Subscribe to our mailing list and stay up-to-date with all Rekor products, solutions, and news.
by Rod Hillman, President of Rekor Recognition Systems, Inc.
Imagine someone driving down the road, faster than the posted speed limit, music blaring, when out of the corner of their eye they see red and blue flashing lights. Before they know it, this person loses control of the vehicle and hits an officer who was just trying to do his or her job. Now, someone must explain to the family why he or she is not coming home tonight.
Across the country, roadside workers are being struck and killed while a law goes unenforced. Move Over laws require drivers to change lanes or slow down when law enforcement vehicles and other emergency vehicles, such as, fire, rescue, construction, or tow trucks, are stopped on the shoulder of the road with emergency lights in operation. The law is only as valuable as its application, and unfortunately Move Over violations are difficult to enforce, posing a national crisis.
The first Move Over law was implemented in 1996 in South Carolina, after a paramedic who was struck and injured, and found to be at fault for stepping into the roadway, lobbied for increased protection for emergency medical responders. Since then, all 50 U.S. states have implemented a form of the Move Over law to try and reduce or prevent such risk and tragedy. Sadly, it’s not working. According to the National Law Enforcement Officers Memorial Fund, more than 150 law enforcement officers have been struck and killed by vehicles along America’s highways since 1999. “Struck by Vehicle” is the fourth highest cause of police officer death since 2008.
Unfortunately, most citizens either don’t realize the laws exist or they choose not to follow them. But when an officer is conducting a traffic stop, they can’t be held responsible to also monitor their own safety or cite and flag Move Over violations that occur. How can we educate drivers before they get behind the wheel, while also protecting the well-being of our law enforcement officers and other roadside workers? A ticket and a fine would likely make a driver think twice the next time they’re on the road, but how do we cite them in the first place when they’re flying by an officer that is already conducting a stop?
The answer could be the adoption of innovative technologies that can do the work of violation capture and citation for the officer, in real time, while they conduct their traffic stop. There are technologies available in the market—innovative camera and license plate reader solutions—that affix to a patrol vehicle, tow truck, or any other emergency vehicle, and capture the violation as it happens. And guess what? It works.
Rekor Recognition Systems, recently conducted field studies in conjunction with multiple law enforcement agencies and tow operators in Ohio, Maryland, and New York, and the numbers were startling: 1,879 violations during 134 traffic stops. With an average stop time of 11 minutes, Rekor recorded approximately 14 violations per stop during the test period. That’s 14 times per stop that a roadside worker’s life was in danger because of a violation of the Move Over law. This is just a small sample size, imagine the numbers when extrapolated on a national scale.
While the responsibility falls on the shoulders of the driver, law enforcement agencies have taken a more proactive approach toward deterring violations by implementing stricter penalties. Over the years we’ve seen many states increase penalties to include stiffer fines, suspended licenses, or even incarceration. While these penalties may strike fear in some to pay closer attention, the issue still remains that law enforcement simply cannot react quickly enough to catch most offenders. If an officer is already on the side of the road when the violation occurs, it is nearly impossible to get back in their vehicle, leave the stop they are currently on, and issue a citation to a driver who may be several miles beyond where the violation occurred. Ultimately, the lack of consequence leads to more violations, more accidents, and more fatalities.
Rekor’s Move Over field studies were conducted using the company’s proprietary technology that captures violations in real-time using multiple high-resolution video cameras, digital tracking radar, and AI-based license plate recognition software. The system provides video and data evidence of infractions, which would ultimately be reviewed and approved for issuance only by law enforcement personnel.
While this solution may not bring an end to Move Over law violations, it is a significant step in the right direction that will lead to dramatic improvements in compliance, and ultimately help to save lives.
