. The success is motivated by the efficiency and the capability of this approach to detect…
In the last years, Haar LBP and HOG cascades for OpenCV became popular thanks to the even more satisfying detection capabilities of a wide range of objects. The success is motivated by the efficiency and the capability of this approach to detect…
Eye In-painting with Exemplar Generative Adversarial Networks (ExGANs) from @facebook research | https://bdol.github.io/exemplar_gans/
The city of Milan deploy the first massive augmented experience in the wild for the urban arts. Milan always the avant-garde for arts, technology and social innovation.
#augmentedreality #deeplearning #mixedreality
#augmentedreality #deeplearning #mixedreality
"Joint Background Reconstruction and Foreground Segmentation via A Two-stage Convolutional Neural Network
" outperform by 4.9% the current state of the art in foreground detection | https://arxiv.org/pdf/1707.07584.pdf
#paper #deeplearning
" outperform by 4.9% the current state of the art in foreground detection | https://arxiv.org/pdf/1707.07584.pdf
#paper #deeplearning
👍1
AR smartglasses headset: Magic Leap One lightfield AR headset "Creator Edition" includes Lightpack and Control (6 DOF controller) | Ready for the market at the beginning of 2018.
the #MagicLeap glasses will cost approx. 2,500$
Further improvements in the DNN module include faster R-CNN support, Javascript bindings and acceleration of OpenCL implementation.
#OpenCV 3.4 straight to #DeepLearning | https://opencv.org/opencv-3-4.html
#OpenCV 3.4 straight to #DeepLearning | https://opencv.org/opencv-3-4.html
voidAR: the Chinese alternative to Vuforia | recognizing and tracking the target in a massive number of images (unlimited).
https://www.voidar.net/uploads/%E3%80%90Demo%E6%BC%94%E7%A4%BA%E3%80%91%E7%9C%9F%E5%AE%9E%E7%8E%AF%E5%A2%83%E8%9E%8D%E5%90%88%EF%BC%88%E9%BE%99%EF%BC%89_%E5%A4%AA%E8%99%9AAR_MRbeta_20161226.mp4
https://www.voidar.net/uploads/%E3%80%90Demo%E6%BC%94%E7%A4%BA%E3%80%91%E7%9C%9F%E5%AE%9E%E7%8E%AF%E5%A2%83%E8%9E%8D%E5%90%88%EF%BC%88%E9%BE%99%EF%BC%89_%E5%A4%AA%E8%99%9AAR_MRbeta_20161226.mp4