Tactical infrastructure such as fencing, roads, and lights are critical to securing a nation’s border. However it alone is not enough to stop the unlawful movement of individuals and contraband into a country.
“Technology will be the primary driver of all land, maritime, and air domain awareness – this can become only more apparent as [U.S. Customs and Border Protection (CBP)] faces future threats,” based on testimony from CBP officials with a Senate hearing on homeland security in 2015.
And machine vision’s fingerprints are all over that technology. “The information extracted from fixed and mobile surveillance systems, ground sensors, imaging systems, along with other advanced technologies enhances situational awareness and enables CBP to detect, identify, monitor, and appropriately respond to threats in the nation’s border regions,” the testimony states.
On the U.S.-Mexico border in the state of Arizona, for instance, Top Machine Vision Inspection System Manufacturer persistently detect and track so-called “pieces 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 at the Nogales station for analysis and decision-making.
On the 3 fronts of land, maritime, and aerial surveillance, machine vision companies are providing imaging systems – and, more frequently, analysis of the generated data – that meet government agencies’ objectives of flexibility, cost effectiveness, and easy deployment in border security applications.
Managing Diverse Conditions – The perennial downside to vision systems found in border surveillance applications is handling the diversity of an outdoor environment using its fluctuating lighting and climatic conditions, as well as varied terrain. Inspite of the challenges, “you can find places that 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 along the southern border in the U.S. for illegal passengers.
“Those trains 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 agencies tasked with border security use infrared cameras to detect targets at night as well as in other low-light conditions, but thermal imaging does have its limits, too. “Infrared cameras work really well once you can use them in high-contrast conditions,” Dr. Lee says. “But when you’re seeking 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 area of the spectrum. So customers count on other parts from the spectrum including shortwave infrared (SWIR) to attempt to catch the main difference.”
Infrared imaging works well in monitoring motorized watercraft because the boat’s engine features a thermal signature. “What’s nice about water is that it’s relatively uniform and it’s simple to ‘wash out’ that background see anomalies,” Dr. Lee says.
But the problem is that the oceans present an enormous quantity of area to cover. Says Dr. Lee, “To view everything is really a compromise between having a whole bunch of systems monitoring this type of water or systems which are rich in the sky, by which case you will find the problem of seeing something really tiny in a huge overall view.”
CMOS Surpasses CCD – One key change in imaging systems utilized in border surveillance applications is definitely the shift from CCD to CMOS sensors since the latter is surpassing the product quality and gratification of the former. To allow for this change, 2 yrs ago Adimec Advanced Image Systems bv (Eindhoven, holland) integrated the most recent generation of CMOS image sensors – that offer significant improvements in image quality and sensitivity – into its TMX series of rugged commercial off-the-shelf cameras for high-end security applications. TMX cameras have 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 substitute for electron-multiplying CCDs (EMCCDs), says Leon van Rooijen, Business Line Director Global Security at Adimec. Due to 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 deliver the best performance. “That is certainly quite some challenge in the sensation of integrating power consumption as well as the fact that you must provide high voltage to the sensors,” van Rooijen says. “And if you need to have systems operating for any long duration without maintenance, an EMCCD will not be the most effective solution.”
To solve these challenges, Adimec is concentrating on image processing “to get the best from the most recent generation CMOS in the future nearer to the performance global security customers are utilized to with EMCCD without each of the downsides of the cost, integration, and reliability,” van Rooijen says.
Adimec is also tackling the challenge of mitigating the turbulence that develops with border surveillance systems over very long ranges, particularly as systems that have been using analog video are actually taking steps toward higher resolution imaging to pay for the bigger areas.
“When imaging at long range, you have atmospheric turbulence from the heat rising through the ground, and on sea level, rising or evaporated water creates problems regarding the haze,” van Rooijen says. “We shall show turbulence mitigation within the low-latency hardware baked into our platform and can work with system integrators to optimize it for land and sea applications simply because they hold the biggest issues with turbulence.”
Greater Than Pictures – Like machine vision systems deployed in industrial applications, border home security systems generate lots of data that will require analysis. “The surveillance industry traditionally has been a little slower to include analytics,” says Dr. Lee of Pyramid Imaging. “We percieve significant opportunity there and also have been working with a lot of our customers to ensure that analytics are more automated when it comes to what exactly is being detected as well as analyze that intrusion, and then be able to take a proper response.”
Some companies have developed software that identifies anomalies in persistent monitoring. As an example, if a passenger on the airport suddenly abandons a suitcase, the application will detect the object is unattended nefqnm anything else around it will continue to move.
Even with robust vision-based surveillance capabilities in any way points of entry, U.S. border patrol and homeland security need to contend with a significantly bigger threat. “America does a very good job checking people arriving, but we all do an extremely poor job knowing when they ever leave,” Dr. Lee says. “We know the best way to solve that problem using technology, but that creates their own problems.
“The best place to do this reaches the Automated Vision Inspection Machines inside the TSA line, in which you can have a mechanism to record everybody,” Dr. Lee continues. “But that is going to be expensive because you need to do this at each airport in america. Monitoring and recording slows things down, and TSA is under plenty of pressure to speed things up.” Another surveillance option that government agencies have discussed has taken noncontact fingerprints at TSA each time someone flies. “Much of the American public won’t tolerate that,” Dr. Lee says. “They are going to argue that fingerprinting is simply too much government oversight, and that will result in a large amount of pressure and pushback.”