Today 501

Yesterday 897

All 39397157

Friday, 29.03.2024
eGovernment Forschung seit 2001 | eGovernment Research since 2001

For smart city planning and growth, city management organisations must go beyond short-term goals and resort to technology, such as computer vision

Smart cities use a mix of low-power sensors, cameras, and AI algorithms to continuously monitor the city’s efficiency. Governments benefit greatly from the use of computer vision and other related technologies. These technologies allow city administrators to easily integrate and manage assets. As the ‘eyes’ of the city, computer vision plays an important role in smart city management. The following are some of the most important computer vision applications for smart cities:

Smart Traffic and Bicycle Monitoring

Greater urban density usually means more automobiles, which means more traffic congestion, longer travel times, accidents, local air pollution, and carbon emissions – not to mention a general sensation of exhaustion, tension, and anxiety. An edge-enabled computer vision system may record a real-time picture of traffic conditions using new or existing street cameras, and then correlate this information with specifically trained machine learning algorithms.

Smart Parking Monitoring

The use of computer vision technologies can assist authorities in providing better services. is responsible for the administration of parking places. Drivers looking for vacant parking places cause a major portion of daily traffic delays and emissions in a congested city. It is feasible to detect automobiles coming or departing a parking space, automatically recognise plate numbers, and record the parking period using parking lot AI cameras. All of the foregoing data may be uploaded into a single, cloud-based database, allowing city officials to save money on parking enforcement.

Public Space Monitoring

Water treatment and distribution systems, electricity networks, telephone equipment, street lighting, highways, tunnels, and bridges are all examples of public infrastructure that cities are responsible for. However, the inevitability of a large number of infrastructure-related accidents can strain even the most well-resourced teams, resulting in a response that is neither quick nor optimal. City authorities, on the other hand, will be able to swiftly make effective and efficient judgments if a cloud-based system has access to the footage accessible from all local CCTV networks, analyses it, and automatically advises on timely actions.

Quality Management

In smart factories, smart camera applications provide a scalable solution for automated visual inspection and quality control of manufacturing processes and assembly lines. In this case, deep learning employs real-time item detection to get better than time-consuming manual inspection. Machine learning approaches are more resilient than classic machine vision systems and they don’t require expensive particular cameras or regulated settings. As a result, AI vision approaches may be used in a variety of places and factories.

Public Health and Safety

As the Covid epidemic demonstrated, there are occasions when municipal officials must react to wholly unexpected and innovative events. Computer vision systems can help public services (such as police stations, hospitals, water treatment facilities, and traffic management control rooms) adapt to changing legislation, notify citizens properly, identify clusters of noncompliance and take remedial action as needed. A breach of a health protocol in a public area, for example, maybe noticed, analysed, and handled more quickly and accurately, lowering the danger of runaway hazards to the local population.

Waste Dumping Monitoring

Littering is a contemporary city’s worst enemy. The city authorities can’t maintain a near real-time monitoring and deterrence system, from the anarchic disposal of gardening waste, building materials, and old furniture to the more dangerous dumping of electrical devices, broken machinery, used tyres, old batteries, and chemical products. Potential dumping places may be accurately monitored utilising street IP cameras with ECV capability.

Governance and Security

Governments are substantially investing in smart cities for a variety of reasons. The ability to improve law enforcement and civilian safety is a major driver for smart city development. To that purpose, local or federal governments can use computer vision for smart city initiatives to keep the peace. The usage of image sensors and face recognition software aids in the building of a citizen database. It facilitates the process of identifying and apprehending an illegal citizen, as well as knowing the identities of wounded people in the event of an accident. The application of computer vision in smart cities allows inhabitants to live in a safe and secure environment.

Medical Skill Training

On self-learning platforms, computer vision applications are utilised to measure the competence level of expert learners. Surgical education, for example, has benefited from the development of simulation-based surgical teaching systems. Furthermore, the concept of action quality evaluation allows for the development of computer systems that evaluate surgical students’ performance automatically. As a result, individuals might receive useful feedback information that will help them develop their skills.

Automatic Harvesting

Traditional agriculture relies heavily on mechanical activities, with hand harvesting being the most common, resulting in high costs and inefficiency. High-end intelligent agricultural harvesting devices, such as harvesting machinery and picking robots based on computer vision technology, have appeared in agricultural production in recent years, marking a new stride in the robotic harvesting of crops. Harvesting operations are primarily concerned with ensuring product quality during harvesting to maximise market value.

Road Condition Monitoring

To monitor concrete and asphalt civil infrastructure, computer vision-based fault identification and condition evaluation is being developed. Pavement condition evaluation gives data that may be used to make more cost-effective and consistent judgments about pavement network maintenance. Pavement distress inspections are usually carried out with the use of sophisticated data-gathering vehicles and/or on-the-ground surveys.

---

Autor(en)/Author(s): Aishwarya Banik

Quelle/Source: Analytics Insight, 05.01.2022

Bitte besuchen Sie/Please visit:

Go to top