Because of the Nov. 14th submission deadline for this years IEEE Conference on Computer Vision and Pattern Recognition (CVPR) several big image-recognition papers are coming out this week:
From Andrej Karpathy and Li Fei-Fei of Stanford:
We present a model that generates free-form natural language descriptions of image regions. Our model leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between text and visual data. Our approach is based on a novel combination of Convolutional Neural Networks over image regions, bidirectional Recurrent Neural Networks over sentences, and a structured objective that aligns the two modalities through a multimodal embedding. We then describe a Recurrent Neural Network architecture that uses the inferred alignments to learn to generate novel descriptions of image regions. We demonstrate the effectiveness of our alignment model with ranking experiments on Flickr8K, Flickr30K and COCO datasets, where we substantially improve on the state of the art. We then show that the sentences created by our generative model outperform retrieval baselines on the three aforementioned datasets and a new dataset of region-level annotations... (website with examples) (full paper)
From Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan at Google:
From Ryan Kiros, Ruslan Salakhutdinov, Richard S. Zemel at University of Toronto:
Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models (full paper)
From Junhua Mao, Wei Xu, Yi Yang, Jiang Wang and Alan L. Yuille at Baidu Research/UCLA:
Explain Images with Multimodal Recurrent Neural Networks (full paper)
From Jeff Donahue, Lisa Anne Hendricks, Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, and Trevor Darrell at UT Austin, UMass Lowell and UC Berkeley:
Long-term Recurrent Convolutional Networks for
Visual Recognition and Description (full paper)
All these came from this Hacker News discussion.
DJI's new Inspire 1 with 4K camera($2899 USD from DJI):
Hovering Accuracy (GPS Mode)
|Vertical: 1.6' / 0.5 m
Horizontal: 8.2' / 2.5 m
|Maximum Angular Velocity||Pitch: 300°/s
|Maximum Tilt Angle||35°/s|
|Maximum Ascent/Descent Speed||Ascent: 16.4 fps / 5 m/s
Descent: 13.1 fps / 4 m/s
|Maximum Speed||72.2 fps / 22 m/s (Attitude mode; no wind)|
|Maximum Flight Altitude||14,764' / 4,500 m|
|Maximum Wind Speed Resistance||32.8 fps / 10 m/s|
|Maximum Flight Time||Up to 18 minutes|
|Sensor||Sony EXMOR 1/2.3" CMOS|
|Lens||Field of View: 94°
Focal Length (35 mm Equivalent): 20 mm
Design: 9 elements in 9 groups; aspherical lens element
Filters: Anti-distortion filter; UV filter
|Video Recording||UHD (4K):
4096 x 2160: 24p, 25p
3840 x 2160: 24p, 25p, 30p
1920 x 1080: 24p, 25p, 30p, 48p, 50p, 60p
1280 x 720: 24p, 25p, 30p, 48p, 50p, 60p
Maximum Biterate: 60 Mbp/s
|File Format||Photo: JPEG, DNG
Video: MP4 in a .MOV wrapper （MPEG-4 AVC/H.264）
|Recording Media||Type: microSD/SDHC/SDXC up to 64 GB
Speed: Class 10 or faster
|Photography Modes||Single shot
Burst: 3, 5, 7 frames per second (AEB: 3/5 frames per second; 0.7 EV bias)
|Operating Temperature||32 to 104°F / 0 to 40°C|
|Number of Axes||3-axis|
|Maximum Controlled Rotation Speed||Pitch: 120°/s
|Controlled Rotation Range||Pitch: -90° to +30°
|Angular Vibration Range||±0.03°|
|Output Power||Static: 9 W
In Motion: 11 W
|Operational Current||Static: 750 mA
In Motion: 900 mA
Video with required "Johnny Ives-alike" introductory speech:
From Project Beyond/Samsung:
Today we offer a sneak preview of Project Beyond,the world’s first true 3D 360˚ omniview camera. Beyond captures and streams immersive videos in stunning high-resolution 3D, and allows every user to enjoy their viewing experience in the way they see fit. It offers full 3D reconstruction in all directions, using stereo camera pairs combined with a top-view camera to capture independent left and right eye stereo pairs.
Project Beyond uses patent-pending stereoscopic interleaved capture and 3D-aware stitching technology to capture the scene just like the human eye, but in a form factor that is extremely compact. The innovative reconstruction system recreates the view geometry in the same way that the human eyes see, producing unparalleled 3D perception.
Project Beyond is not a product, but one of the many exciting projects currently being developed by the Think Tank Team, an advanced research team within Samsung Research America. This is the first operational version of the device, and just a taste of what the final system we are working on will be capable of. Once complete, we hope to deploy Project Beyond around the world to beautiful and noteworthy locations and events, and allow users to experience those locations as if they were really there. The camera system can stream real time events, as well as store the data for future viewing... (website)
Atlas robot at IHMC standing on a stack of cinder blocks doing various poses. Robot is built by Boston Dynamics.
International FPV Multicopter Racing League:
In the spec class, competitors must use a quadcopter with 2300Kv motors, 3S LiPo and 5" props. This is to ensure a level playing field amongst competitors with different budgetary constraints.
