International. In a recent IHS report, he talks about how in the last 12 months different new terms have emerged that are frequently used in the video surveillance industry. Jon Cropley, its author, tries to make a brief summary of some of them.
Artificial intelligence. Faculty of computers that allows them to perform specific tasks as well or better than human intelligence. In the context of video surveillance, AI is used in the field of computer vision (also known as computer vision) to classify visual images and the patterns within them.
Big data. Huge volumes of different information that is stored, organized and analyzed by computers to identify trends, patterns and relationships. In the context of video surveillance, it could be metadata describing hours of video surveillance footage recorded, in conjunction with other data sources to highlight patterns of security or business operations.
Cloud computing. Instead of using a local server to store or manage video surveillance data, a network of remote servers connected to the Internet is used. Typically, this network has the ability to provide additional resources, when needed, from among a larger pool of available resources. The available resource can be grouped in a data center or in a network of data centers. These can be private (wholly or partially owned for the exclusive use of certain organizations) or public (resources that can be accessed by multiple users separately).
Deep learning. It is a branch of machine learning and a subset of the field of AI. Deep learning uses algorithms to structure high-level abstractions in data, by processing multiple layers of information, emulating the functioning of a human brain (a neural network).
Edge computing/storage. Perform data processing and analysis/storage closer to the source of the data (usually, in this context, in a video surveillance camera).
Facial recognition (face recognition). When a video surveillance system can automatically check a person's face with a database of people.
Graphics processing unit. A specialized programmable chip used in image processing. Given the current need (in image processing) to simultaneously process several bulky blocks of data, graphics processing units (GPUs) have been found to be ideal for deep learning or neural network processing.
H.265 – (or MPEG-4 part 2). It is a standard that defines a video compression codec, approved by the Telecommunication Standardization Section of the International Telecommunication Union (ITU-T). Compared to the H.264, the H.265 has the potential to use 30-40% less bandwidth for video streaming of the same quality.
Internet of Things (IoT). It is not a specific device or technology but a conceptual framework whose axis is the idea of incorporating connectivity and intelligence into a wide range of devices. IHS Markit defines an IoT device as a device that has some form of built-in connectivity that allows it to connect directly to the Internet (i.e., it has an IP address) or be connected (bound) to a device with an IP address. In the context of video surveillance, this could mean using video surveillance data with other sensors or sources of information.
