We are excited to bring Transform 2022 back in-person July 19 and virtually July 20 – August 3. Join AI and data leaders for insightful talks and exciting networking opportunities. Learn more about Transform 2022
As more and more people live in cities and towns, the implementation of smart cities has become paramount to promoting sustainable development, addressing growing urbanization challenges and improving overall quality of life. But what is a smart city? And how do they work?
A smart city is a technologically modern urban area that uses (primarily) information and communication technologies to develop and deploy sustainable practices that address various urbanization challenges. For example, smart cities can help communities streamline trash collection, minimize traffic and improve air quality. By collecting and analyzing various data points, a city’s infrastructure can be optimized.
In fact, strides have already been made toward this becoming a reality. Driverless cars burn less gas or use less battery power, resulting in less air pollution and companies like Waymo, Zoox and Cruise are already offering these types of vehicles in select cities.
So how do we continue the forward progress and employ even more on-the-ground technologies to power smart cities? The key is the right geospatial data.
Geospatial data – the what and the why
Geospatial data is information that describes objects, events and other features with a location on or near the surface of the earth. In relation to cities and urban planning, this data can look like pedestrian movement, traffic patterns and construction work. The key here is that this data is dynamic — from the various sensors, satellites and other collection methods, we’re able to accumulate real-time information which helps autonomous technologies be as efficient and accurate as possible while also enabling data analysts to spot trends that might not otherwise be seen.
From feature identification and image classification to object tracking and LiDAR annotation, geospatial data powers the deployed technology based on geographically referenced information and provides a detailed map of the environment in which the technology is operating. For this map to be as accurate as possible, it needs to reflect all changes that happen to the area it’s representing.
By collecting real-time inputs from various sensors, dynamic geospatial data can be used to power autonomous tech and smart city projects. We’ll be able to know and predict when there’s a spike in pedestrian traffic, the best cadence for trash collection, the ebbs and flows of automotive congestion, the impact of specific or random events on city operations and much more.
Beyond data collection
While the collection of data is important, there are two additional considerations that serve to improve smart cities’ operations — data sharing and robust annotation.
The robust annotation of data is a key piece to ensuring our autonomous technologies and systems work like they’re supposed to. Properly addressing edge cases and anomalous scenarios helps the technology make the correct decisions and function properly, even in new or uncommon situations.
For example, what happens when there is a sporting event and there’s more pedestrian traffic than normal? In a situation like this, there is likely to be more jay-walking, crosswalk congestion and automotive traffic. There may also be a heightened need for public transportation.
In order to ensure the technologies and systems not only function correctly during these types of scenarios, but adjust their operations to meet current needs, they need to be prepared for them. Building models to identify edge cases and represent anomalous situations is key to properly annotating and labeling data. Unfortunately, we can’t possibly know every single edge case or anomalous situation the technology will run into, which is why it’s also important to share data.
The more sensors providing data, the more data points collected, the more edge cases tested and anomalous situations prepared for — the better our autonomous technologies will work. Put simply, the more our machines can learn about the world in which they operate, the better they operate. That’s why I believe it’s so important for companies employing autonomous technologies to share their data. Think of it this way — it’s hard to have a complete picture when you’re only working with a portion of the puzzle.
If a city is the full picture, then the data collected serve as the puzzle pieces. If these companies share their data both with each other and with their local governments, it could allow our cities to reach a whole new level of smart — becoming more efficient and more effective. Local government entities are a key piece of the equation, and must share the responsibility for achieving this vision because they often have insight into planned roadway changes, scheduled construction and other key pieces of information that can affect how autonomous technology functions.
Smart cities: Where we go from here
Smart cities aren’t quite a reality just yet, but we’re closer than we’ve ever been. It’s important to recognize that we’re still in the early stages, having taken only the first steps toward autonomous technologies being applied to the field. Standardized protocols and regulations have yet to be established, but will be a critical part of the process if we want widespread adoption.
However, big steps are still being taken. China has developed smart roads that talk to driverless cars and Michigan is developing a 40-mile corridor for CAVs. We’ve already started adopting the type of technology necessary to power smart cities. From here, it’s up to us to provide the data needed to fully power accurate and effective technology that will improve our infrastructure, efficiency and quality of life.
Jeff Mills is the chief revenue officer at iMerit.