With so much information out there on image quality, accuracy, frames per second, focal points, distortion, AI algorithms, and more—it’s tough to understand which inspection drone is right for your needs. This blog should clear some of the fog and help you see the big picture.

It’s pretty obvious why we are loving drones for visual inspection. They can maneuver, hover, and hold—making inspections safer, more efficient, and more thorough. New advances in computer vision have made it even possible to inspect large scale sites autonomously, especially when you need precise monitoring for those critical assets and infrastructure.

Here’s the thing. A drone is only as good as the data it collects. Without high quality imaging, you can’t perform accurate inspections or make reliable decisions. By catching minute faults or problems early on, you can prevent downtime for your business, improve safety, and even cut the risk of environmental damage.

With so many options, buzzwords, and parameters for image quality out there, we wrote a tech deep dive to demystify the decision-making for autonomous visual inspection solutions. It goes through some essential background information, introduces the ins and outs of accuracy and quality for visual inspection, and then zeroes in on image quality and why it’s important. This blog takes you through some of the deep dive’s highlights, but you’re welcome to read it all to learn more.

 

Clearing up image quality myths

Before we get started, you’ll want to keep two things in mind. 1) There is no single answer or parameter that sets the benchmark for image quality. 2) Good quality is not just a matter of camera features. It ultimately depends on what you need the image for.  Although a camera’s resolution is expressed in megapixels, the resolution of an imaging system has to include a spatial metric. And the more details the better. Let’s take a closer look at why to clear up some common misconceptions.

 

Myth: Lower GSD means better inspection 

Truth: Although GSD can precisely calculate the level of detail detected, you can still have the same GSD for a very crisp image and a very blurry one.

Ground sampling distance (GSD), representing the difference between the center of two pixels, is the most common statistic noted in discussions of resolution. A 1 cm GSD means that every pixel reflects one centimeter down on the ground. In short, the same camera flying at a low altitude will have a smaller (i.e., better) GSD than it would at a high altitude.

Although GSD can precisely calculate the level of detail that can be detected, you can still have the same GSD for a very crisp image and a very blurry one. This is because GSD doesn’t take into account diffractions, defocus, aberrations, distortion, lens curvature, motion blur, and other artifacts.

 

Myth: More megapixels means better quality images

Truth: Too many megapixels can harm a camera’s performance. The sensor size is more important when it comes to getting sharper details. 

The photo resolution reflects the tradeoff between field of view (FOV) and GSD. A higher resolution means that we can either increase FOV without compromising GSD, or increase GSD without compromising FOV–or even increase both.

In short, by itself, photo resolution doesn’t reflect the amount of details or the quality of the image. That said, if you’ve got the right optical system, you can get a high level of detail and a large field of view.  In the commercial drone industry, the standard photo resolution ranges from about 12MP–including  the retired Percepto Sparrow, Skydio 2+ for Enterprise, and DJI mini 2–to 24MP for the Percepto Air Max, and can go up to about 48MP as it does for the DJI Mavic 2 Enterprise Advanced.

Myth: The more lines per centimeter, the better the system

Truth: Higher spatial resolution means a smaller area is photographed, and you’ll need more flight time to cover the same area. 

Spatial resolution, measured in line pairs per centimeter (lp/cm), describes the amount of distinguishable details captured on a physical surface. This is usually the first and most common measure for the image quality.

But more lines per centimeter also means you’re getting a smaller area photographed, which translates directly into more flight time or more footage needed to cover the same area. To balance this tradeoff, we calibrated our solution to get the best possible detail for inspection at close range so that any cracks or anomalies are visible—while ensuring that the same configuration works well for mapping applications, which don’t require as much detail.

 

Myth: MTF is a precise measurement of contrast detail

Truth: There is no standard way to measure MTF. Each camera sensor has its own MTF chart as does each lens. The lens MTF should match or exceed that of the sensor.

Modulation transfer function (MTF) measures the ability of a lens to differentiate between pixels, and is a good indication for image sharpness. MTF plots the contrast and resolution of a lens from its center to its edges, against a theoretical perfect lens. Of course, this perfect lens doesn’t exist because glass is not 100% transparent and the rounded surface of the lens inevitably creates distortions in the light passing through.

