The field of deep learning has been suffering from what you might call a Big Data fallacy, the belief that more and more data is always a good thing. It may be time to focus on quality rather than just quantity. "There's a very fundamental problem that a lot of AI faces," said Andrew Ng, founder and CEO of Landing AI, a startup working to perfect the technology for industrial uses, in an interview with ZDNet this week. "A lot of AI is focused on maximizing the number of calories, which works up to a certain point," he said. "And sometimes you do have a lot of data, but when you have a small data set, it's more the quality of the data rather than the sheer volume."
Advances in 3D imaging have allowed vision users to overcome some challenging inspection tasks. In the machine vision marketplace, 3D imaging continues to mature, tackling applications 2D imaging cannot. "In a manufacturing setting, the fusion of 2D with 3D is necessary to measure how well components go together into an assembly and assess the product for final fit, finish, and packaging," says Terry Arden, CEO of LMI Technologies. According to David Dechow, Principal Vision Systems Architect at Integro Technologies, a systems integrator specializing in machine vision technologies with broad experience in helping companies implement 3D and 2D imaging for industrial automation, accuracy has improved as well. And with inspection tasks in 3D space, which may include measurement or reconstruction, precision is even more essential than with most tasks in robotic guidance or bin picking.
In recent artificial intelligence (AI) research, convolutional neural networks (CNNs) can create artificial agents capable of self-learning. Self-learning autonomous moving objects utilize machine vision techniques based on processing and recognizing objects in digital images. Afterwards, deep reinforcement learning (Deep-RL) is applied to understand and learn intelligent actions and controls. The objective of our research is to study methods and designs on how machine vision and deep machine learning algorithms can be implemented in a virtual world (e.g., a computer game) for moving objects (e.g., vehicles or aircrafts) to improve their navigation and detection of threats in real life. In this paper, we create a framework for generating and using data from computer games to be used in CNNs and Deep-RL to perform intelligent actions. We show the initial results of applying the framework and identify various military applications that may benefit from this research.
Computer vision is the field of study surrounding how computers see and understand digital images and videos. Computer vision spans all tasks performed by biological vision systems, including "seeing" or sensing a visual stimulus, understanding what is being seen, and extracting complex information into a form that can be used in other processes. This interdisciplinary field simulates and automates these elements of human vision systems using sensors, computers, and machine learning algorithms. Computer vision is the theory underlying artificial intelligence systems' ability to see and understand their surrounding environment. There are many examples of computer vision applied because its theory spans any area where a computer will see its surroundings in some form.
TL:DR: Get an extra pair of eyes with the TOKK CAM C2: Discreet Day/Night Vision Camera for $64.99, a 18% savings. The TOKK CAM C2: Discreet Day/Night Vision Camera is a camera worth considering. It connects to Wi-Fi and has a built-in microphone, so you can easily pick up high-quality sound wherever you take it -- whether that's your car, your home, or even your bike. It also has night vision, which means it can capture video in dark conditions. The TOKK CAM C2 comes with a free iOS and Android app, which gives you wireless control of the camera on your phone. The battery will run for 90 minutes on a full charge, so make sure to have the charger nearby in case you're planning on capturing longer recordings.