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.
Computer visionComputer vision tasks include methods for , , and understanding digital images, and extraction of high-dimensional data from the real world in order to produce numerical or symbolic information, e.g. in the forms of decisions. Understanding in this context means the transformation of visual images (the input to the retina in the human analog) into descriptions of the world that make sense to thought processes and can elicit appropriate action.
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.
Self-driving carA self-driving car, also known as an autonomous car, driverless car, or robotic car (robo-car), is a car that is capable of traveling without human input. Self-driving cars use sensors to perceive their surroundings, such as optical and thermographic cameras, radar, lidar, ultrasound/sonar, GPS, odometry and inertial measurement units. Control systems interpret sensory information to create a three-dimensional model of the vehicle's surroundings.
Moon rockMoon rock or lunar rock is rock originating from Earth's Moon. This includes lunar material collected during the course of human exploration of the Moon, and rock that has been ejected naturally from the Moon's surface and landed on Earth as meteorites. Moon rocks on Earth come from four sources: those collected by six United States Apollo program crewed lunar landings from 1969 to 1972; those collected by three Soviet uncrewed Luna probes in the 1970s; those collected by the Chinese Lunar Exploration Program's uncrewed probes; and rocks that were ejected naturally from the lunar surface before falling to Earth as lunar meteorites.
Geology of the MoonThe geology of the Moon (sometimes called selenology, although the latter term can refer more generally to "lunar science") is quite different from that of Earth. The Moon lacks a true atmosphere, and the absence of free oxygen and water eliminates erosion due to weather. Instead, the surface is eroded much more slowly through the bombardment of the lunar surface by micrometeorites. It does not have any known form of plate tectonics, it has a lower gravity, and because of its small size, it cooled faster.
MoonThe Moon is Earth's only natural satellite. Its diameter is about one-quarter of Earth's (comparable to the width of Australia), making it the fifth largest satellite in the Solar System and the largest and most massive relative to its parent planet. It is larger than all known dwarf planets in the Solar System. The Moon is a planetary-mass object with a differentiated rocky body, making it a satellite planet under the geophysical definitions of the term. It lacks any significant atmosphere, hydrosphere, or magnetic field.
Activity recognitionActivity recognition aims to recognize the actions and goals of one or more agents from a series of observations on the agents' actions and the environmental conditions. Since the 1980s, this research field has captured the attention of several computer science communities due to its strength in providing personalized support for many different applications and its connection to many different fields of study such as medicine, human-computer interaction, or sociology.
Digital image processingDigital image processing is the use of a digital computer to process s through an algorithm. As a subcategory or field of digital signal processing, digital image processing has many advantages over . It allows a much wider range of algorithms to be applied to the input data and can avoid problems such as the build-up of noise and distortion during processing. Since images are defined over two dimensions (perhaps more) digital image processing may be modeled in the form of multidimensional systems.
Self-driving truckA self-driving truck, also known as an autonomous truck or robo-truck, is an application of self-driving technology aiming to create trucks that can operate without human input. Alongside light, medium, and heavy-duty trucks, many companies are developing self-driving technology in semi trucks to automate highway driving in the delivery process. In September 2022, Guidehouse Insights listed Waymo, Aurora, TuSimple, Gatik, PlusAI, Kodiak Robotics, Daimler Truck, Einride, Locomation, and Embark as the top 10 vendors in automated trucking.
Image analysisImage analysis or imagery analysis is the extraction of meaningful information from s; mainly from s by means of techniques. Image analysis tasks can be as simple as reading bar coded tags or as sophisticated as identifying a person from their face. Computers are indispensable for the analysis of large amounts of data, for tasks that require complex computation, or for the extraction of quantitative information.
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.
Oldest dated rocksThe oldest dated rocks formed on Earth, as an aggregate of minerals that have not been subsequently broken down by erosion or melted, are more than 4 billion years old, formed during the Hadean Eon of Earth's geological history. Meteorites that were formed in other planetary systems can pre-date Earth. Particles from the Murchison meteorite were dated in January 2020 to be 7 billion years old. Hadean rocks are exposed on Earth's surface in very few places, such as in the geologic shields of Canada, Australia, and Africa.
Transient lunar phenomenonA transient lunar phenomenon (TLP) or lunar transient phenomenon (LTP) is a short-lived light, color or change in appearance on the surface of the Moon. The term was created by Patrick Moore in his co-authorship of NASA Technical Report R-277 Chronological Catalog of Reported Lunar Events, published in 1968. Claims of short-lived lunar phenomena go back at least 1,000 years, with some having been observed independently by multiple witnesses or reputable scientists.
Edge detectionEdge detection includes a variety of mathematical methods that aim at identifying edges, curves in a at which the image brightness changes sharply or, more formally, has discontinuities. The same problem of finding discontinuities in one-dimensional signals is known as step detection and the problem of finding signal discontinuities over time is known as change detection. Edge detection is a fundamental tool in , machine vision and computer vision, particularly in the areas of feature detection and feature extraction.
Corner detectionCorner detection is an approach used within computer vision systems to extract certain kinds of features and infer the contents of an image. Corner detection is frequently used in motion detection, , video tracking, image mosaicing, panorama stitching, 3D reconstruction and object recognition. Corner detection overlaps with the topic of interest point detection. A corner can be defined as the intersection of two edges. A corner can also be defined as a point for which there are two dominant and different edge directions in a local neighbourhood of the point.
Pupillary distancePupillary distance (PD), more correctly known as interpupillary distance (IPD) is the distance in millimeters between the centers of each pupil. Distance PD is the separation between the visual axes of the eyes in their primary position, as the subject fixates on an infinitely distant object. Near PD is the separation between the visual axes of the eyes, at the plane of the spectacle lenses, as the subject fixates on a near object at the intended working distance. Intermediate PD is at a specified plane in between distance and near.
Training, validation, and test data setsIn machine learning, a common task is the study and construction of algorithms that can learn from and make predictions on data. Such algorithms function by making data-driven predictions or decisions, through building a mathematical model from input data. These input data used to build the model are usually divided into multiple data sets. In particular, three data sets are commonly used in different stages of the creation of the model: training, validation, and test sets.
Attention (machine learning)Machine learning-based attention is a mechanism mimicking cognitive attention. It calculates "soft" weights for each word, more precisely for its embedding, in the context window. It can do it either in parallel (such as in transformers) or sequentially (such as recursive neural networks). "Soft" weights can change during each runtime, in contrast to "hard" weights, which are (pre-)trained and fine-tuned and remain frozen afterwards. Multiple attention heads are used in transformer-based large language models.
Pedestrian detectionPedestrian detection is an essential and significant task in any intelligent video surveillance system, as it provides the fundamental information for semantic understanding of the video footages. It has an obvious extension to automotive applications due to the potential for improving safety systems. Many car manufacturers (e.g. Volvo, Ford, GM, Nissan) offer this as an ADAS option in 2017.
