Personal Profile

Video Processing

Teaching an AI to Detect Key Actors in Multi-person Videos

Teaching an AI to Detect Key Actors in Multi-person Videos

Teaching an AI to Detect Key Actors in Multi-person Videos

Researchers from Google and Stanford have taught their computer vision model to detect the most important person in a multi-person video scene – for example, who the shooter is in a basketball game which typically contains dozens or hundreds of people in a scene.

Using 20 Tesla K40 GPUs and the cuDNN-accelerated Tensorflow deep learning framework to train their recurrent neural network on 257 NCAA basketball games from YouTube, an attention mask selects which of the several people are most relevant to the action being performed, then tracks relevance of each object as time proceeds. The team published a paper detailing more of their work.

The distribution of attention for the model with tracking, at the beginning of “free-throw success”. The attention is concentrated at a specific defender’s position. Free-throws have a distinctive defense formation, and observing the defenders can be helpful as shown in the sample images in the top row.

The distribution of attention for the model with tracking, at the beginning of “free-throw success”. The attention is concentrated at a specific defender’s position. Free-throws have a distinctive defense formation, and observing the defenders can be helpful as shown in the sample images in the top row.

Over time the system can identify not only the most important actor, but potential important actors and the events with which they are associated – such as, the ability to understand the player going up for a layup could be important, but that the most important player is the one who then blocks the shot.

New Deep Learning Method Enhances Your Selfies

New Deep Learning Method Enhances Your Selfies

New Deep Learning Method Enhances Your Selfies

Researchers from Adobe Research and The Chinese University of Hong Kong created an algorithm that automatically separates subjects from their backgrounds so you can easily replace the background and apply filters to the subject.

Their research paper mentions there are good user-guided tools that support manually creating masks to separate subjects from the background, but the “tools are tedious and difficult to use, and remain an obstacle for casual photographers who want their portraits to look good.”

A highly accurate automatic portrait segmentation method allows many portrait processing tools to be fully automatic.

A highly accurate automatic portrait segmentation method allows many portrait processing tools to be fully automatic.

Using a TITAN X GPU and the cuDNN-accelerated Caffe deep learning framework, the researchers trained their convolutional neural network on 1,800 portrait images from Flickr. Their GPU-accelerated method was 20x faster than a CPU-only approach.

Portrait video segmentation is next on the radar for the researchers.

Facial Recognition Software Helping Caterpillar Identify Sleepy Operators

Facial Recognition Software Helping Caterpillar Identify Sleepy Operators

Facial Recognition Software Helping Caterpillar Identify Sleepy Operators

Operator fatigue can potentially be a fatal problem for Caterpillar employees driving the massive mine trucks on long, repetitive shifts throughout the night.

Caterpillar recognized this and joined forces with Seeing Machines to install their fatigue detection software in thousands of mining trucks worldwide. Using NVIDIA TITAN X and GTX 1080 GPUs along with the cuDNN-accelerated Theano, TensorFlow and Caffe deep learning frameworks, the Australian-based tech company trained their software for face tracking, gaze tracking, driver attention region estimation, facial recognition, and fatigue detection.

On-board the truck, a camera, speaker and light system are used to monitor the driver and once a potential “fatigue event” is detected, an alarm sounds in the truck and a video clip of the driver is sent to a 24-hour “sleep fatigue center” at the Caterpillar headquarters.

Facial Recognition Software Helping Caterpillar Identify Sleepy Operators

Facial Recognition Software Helping Caterpillar Identify Sleepy Operators

“This system automatically scans for the characteristics of microsleep in a driver,” Sal Angelone, a fatigue consultant at the company, told The Huffington Post, referencing the brief, involuntary pockets of unconsciousness that are highly dangerous to drivers. “But this is verified by a human working at our headquarters in Peoria.”

In the past year, Caterpillar referenced two instances – in one, a driver had three fatique events within four hours and he was contacted onsite and forced to take a nap. In another, a night shift truck driver who experienced a fatique event realized it was a sign of sleep disorder and asked his management for medical assistance.