What’s important is that each camera sensor has its own MTF chart. If the MTF of the lens is lower than the MTF of the camera, the lens will be the limiting factor. Ideally, you want the MTF of the lens to be on a par, or even higher, than the MTF of the camera–so you get the full benefit of the camera’s capabilities.

 

The ingredients for superior image quality

Although we already looked at four important and well-known parameters for image quality, there are other less-known factors that, together,  impact the viability of inspection solutions.

Superior detail separation

Detail separation isn’t about the best looking image. It’s the one in which the smallest faults can be detected at an early stage, and from a distance. A more robust algorithm with high detail separation will help you catch issues earlier on. In the figure below, you can see the results of a test we did to measure the detail separation for four different drone sensors. The superior detail separation of the black and white lines at the edge of pad for the Air Max is quite obvious. In contrast, the lack of detail separation for the same lines is almost non-existent for the Mavic-E.

DJI Mavic – E	DJI Phantom 4	DJI M300	Percepto Air Max

Figure 2: Differences in detail separation at 20m distance

 

White balance

White balance is the process that adjusts the color ‘temperature’ of your data captures so they match what our eyes would see. Having a sophisticated software solution for white balance will make problem detection easier and lower the rate of false alarms.

Figure 3: White balance helps ensure colors appear as seen by the human eye

 

Best lens for the job

Each lens has specific distances at which it performs best, based on its MTF, distortion, focal distance, and some other parameters. While a lens can be calibrated for a certain depth of field, it can’t be set for multiple distances. Images taken beyond the range established for the lens, will have lower image quality. You’ll want a system that has the best lens and lens calibration for your use case.

 

Optimized software parameters

Although we don’t often think about it, each drone solution has to take the raw pixels collected and transform them to compose an image. This process, known as mosaicking or Debayer, should ideally run at the edge in real-time on the drone’s GPU.  Having a powerful feedback loop between the camera and software, makes it possible for the drone to continuously adjust its position and direction to get the best image, while the system automatically chooses the exposure and gain that will produce an image with the lowest amount of noise, lowest blur, and maximum amount of recognizable detail.

Getting the right drone for your business 

Although there is no one size fits all solution when it comes to drone inspection, you can still get the best in class image quality available in today’s marketplace. By giving top priority to our lens configuration, image quality, and software algorithms, Percepto drones deliver best in class detail separation and therefore detailed, high-quality change detection. Read the complete tech deep dive to learn more about what image quality is right for your use cases, become familiar with the different terms for image quality, and make an educated decision when it comes to the best fit for your operations.

In 2020, we at Percepto introduced a game changer in the visual inspection market. We did this with the introduction of Percepto AIM – Autonomous Inspection and Monitoring. Percepto AIM is the first-ever enterprise solution enabling truly autonomous management of a fleet of robots residing on-site, and automatic generation of business insights relevant for various stakeholders within organizations.

In this blog:

• Wouldn’t it be great if…
• And now, one year later
• Next-gen change detection and Insight Manager
• More robots, more visual data
• Enhanced user experience removing information bottlenecks

AIM has evolved. AIM 2022. So, what are the upgrades, and how do they add value for your industrial site?

Wouldn’t it be great if

Wouldn’t it be great if you always knew the status of your maintenance? How has construction progressed in the last week, and how is it compared to plans? What are the variations in pile volume, and are we meeting production targets? How can we respond to security, emergency or other situations swiftly and effectively as they arise?

Well, that’s Percepto AIM, which is designed to deliver business intelligence and actionable insights. Based on AI-powered change detection, AIM leverages both ongoing and historical data collection to better detect anomalies, identify trends and focus stakeholder attention. Our continuous monitoring and data feed allows AIM to “learn” about site assets, getting to know them as well as any employee or stakeholder. This enables the system’s AI-powered analytics to derive insights from repetitiveness – detecting changes over time.

