Object detectionObject detection is a computer technology related to computer vision and that deals with detecting instances of semantic objects of a certain class (such as humans, buildings, or cars) in digital images and videos. Well-researched domains of object detection include face detection and pedestrian detection. Object detection has applications in many areas of computer vision, including and video surveillance. It is widely used in computer vision tasks such as , vehicle counting, activity recognition, face detection, face recognition, video object co-segmentation.
Convolutional neural networkConvolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.
Deep learningDeep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.
Object co-segmentationIn computer vision, object co-segmentation is a special case of , which is defined as jointly segmenting semantically similar objects in multiple images or video frames. It is often challenging to extract segmentation masks of a target/object from a noisy collection of images or video frames, which involves object discovery coupled with . A noisy collection implies that the object/target is present sporadically in a set of images or the object/target disappears intermittently throughout the video of interest.
Deep reinforcement learningDeep reinforcement learning (deep RL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. RL considers the problem of a computational agent learning to make decisions by trial and error. Deep RL incorporates deep learning into the solution, allowing agents to make decisions from unstructured input data without manual engineering of the state space. Deep RL algorithms are able to take in very large inputs (e.g.
Face detectionFace detection is a computer technology being used in a variety of applications that identifies human faces in digital images. Face detection also refers to the psychological process by which humans locate and attend to faces in a visual scene. Face detection can be regarded as a specific case of object-class detection. In object-class detection, the task is to find the locations and sizes of all objects in an image that belong to a given class. Examples include upper torsos, pedestrians, and cars.
Caffe (software)Caffe (Convolutional Architecture for Fast Feature Embedding) is a deep learning framework, originally developed at University of California, Berkeley. It is open source, under a BSD license. It is written in C++, with a Python interface. Yangqing Jia created the Caffe project during his PhD at UC Berkeley. It is currently hosted on GitHub. Caffe supports many different types of deep learning architectures geared towards and . It supports CNN, RCNN, LSTM and fully-connected neural network designs.
Image segmentationIn and computer vision, image segmentation is the process of partitioning a into multiple image segments, also known as image regions or image objects (sets of pixels). The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. More precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain characteristics.
Neural architecture searchNeural architecture search (NAS) is a technique for automating the design of artificial neural networks (ANN), a widely used model in the field of machine learning. NAS has been used to design networks that are on par or outperform hand-designed architectures. Methods for NAS can be categorized according to the search space, search strategy and performance estimation strategy used: The search space defines the type(s) of ANN that can be designed and optimized. The search strategy defines the approach used to explore the search space.
Video content analysisVideo content analysis or video content analytics (VCA), also known as video analysis or video analytics (VA), is the capability of automatically analyzing video to detect and determine temporal and spatial events. This technical capability is used in a wide range of domains including entertainment, video retrieval and video browsing, health-care, retail, automotive, transport, home automation, flame and smoke detection, safety, and security. The algorithms can be implemented as software on general-purpose machines, or as hardware in specialized video processing units.
Q-learningQ-learning is a model-free reinforcement learning algorithm to learn the value of an action in a particular state. It does not require a model of the environment (hence "model-free"), and it can handle problems with stochastic transitions and rewards without requiring adaptations. For any finite Markov decision process (FMDP), Q-learning finds an optimal policy in the sense of maximizing the expected value of the total reward over any and all successive steps, starting from the current state.
Coronal loopIn solar physics, a coronal loop is a well-defined arch-like structure in the Sun's atmosphere made up of relatively dense plasma confined and isolated from the surrounding medium by magnetic flux tubes. Coronal loops begin and end at two footpoints on the photosphere and project into the transition region and lower corona. They typically form and dissipate over periods of seconds to days and may span anywhere from in length. Coronal loops are often associated with the strong magnetic fields located within active regions and sunspots.
Solar phenomenaSolar phenomena are natural phenomena which occur within the atmosphere of the Sun. These phenomena take many forms, including solar wind, radio wave flux, solar flares, coronal mass ejections, coronal heating and sunspots. These phenomena are believed to be generated by a helical dynamo, located near the center of the Sun's mass, which generates strong magnetic fields, as well as a chaotic dynamo, located near the surface, which generates smaller magnetic field fluctuations.
Stellar coronaA corona ( coronas or coronae) is the outermost layer of a star's atmosphere. It consists of plasma. The Sun's corona lies above the chromosphere and extends millions of kilometres into outer space. It is most easily seen during a total solar eclipse, but it is also observable with a coronagraph. Spectroscopic measurements indicate strong ionization in the corona and a plasma temperature in excess of 1 000 000 kelvins, much hotter than the surface of the Sun, known as the photosphere. Corona is, in turn, derived .
SkylabSkylab was the first United States space station, launched by NASA, occupied for about 24 weeks between May 1973 and February 1974. It was operated by three separate three-astronaut crews: Skylab 2, Skylab 3, and Skylab 4. Major operations included an orbital workshop, a solar observatory, Earth observation, and hundreds of experiments. Unable to be re-boosted by the Space Shuttle, which was not ready until 1981, Skylab's orbit eventually decayed, and it disintegrated in the atmosphere on July 11, 1979, scattering debris across the Indian Ocean and Western Australia.
X-ray astronomyX-ray astronomy is an observational branch of astronomy which deals with the study of X-ray observation and detection from astronomical objects. X-radiation is absorbed by the Earth's atmosphere, so instruments to detect X-rays must be taken to high altitude by balloons, sounding rockets, and satellites. X-ray astronomy uses a type of space telescope that can see x-ray radiation which standard optical telescopes, such as the Mauna Kea Observatories, cannot.