It’s a matter of time before this technology is incorporated into every car on the road.

World’s Fastest Commercial Drone Powered by Jetson TX1

World’s Fastest Commercial Drone Powered by Jetson TX1

World’s Fastest Commercial Drone Powered by Jetson TX1

Records were made to be broken, and drones are no exception. Teal Drones unveiled its first production product, Teal, a Jetson TX1-powered drone capable of flight speeds in excess of 70 mph. That makes Teal the world’s fastest production drone. 

But Teal is as much a flying supercomputer platform as it is “just” a drone. Set to ship with an SDK and its own operating system — Teal OS —Teal is designed with user- and developer-friendliness firmly in mind. The drone will ship fully assembled and ready to fly straight out of the box, with the SDK providing access to software and hardware development via onboard USB ports. Built for a wide variety of uses, from drone racing to industrial applications, Teal features an onboard camera for still image and video capture, integrated storage and a microSD expansion slot, and the full visual computing power of the NVIDIA Jetson ecosystem for machine learning, image recognition, and autonomous navigation applications.

George Matus’ startup has built the world’s fastest production drone.

George Matus’ startup has built the world’s fastest production drone.

The company’s backstory is nearly as compelling as its first product. Teal Drones was founded by George Matus, Jr. Matus built his first drone from scratch at age 14, was selected as a Thiel Fellow at 16, and as CEO of Teal Drones, built the fastest production drone in the world at the ripe old age of 18. To hear him tell it, the drone itself is just the beginning of his vision for Teal.

AI Build Smart Home Hub Smart Home Hub Brings Artificial Intelligence Into Your Home

Smart Home Hub Brings Artificial Intelligence Into Your Home

Smart Home Hub Brings Artificial Intelligence Into Your Home

A new AI-powered device will be able to replace all of your various smart home control apps, as well as being able to recognize specific people and respond to a range of emotions and gestures.

AI Build is a London-based startup focused on making your smart home more natural and intuitive. Powered by an NVIDIA Jetson TX1 and six cameras, the aiPort keeps track of your daily activities and uses this knowledge to get better at helping you. It learns your preferences, recognizes your body language, and adapts its actions with your comfort in mind.

The startup plans to launch a crowd-funding campaign later this year toand sell the device for about $1,000 each.

Autonomous Robot Starts Work as Office Manager

Autonomous Robot Starts Work as Office Manager

Autonomous Robot Starts Work as Office Manager

Programmed with the latest artificial intelligence software, Betty will spend the next two months working as an office manager at Transport Systems Catapult monitoring staff and check environmental conditions.

The robot, developed by engineers at the University of Birmingham, uses NVIDIA GPUs for various forms of computer vision — like feature extraction — and 3D image processing to create a map of the surrounding area. This allows Betty to identify desks, chairs and other objects that she must negotiate while moving around the office, and observe her colleague’s movement through activity recognition.

“For robots to work alongside humans in normal work environments it is important that they are both robust enough to operate autonomously without expert help, and that they learn to adapt to their environments to improve their performance,” said Dr Nick Hawes, from the School of Computer Science at the University of Birmingham. “Betty demonstrates both these abilities in a real working environment: we expect her to operate for two months without expert input, whilst using cutting-edge AI techniques to increase her understanding of the world around her.”

Betty is part of an EU-funded STRANDS project where robots are learning how to act intelligently and independently in real-world environments while understanding 3D space.

AI-Powered Flying Camera to Replace Your Selfie Stick

AI-Powered Flying Camera to Replace Your Selfie Stick

AI-Powered Flying Camera to Replace Your Selfie Stick

After raising $25 million in funding, Beijing-based ZeroZero Robotics came out of stealth mode and launched their Hover Camera just days before the GMIC Beijing 2016 trade show, the ‘CES of China.’