And now, one year later

Over the past year, our familiarity and experience with various industrial sites continued to grow. This enables us to better our AI and product experience. Consider, since AIM was launched, we’ve worked closely with some of the leading industrial companies and most complex sites. By being engaged in actual everyday operations, we’ve gained data from thousands of hours of flights and missions. This data feeds the AI/machine learning so that the derived insights are accurate. Our engagement also enables us to build the product experience our clients need specifically for their operations and stakeholders.

We’ve taken that data and insight and put it into AIM 2022. This advance is sure to provide actionable insights from site inspections that can help you keep your site operating optimally, minimize downtime, and prevent large-scale failure and catastrophe.

Next-gen change detection and Insight Manager

Our clients come from multiple industries, including electric utilities, solar energy, mining, oil and gas, ports and terminals and heavy industrial sites. While every site is looking for actionable insights, their specific needs may be different.

To meet those needs, AIM 2022 includes Insight Manager – packing customized solutions for each industry. These solutions are powered by our new change detection framework and provide highly reliable and accurate analytics. This is crucial not only to deliver the insights needed to keep facilities in top shape, but also empowers any stakeholder to request the information they need – removing experts such as drone pilots and data analysts from the loop. With Insights Manager, it’s easy for any stakeholder to get the insights they need – it’s just one click away.

Our expertise and AI-based solution can filter information based on requests/interests. Each stakeholder can subscribe to the asset(s) that is of interest and relevance to them and receive automatic notifications on important changes.

Consider the inspection of a refinery. Our oil & gas solution identifies structural and thermal anomalies for previously collected visual data. Further capabilities include detecting gas leaks and spills, pipe insulation anomalies, and structural faults in tanks, pipelines or other infrastructure.

Then, there’s the solution for power grid inspection and monitoring. The solution uses semantic segmentation to place and classify components of these very structurally complex assets. And then, the change detection framework identifies structural faults and hot points in the grid as predictors of potential failures.

The change detection framework is helpful for monitoring construction as well. The solution identifies different components and their location to review the progress and stages of construction. The monitoring can also assist in ensuring employee safety standards, construction quality and timelines are met.

Each new solution includes reports and insights that are automatically generated and disseminated to relevant stakeholders.

More robots, more visual data

Alongside AIM 2022, we introduced a brand new drone-in-a-box, Percepto Air Mobile – joining our flagship drone-in-a-box the Percepto Air Max.

Both Percepto Air drones are integrated with AIM, and we’ve leveraged our thousands of flight hours of repetitive data collected by our fleet of robots. This high-quality data allows our machine learning networks to be trained and ultimately deliver highly reliable and accurate analytics. Our cutting-edge technology continues to progress as, over the past year, we’ve gained even more visual data sources.

There are even more ways to make use of our cutting-edge software and AI platform. Because our customers request that Percepto be their “everything visual data” solution, we are integrating new drones and visual data capture devices. Now, DJI drones and fixed cameras can be fully managed from the new Percepto Mobile App. The app can launch flight inspections of DJI drones and provide automatic visual data upload. Another benefit is having all the information gained from the inspection done by DJI drones stored in one place making it easier to gain valuable insights.

Enhanced user experience removing information bottlenecks

When developing AIM 2022, we also focused on the user experience to help ensure any user can access data and get the insights they need. Our new Insight Manager provides packaged solutions for industry-specific use cases, making it even easier to get the insights you need. With insights more easily gained and shared, data is no longer siloed. It also encourages collaboration and removes bottlenecks.

There are multiple features available that enable AIM 2022 to deliver a superior user experience. Features include a mobile interface that is accessible anywhere through a smartphone. This means remote operations – an inspection can be initiated anywhere you have your phone and the insights gained can be viewed/delivered right to your phone.

Other user experience features include:

• Collaborative tools that make sharing and acting upon insights simple. This encourages problem-solving, leads to greater productivity, and fosters communication.
• Automatic notifications that present information in real-time. Problems are not left to fester and can be handled as soon as possible.
• Delivery of information in a user-friendly way that can be filtered based on area of interest. Who wants another email/notification with excess information when everyone is already busy? Get the information you need and use your time wisely.
• A map timeline with integrated CAD overlays to better manage construction issues found by our AI engine.

