A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
From Computer Vision Freiburg: Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated dataset. The present paper extends the concept of optical flow estimation via convolutional networks to disparity and scene flow estimation. To this end, we propose three synthetic stereo video datasets with sufficient realism, variation, and size to successfully train large networks. Our datasets are the first large-scale datasets to enable training and evaluating scene flow methods. Besides the datasets, we present a convolutional network for real-time disparity estimation that provides state-of-the-art results. By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network. his video shows impressions from various parts of our dataset, as well as state-of-the-art realtime disparity estimation results produced by one of our new CNNs... (full paper)
Kagan Pittman for Engineering.com: As Chinese companies move to expand their market share in industrial robotics, so too are companies in the West, with some of the biggest power-plays coming from R&D departments. A recent report by Technavio predicts that global R&D spending in the robotics industry will grow at a CAGR of more than 17 percent between 2016-2020. Technavio analysts cite the following factors as key drivers in the growth of R&D spending: A race for robotics patents Demand for lower system engineering and installation costs Growing demand for industrial robots from non-automotive industries The report’s analysis considers market trends across user segments including: defense, healthcare, automotive, domestic, food and beverage, electricals, electronics, oil and gas, textiles and packaging. Cont'd...
Here is a summary of what Tradeshows, Conferences & Exhibitions to look forward to in the coming months.
In the long term, job roles will shift away from their traditional remits and evolve to meet the needs of the modern, automated workplace.
Caitlin Ju for The Stanford Daily: Stanford researchers in the Computational Vision and Geometry Lab have designed an autonomously navigating robot prototype that they say understands implicit social conventions and human behavior. Named “Jackrabbot” after the swift but cautious jackrabbit, the visually intelligent and socially amicable robot is able to maneuver crowds and pedestrian spaces. A white ball on wheels, the Jackrabbot is built on a Segway system and contains a computing unit and multiple sensors that acquire a 3-D structure of the surrounding environment. 360-degree cameras and GPS also enhance the robot’s navigation and detection capabilities. To interact smoothly in public settings, the robot has to know how to avoid someone in a natural way, how to yield the right-of-way and how to leave personal space, among other skills. Cont'd...
Robotic surgery has treated over 3 million patients
Encoders use different types of technologies to create a signal, including: mechanical, magnetic, resistive and optical - optical being the most common.
From Gizmag: Researchers at Siemens have created a new prototype electric motor specifically designed for aircraft that weighs in at just 50 kg (110 lb) and is claimed to produce about 260 kW (348 hp) at just 2,500 RPM. With a quoted power five times greater than any comparable powerplant, the new motor promises enough grunt to get aircraft with take-off weights of up to 1,800 kg (2 ton) off the ground... ... As a result, the new aircraft electric drive system achieves a claimed weight-to-performance ratio of 5 kW per kilogram. This ratio is an exceptional figure – especially if compared to similarly powerful industrial electric motors used in heavy machinery that produce less than 1 kW per kilogram, or even to more efficient electric motors for vehicles that generate around 2 kW per kilogram... (full article)
Manish Sablokk for IoTTech: Cutting-edge robots and other advanced smart machines are set to be added into the rapidly expanding Internet of Things, which is projected to reach 25 billion devices by 2020. Robotics has already been used in manufacturing to great effect for over a decade, performing delicate and precise tasks with a higher success rate than humans. With advancements such as 'deep learning' robots, delivery drones and ubiquitous knowledge-sharing between machines, widespread robotics adoption is becoming far more feasible. In healthcare, there are already robotic services in operation with automated pharmacy dispensing and robotic trolleys - robots that can navigate between floors and even call the lift using a Wi-Fi sensor. The hospitality sector has also been a keen adopter of robotics to deliver services and in education, robots are being deployed successfully as a tutor, tool or peer in learning activities, providing language, science and technology education. Cont'd...
It's important that your IT staff understand the impact of automation - more importantly, that it is not a replacement for your IT team.
The number of unique parts required is high - some 200 parts in the past year or so - but the volume in which each part is needed is low, often only one or two.
Raspberry Pi serves as the main controller board for the setup, capturing the images using the Pi Camera, controlling the Line LASER diode and providing control signals to the EasyDriver (Stepper Motor Driver).
ABIGAIL BEALL FOR MAILONLINE: Many people spend their childhood peering up into the vast expanse of the sky, dreaming of growing up to become an astronaut. But these dreams could be dashed as the idea of people venturing into space will one day become a distant memory, according to a report published today. Robots will eventually have enough capabilities to replace humans and other animals on space missions, experts have said. Many missions involving humans in space are dangerous and expensive. But for years robots have been sent to places humans could not venture, like the rovers venturing to the edges of our solar system. According to European Space Agency (Esa) Astronaut Roberto Vittori, who launched a paper on space robotics and autonomous systems, robots can help carry out these dangerous missions. Cont'd...
Recent servo motors are equipped with the encoder of 20 bits (1,048,576 steps) which has a very fine resolution. Because of this, errors due to the encoder installation accuracy have a huge effect on stopping accuracy.
2016, through mid-June, shows 56 startups received $427.5 million; and that 20 acquisitions have happened thus far totaling $4.53 bn (from the 11 reporting amounts involved).
Records 616 to 630 of 1766
App Your Sensor®! What would smartphones be without apps? They would be mobile phones that can't do much more than make phone calls and sending SMS. Apps turn smartphones into intelligent assistants with any number of different tasks. Transferred into the world of image processing, this app-based approach transforms cameras and sensors into customised, smart vision sensors.