Tactical infrastructure like fencing, roads, and lights are essential to securing a nation’s border. But it alone is not enough to avoid the unlawful movement of men and women and contraband in to a country.
“Technology is the primary driver of all the 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 with a Senate hearing on homeland security in 2015.
And machine vision’s fingerprints are common over that technology. “The information obtained from fixed and mobile surveillance systems, ground sensors, imaging systems, and other advanced technologies enhances situational awareness and better enables CBP to detect, identify, monitor, and appropriately reply to threats within the nation’s border regions,” the testimony states.
In the U.S.-Mexico border within the state of Arizona, for example, Top Machine Vision Inspection System Manufacturer persistently detect and track so-called “items of interest.” Created to withstand its harsh desert surroundings, IFT comes with radar, commercial off-the-shelf daylight cameras and thermal imaging sensors, and microwave transmitters that send data to border agents at the Nogales station for analysis and decision-making.
On all 3 fronts of land, maritime, and aerial surveillance, machine vision companies are providing imaging systems – and, more frequently, research into the generated data – that meet government agencies’ objectives of flexibility, cost effectiveness, and simple deployment in border security applications.
Managing Diverse Conditions – The perennial downside to vision systems utilized in border surveillance applications is handling the diversity of the outdoor environment featuring its fluctuating lighting and weather conditions, as well as varied terrain. Despite the challenges, “you can find places where you can implement controls to improve upon the intelligence from the system,” says Dr. Rex Lee, president and CEO of Pyramid Imaging (Tampa, Florida). He points to customers who monitor trains across the southern border in the U.S. for illegal passengers.
“Those trains have to go within a trellis, which can be equipped with the proper sensors and lighting to assist inspect the trains,” Dr. Lee says. Government agencies tasked with border security use infrared cameras to detect targets at night as well as in other low-light conditions, but thermal imaging has its limits, too. “Infrared cameras work really well when you can make use of them in high-contrast conditions,” Dr. Lee says. “But when you’re attempting to pick up a human at 98.6°F on a desert floor that is certainly 100°F, the desert is emitting radiation at nearly exactly the same portion of the spectrum. So customers count on other regions from the spectrum such as shortwave infrared (SWIR) to attempt to catch the main difference.”
Infrared imaging works well in monitoring motorized watercraft because the boat’s engine has a thermal signature. “What’s nice about water is the fact that it’s relatively uniform and it’s simple to ‘wash out’ that background see anomalies,” Dr. Lee says.
But however , the oceans present a vast amount of area to cover. Says Dr. Lee, “To find out everything is actually a compromise between having a whole bunch of systems monitoring water or systems that are rich in the sky, by which case you have the problem of seeing something really tiny in a large overall view.”
CMOS Surpasses CCD – One key change in imaging systems found in border surveillance applications will be the shift from CCD to CMOS sensors since the latter is surpassing the standard and performance from the former. To support this change, two years ago Adimec Advanced Image Systems bv (Eindhoven, holland) integrated the most recent generation of CMOS image sensors – that provide significant improvements in image quality and sensitivity – into its TMX number of rugged commercial off-the-shelf cameras for high-end security applications. TMX cameras maintain 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 an alternative 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 has to be cooled in order to offer the best performance. “That is certainly quite some challenge in the feeling of integrating power consumption and in addition because you need to provide high voltage for the sensors,” van Rooijen says. “And if you want to have systems operating for a long duration without maintenance, an EMCCD is not the most effective solution.”
To fix these challenges, Adimec is working on image processing “to obtain the most from the latest generation CMOS to come even closer to the performance global security customers are utilized to with EMCCD without all the downsides from the cost, integration, and reliability,” van Rooijen says.
Adimec also is tackling the task of mitigating the turbulence that develops with border surveillance systems over very long ranges, particularly as systems that were using analog video are now taking steps toward higher resolution imaging to cover the larger areas.
“When imaging at long range, you may have atmospheric turbulence through the heat rising from the ground, as well as on sea level, rising or evaporated water creates problems regarding the haze,” van Rooijen says. “We shall show turbulence mitigation inside the low-latency hardware a part of our platform and will work with system integrators to optimize it for land and sea applications since they have the biggest issues with turbulence.”
Greater Than Pictures – Like machine vision systems deployed in industrial applications, border security systems generate plenty of data that will require analysis. “The surveillance industry traditionally is a little slower to incorporate analytics,” says Dr. Lee of Pyramid Imaging. “We see significant opportunity there and possess been utilizing a lot of our customers so that analytics tend to be more automated with regards to what exactly is being detected as well as analyze that intrusion, and then have the capacity to require a proper response.”
Some companies have developed software that identifies anomalies in persistent monitoring. For example, when a passenger on the airport suddenly abandons a suitcase, the program will detect that this object is unattended nefqnm everything around it continues to move.
Even with robust vision-based surveillance capabilities whatsoever points of entry, U.S. border patrol and homeland security need to cope with a much bigger threat. “The Usa does a very good job checking people to arrive, but perform a really poor job knowing should they ever leave,” Dr. Lee says. “We know the best way to solve that problem using technology, but that produces its own problems.
“The right place to do this are at the Automated Vision Inspection Machines inside the TSA line, that you can possess a mechanism to record everybody,” Dr. Lee continues. “But that is going to be expensive because you need to do this at each and every airport in the usa. Monitoring and recording slows things down, and TSA is under lots of pressure to speed things up.” Another surveillance option that government agencies have discussed has taken noncontact fingerprints at TSA each time someone flies. “A lot of the American public won’t tolerate that,” Dr. Lee says. “They are likely to argue that fingerprinting is simply too much government oversight, and will result in a great deal of pressure and pushback.”