Since its launch in November 2020, AIM has grown into an even more advanced, inclusive and collaborative solution. It packages the most cutting-edge AI, into a user-friendly, easy to collaborate solution. The insights provided – both positive changes and fault detection – empower companies to maintain their sites, prevent outages, spills, leaks, etc. To put it simply, optimize productivity and minimize downtime.

And we are not finished. We continue to evolve AIM by integrating more visual sensors, customizing additional AI solutions and more. It’s our vision that every industrial site can automate and optimize their visual inspections. And we aim to do just that.

Percepto’s anomaly detection is an essential tool for utility companies in their battle to maintain regular operations and minimize the downtime of a power grid. It enables companies of all sizes – utility companies that are responsible for keeping the power on for millions of customers to individual companies that manage their own power grid – to inspect their sites effectively and proactively. The regular inspections empower anomaly detection resulting in continual operations.

Our solution, which utilizes our AI change detection algorithm, is the only one in the industry for electrical utilities. It is the key to optimizing situational awareness, effective operations and maintenance as it serves as a flawless indicator of faults or defects. 

Consider these examples: 

1. Is the temperature on that insulator, fuse, or lightning arrester out of range? While some temperature variation is acceptable, significant swings indicate a problem and anomaly detection will flag this.
2. Is there a crack in the electric pole? Over time, small cracks grow into bigger cracks that require attention. Anomaly detection will allow for the study of the pole leading to rectifying the issue before it impacts service.
3. Is a branch encroaching on the clearance area? Is it verging on potentially interfering with service? Anomaly detection can spot this and help maintenance determine the severity of the issue.

So, frequently inspecting power lines with autonomous drones with change detection allows companies to detect minor faults before they lead to outages and prevent failures from occurring.

But what happens when the inevitable weather event strikes and failures occur? Anomaly detection helps pinpoint exactly where failures occurred, making it a great asset to maintenance crews and engineers. It helps them to:

1. Stay safe – they can safely remain indoors while the drone performs inspections. 
2. Save time – they don’t have to walk or drive around the entire grid because they know exactly where to go.
3. Get the power back up faster – they know what tools or equipment they need to quickly perform repairs. 

How Percepto’s anomaly detection solution works

Percepto’s autonomous drones collect good high-quality data on a regular basis. Companies have the drone on-site and can use it to collect data daily. In addition, an automated drone can go at the same time of day and take the same exact route. So, the pictures and data are from the same angle and height. These two elements provide consistent, repetitive high-quality data, the key to anomaly detection.

The data collected by Percepto’s autonomous drones is automatically uploaded to AI-powered software. Companies can buy (or lease) the software. Either way, it’s a time saver.

With the powerful change detection algorithm and consistent data, any change can be detected. However, the analysis is conducted only on those areas where anomalies matter, ignoring measurements in surrounding areas that are not only irrelevant but might provide misleading data. Plus, anomaly detection compares the temperature measured in each component to those surrounding it, predefined thresholds of low/high temperatures or historical data, anomalies will be automatically detected.

Only relevant changes are flagged. This is because the change detection in our technology detects new issues and separates them from known issues as well as irrelevant noises (shadows, changing light conditions, etc.). Lastly, the object is GPS tagged for immediate location identification, allowing precise and swift action.

Anomaly detection in the field – saving lives and keeping communities safe

Our fully autonomous drones, with anomaly detection, allow for remote inspection of power lines and transmission towers. This makes inspections safer, better, and faster.

Here are some examples of the technology working side by side with engineers and technicians to keep them safe and prepared.

A large American utility company that serves over 10 million people and has 119,000 km of transmission lines uses our technology for initial assessments rather than putting employees at risk. They also use it because it’s faster and can spot issues in areas that humans can’t get to.

A second client that maintains their own private power grid notes the technology enables them to monitor and secure their site efficiently and safely.

Percepto’s autonomous data collection and anomaly detection are the ingredients needed for optimal power grid inspection. These unique abilities allow utility companies to keep the power on and get it back up quickly when storms hit.