10 points will be awarded for 1st place, 8 points for 2nd place, 5 points for 3rd place and 1 point for 4th place. These results will be recorded on the regional leaderboard, with the champions at the end of each season being invited to a national competition.
Throughout the course there will be obstacles such as hoops. Missing an obstacle will incur a time penalty. These obstacles should be made clearly visible with brightly-colored material or flashing lights...
Long article about Rodney Brooks co-founder of Rethink and former CTO at iRobot:
...Brooks cofounded the bedford-based iRobot in 1990, and his motivation, he explains, had something to do with vanity: “My thoughts on my self-image at the time was that I didn’t really want to be remembered for building insects.” Then he pauses for a moment and laughs. “But after that I started building vacuum-cleaning robots. And now there is a research group using Baxter to open stool samples. So now it’s shit-handling robots. I think maybe I should have quit while I was ahead. You know, that’s something no one ever says: ‘I hope my kid grows up to open stool samples... (full article)
Paracosm, a cloud-based software company, raised 3.3 million in seed round funding to further its mission to 3D-ify the world. The round, led by Atlas Venture, includes contributions from iRobot, Osage University Partners, BOLDstart Ventures, New World Angels, Deep Fork Capital and a number of angel investors.
Paracosm's advanced three-dimensional reconstruction technologies create digital models of physical spaces. When shared with machines, these models serve as blueprints which provide robots and applications a greater sense of awareness and understanding of the physical world. Such technologies are valuable for robotics, video game development, special effects, indoor navigation applications, and for the improvement of both virtual and augmented reality experiences... (full press release)
From MegaBots Kickstarter:
The mad scientists at MegaBots, Inc. have been zealously working on the prototypes and final design of 15-foot-tall, 15,000-pound, walking humanoid combat robots with giant, modular pneumatic cannons for arms. A driver-and-gunner team pilot each MegaBot in a battle against other MegaBots, vehicles, and a variety of other defenses and obstacles in live-action combat – the likes of which the world has only dreamed of through video games and movies...
...At our minimum funding level ($1.8M), we can build two robots. They’ll duke it out in an epic 1-on-1 deathmatch tournament. At higher funding levels, we can build more MegaBots and unlock the gameplay options you know and love: team deathmatches, free-for-alls, king of the hill, capture the flag, home base capture, escort missions, and more! (Kickstarter)
From Grabit Inc.:
Grabit technology eliminates the need for part-specific grippers and minimizes gripper changeover, dramatically reducing costs and downtime.
Grabit grippers offer scratch and smudge-free handling with its clean grasping and eliminates the need to remove residue left by vacuum cups. Grabit’s uniform grasping effect eliminates high “point stresses” on large format glass sheets.
Low Energy & Quiet Operations
Grabit products operate at ultra-low energy levels providing cost savings and enabling mobile robot applications, and also offer quiet operations improving factory conditions and supporting the adoption of collaborative robots... (homepage)
From Brian Benchoff at Hack A Day:
The FTDI FT232 chip is found in thousands of electronic baubles, from Arduinos to test equipment, and more than a few bits of consumer electronics. It’s a simple chip, converting USB to a serial port, but very useful and probably one of the most cloned pieces of silicon on Earth. Thanks to a recent Windows update, all those fake FTDI chips are at risk of being bricked. This isn’t a case where fake FTDI chips won’t work if plugged into a machine running the newest FTDI driver; the latest driver bricks the fake chips, rendering them inoperable with any computer.
Reports of problems with FTDI chips surfaced early this month, with an explanation of the behavior showing up in an EEVblog forum thread. The new driver for these chips from FTDI, delivered through a recent Windows update, reprograms the USB PID to 0, something Windows, Linux, and OS X don’t like. This renders the chip inaccessible from any OS, effectively bricking any device that happens to have one of these fake FTDI serial chips... (full story with workaround solution)
From Japan Times:
iRobot Unveils Its First Multi-Robot Tablet Controller for First Responders, Defense Forces and Industrial Customers
The uPoint MRC system runs an Android-based app that standardizes the control of any robot within the iRobot family of unmanned vehicles. Utilizing the same intuitive touchscreen technology in use today on millions of digital devices, the uPoint MRC system simplifies robot operations including driving, manipulation and inspection, allowing operators to focus more on the mission at hand... (full press release)
From NASA, Google's Project Tango, and Top Coders:
Welcome to the NASA Free Flying Robot Mission Patch & Naming Challenge sponsored by the NASA Tournament Lab!
In 2017, NASA is aiming to launch a robot that will be used on-board the International Space Station (ISS). The robot has been tentatively called the “Free Flying Robot”. Not that catchy, right?
So here’s where NASA needs your help – we need the Topcoder community to help design a custom mission patch AND develop a name for the Free Flying Robot.
So what is a Free Flying Robot? It’s a robot that is capable of functioning autonomously, but can also be controlled by a flight crew on-board the ISS or from Earth. It can conduct zero gravity robotics experiments, carry mobile sensors such as an RFID reader for logging inventory & inspect items using a built in camera
Currently on the ISS there are robotic devices called “SPHERES” (Synchronized Position Hold, Engage, Reorient, Experimental Satellites), and the new Free Flyer Robot program is being seen as a step forward in the use of robotic devices in spaceflight... (submission form)
From french quad racing association Airgonay:
Records 196 to 210 of 516