Co-founder MQ Wang, a Stanford PhD alum focused on machine learning and natural language processing, was inspired to create the autonomous Hover Camera after watching a documentary about a man who walked 1600 miles solo across Australia.

Using a machine learning model trained on an NVIDIA Tesla K40 GPU, the camera automatically tracks your face to take photos and capture videos wherever you go.

AI-Powered Flying Camera to Replace Your Selfie Stick

AI-Powered Flying Camera to Replace Your Selfie Stick

“We wanted the user experience to be very natural — easy to use,” MQ told Mashable. “We wanted to make sure the learning curve for users is minimum. So there is no remote control or anything. There’s no calibration process.”

The final version of the product will be released this summer.

Real-Time Pedestrian Detection using Cascades of Deep Neural Networks

Real-Time Pedestrian Detection using Cascades of Deep Neural Networks

Real-Time Pedestrian Detection using Cascades of Deep Neural Networks

Google Research presents a new real-time approach to object detection that exploits the efficiency of cascade classifiers with the accuracy of deep neural networks. Pedestrian detectors is very important as it relates to a variety of applications including advanced driver assistance systems, or surveillance systems. The need for very high-accurate and real-time speed is crucial that can be relied on and are fast enough to run on systems with limited compute power.

Real-Time Pedestrian Detection using Cascades of Deep Neural Networks

Real-Time Pedestrian Detection using Cascades of Deep Neural Networks

The research team combined a fast cascade with a cascade of deep neural networks which is both very fast, running in real-time at 67 milliseconds on GPU per image or 15 frames per second. Their approach was trained using the publicly available ‘cuda-convnet2’ code  running on an NVIDIA Tesla K20 GPU.

Detecting Objects from Space with Artificial Intelligence

Detecting Objects from Space with Artificial Intelligence

Detecting Objects from Space with Artificial Intelligence

To reveal deeper insights into important activities taking place around the world, DigitalGlobe’s advanced satellite constellation collects nearly 4 million km2 of high-resolution earth imagery each day.

The company announced they will now rely on NVIDIA GPUs and deep learning to automatically identify objects such as airplanes, vehicles, and gray elephants, as well as to detect patterns from their massive volumes of big data satellite imagery.

Object recognition results from DigitalGlobe’s deep learning software

Object recognition results from DigitalGlobe’s deep learning software

This technology has a wide variety of uses within defense and intelligence, civil agencies, mapping and analysis, environmental monitoring, oil and gas exploration, infrastructure management, Internet portals, and navigation technology.



Popular Pages
Popular posts
Interested
About me

My name is Sayed Ahmadreza Razian and I am a graduate of the master degree in Artificial intelligence .
Click here to CV Resume page

Related topics such as image processing, machine vision, virtual reality, machine learning, data mining, and monitoring systems are my research interests, and I intend to pursue a PhD in one of these fields.

جهت نمایش صفحه معرفی و رزومه کلیک کنید

My Scientific expertise
  • Image processing
  • Machine vision
  • Machine learning
  • Pattern recognition
  • Data mining - Big Data
  • CUDA Programming
  • Game and Virtual reality

Download Nokte as Free


Coming Soon....

Greatest hits

Gravitation is not responsible for people falling in love.

Albert Einstein

Anyone who has never made a mistake has never tried anything new.

Albert Einstein

One day you will wake up and there won’t be any more time to do the things you’ve always wanted. Do it now.

Paulo Coelho

It’s the possibility of having a dream come true that makes life interesting.

Paulo Coelho

You are what you believe yourself to be.

Paulo Coelho

Waiting hurts. Forgetting hurts. But not knowing which decision to take can sometimes be the most painful.

Paulo Coelho

Imagination is more important than knowledge.

Albert Einstein

The fear of death is the most unjustified of all fears, for there’s no risk of accident for someone who’s dead.

Albert Einstein


Site by images
Statistics
  • 2,319
  • 10,075
  • 92,535
  • 25,499
Recent News Posts