As a fellow driver, I understand that sometimes we are in a rush to get to our destination and that distractions happen. However, the few seconds it takes to focus, move over, or slowdown could not only save someone else’s life but can save the driver’s as well. While it is improbable to eliminate Move Over violations, it is imperative that communities nationwide are educated about responsible actions while providing law enforcement agencies access to the most advanced tools available.
by Matt Hill, Founder of OpenALPR
Artificial Intelligence (AI) has enabled applications that, only a few years ago, seemed impossible. Active development of this emerging technology is yielding self-driving cars, facial recognition, augmented reality, and much more. OpenALPR uses AI in its License Plate Recognition (LPR) engine to achieve superior accuracy compared to legacy products.
The combination of massive volumes of data, large-scale computer resources, and specialized software algorithms called neural networks, combine to enable computer programs to learn to make remarkably accurate predictions from imperfect inputs.
he breakthrough that began the recent AI boom was in 2012 when Alex Krizhevsky presented a solution, named “AlexNet”, to the ImageNet research challenge. AlexNet utilized a novel convolutional neural network architecture to classify images. While other teams were researching solutions that provided a 2-4% incremental improvement over the previous year’s best result, AlexNet was roughly 40% better than the second-place team. It was immediately apparent that this was a superior approach, meriting further research. In the following year, and every year since, all of the top scoring competitors use some variant of neural networks in their submissions.
This disruptive technology has had a similar effect across virtually all software fields where it has been successfully adapted. Software that was once state-of-the-art is becoming obsolete as AI solutions perform significantly better. AI has also found utility in automating tasks that previously required human intuition, such as analyzing radiological studies and logistical planning.
The short answer is that is significantly more accurate and it can detect vehicle make, model and color using low-cost consumer-grade video cameras.
OpenALPR began as an open source project in 2013. The software originally employed traditional computer vision techniques to recognize license plates in images and videos. This initial approach was similar to how other commercial LPR products currently operate. The effectiveness of traditional computer vision is limited because it can only achieve a moderate level of accuracy, usually about 80%, before reaching a plateau. OpenALPR commercial software uses an exclusively-AI approach which increases accuracy significantly. Further, as the AI training dataset becomes larger and the algorithms are fine-tuned, OpenALPR’s accuracy continues to improve.
OpenALPR publishes verifiable benchmarks that demonstrate its software’s accuracy.
The use of AI also allows OpenALPR to detect information such as the make, model, and color of the vehicle. This detection is based solely on surveillance video data and does not require the use of a separate vehicle registration or government database. And with fixed-based camera’s, OpenALPR can also detect a vehicle’s travel direction. This type of vehicle information becomes crucial to law enforcement when eye witnesses can recall the vehicle information, but not the license plate number.
Traditional LPR has been available for more than a decade, but it required specialized, and often proprietary, camera equipment to simplify visual data so that software could pick out the license plate data. This equipment is more expensive than consumer-grade, mass-market video cameras that can be used for a variety of purposes. Because OpenALPR’s software is AI-based, it can effectively us image data from low-cost, commodity cameras while also being more accurate – a better and economical solution.
LPR is widely used by law enforcement, for security, and by the vehicle repossession industry. LPR can also be used for parking lot management, car wash loyalty programs, fast-food drive-through lanes, logistics tracking, automated ticketing, etc. In the past, LPR was not considered for these purposes because it was not accurate enough. By increasing recognition accuracy from less than 80% to 99%, OpenALPR’s software is enabling transformative automation solutions to be viable.
OpenALPR provides a solution that is significantly more accurate and cost-effective than other products on the market. Not only does this make it more compelling to deploy more LPR cameras for law enforcement, security and commercial purposes, it also opens new markets for the technology. In the near future, we expect to see a dramatic increase in the number of license plate recognition devices installed across the world.
Consider briefly explaining in a call out, a neural network. I found the following on Wiki “ A neural network is framework for many different machine learning algorithms to work together and process complex data inputs. Such systems “learn” to perform tasks by considering examples, generally without being programmed with any task-specific rules.” We could add a similar callout box to briefly describe “machine learning”
WHITE PAPERS & CASE STUDIES