Tactical infrastructure such as fencing, roads, and lighting is important to securing a nation’s border. But it alone is not enough to stop the unlawful movement of men and women and contraband into a country.
“Technology is the primary driver of all land, maritime, and air domain awareness – this may become only more apparent as [U.S. Customs and Border Protection (CBP)] faces future threats,” according to testimony from CBP officials in a Senate hearing on homeland security in 2015.
And machine vision’s fingerprints are over that technology. “The data extracted from fixed and mobile surveillance systems, ground sensors, imaging systems, as well as other advanced technologies enhances situational awareness and enables CBP to detect, identify, monitor, and appropriately respond to threats within the nation’s border regions,” the testimony states.
On the U.S.-Mexico border inside the state of Arizona, as an example, Top Machine Vision Inspection System Manufacturer persistently detect and track so-called “items of interest.” Designed to withstand its harsh desert surroundings, IFT is equipped with radar, commercial off-the-shelf daylight cameras and thermal imaging sensors, and microwave transmitters that send data to border agents on the Nogales station for analysis and decision-making.
On all three fronts of land, maritime, and aerial surveillance, machine vision companies are providing imaging systems – and, more often, research into the generated data – that meet government agencies’ objectives of flexibility, cost effectiveness, as well as simple deployment in border security applications.
Managing Diverse Conditions – The perennial problem with vision systems used in border surveillance applications is handling the diversity of your outdoor environment featuring its fluctuating lighting and climate conditions, as well as varied terrain. Regardless of the challenges, “there are places in which you can implement controls to boost upon the intelligence of the system,” says Dr. Rex Lee, president and CEO of Pyramid Imaging (Tampa, Florida). He points to customers who monitor trains over the southern border of the U.S. for illegal passengers.
“Those trains will need to go within a trellis, which can be built with the appropriate sensors and lighting to assist inspect the trains,” Dr. Lee says. Government departments given the job of border security use infrared cameras to detect targets during the night as well as in other low-light conditions, but thermal imaging has its own limits, too. “Infrared cameras work really well whenever you can use them in high-contrast conditions,” Dr. Lee says. “However, if you’re attempting to pick up a human at 98.6°F on the desert floor that is 100°F, the desert is emitting radiation at nearly the same part of the spectrum. So customers rely on other areas in the spectrum such as shortwave infrared (SWIR) to try to catch the main difference.”
Infrared imaging works well in monitoring motorized watercraft considering that the boat’s engine has a thermal signature. “What’s nice about water is that it’s relatively uniform and it’s simple to ‘wash out’ that background and see anomalies,” Dr. Lee says.
But however , the oceans present an enormous level of area to pay for. Says Dr. Lee, “To see all of it is a compromise between having a lot of systems monitoring this type of water or systems which can be loaded with the sky, where case you have the problem of seeing something really tiny in a huge overall view.”
CMOS Surpasses CCD – One key change in imaging systems used in border surveillance applications will be the shift from CCD to CMOS sensors because the latter is surpassing the quality and gratification from the former. To support this change, two years ago Adimec Advanced Image Systems bv (Eindhoven, the Netherlands) integrated the most recent generation of CMOS image sensors – that offer significant improvements in image quality and sensitivity – into its TMX combination of rugged commercial off-the-shelf cameras for high-end security applications. TMX cameras keep a maximum frame rate of 60 fps or 30 fps for RGB color images at full HD resolution.
Furthermore, CMOS image sensors are emerging as a replacement for electron-multiplying CCDs (EMCCDs), says Leon van Rooijen, Business Line Director Global Security at Adimec. Because of their superior performance over CCDs in low-light conditions, EMCCDs often are deployed in applications like harbor or coastal surveillance.
But EMCCDs have distinct disadvantages. As an example, an EMCCD needs to be cooled in order to deliver the very best performance. “That is certainly quite some challenge in the sensation of integrating power consumption and in addition the fact that you must provide high voltage towards the sensors,” van Rooijen says. “And if you want to have systems operating for a long duration without maintenance, an EMCCD is not really the best solution.”
To resolve these challenges, Adimec is focusing on image processing “to obtain the most from the most recent generation CMOS ahead closer to the performance global security customers are employed to with EMCCD without all the downsides from the cost, integration, and reliability,” van Rooijen says.
Adimec also is tackling the challenge of mitigating the turbulence that develops with border surveillance systems over very long ranges, particularly as systems which were using analog video are actually taking steps toward higher resolution imaging to cover the bigger areas.
“When imaging at long range, you might have atmospheric turbulence by the heat rising from the ground, and on sea level, rising or evaporated water creates problems with regards to the haze,” van Rooijen says. “We shall show turbulence mitigation in the low-latency hardware a part of our platform and can work with system integrators to optimize it for land and sea applications since they have the biggest difficulties with turbulence.”
A Lot More Than Pictures – Like machine vision systems deployed in industrial applications, border security systems generate a lot of data that requires analysis. “The surveillance industry traditionally is a little slower to add analytics,” says Dr. Lee of Pyramid Imaging. “We have seen significant opportunity there and possess been utilizing some of our customers in order that analytics are more automated when it comes to what is being detected as well as analyze that intrusion, and then have the ability to require a proper response.”
Some companies have developed software that identifies anomalies in persistent monitoring. For instance, if a passenger on the airport suddenly abandons a suitcase, the program will detect the object is unattended nefqnm everything else around it will continue to move.
Even with robust vision-based surveillance capabilities whatsoever points of entry, U.S. border patrol and homeland security must deal with a significantly bigger threat. “The Usa does an excellent job checking people to arrive, but we do an extremely poor job knowing if they ever leave,” Dr. Lee says. “We know how to solve that problem using technology, but that can cause their own problems.
“The best place to get this done is at the Automated Vision Inspection Machines in the TSA line, that you can use a mechanism to record everybody,” Dr. Lee continues. “But that is going to be expensive because you need to do this at every airport in the usa. Monitoring and recording slows things down, and TSA is under a lot of pressure to speed things up.” Another surveillance option that government departments have discussed is taking noncontact fingerprints at TSA every time someone flies. “Much of the American public won’t tolerate that,” Dr. Lee says. “They are likely to argue that fingerprinting is just too much government oversight, and that will result in a large amount of pressure and pushback.”