The company demonstrated a system that respect privacy by only recording persons entering a restricted area, and another that can call up images from a network of cameras corresponding to a person of interest.
Canon is increasingly moving beyond its core activities in copying/printing, medical imaging and photography, boosting its video surveillance activities with a number of acquisitions in recent years. In June 2014 Canon bought Danish video management and analytics vendor Milestone Systems, one of the largest players in that market, for an undisclosed sum then in February this year snapped up Swedish IP-camera manufacturer Axis for US$2.8 billion.
Although Canon already made surveillance cameras, those deals mean its network video solutions business can now also offer customers centralized and decentralized video processing capabilities.
Surveillance technologies of all kinds have had bad press of late, in large part due to their misuse by secretive government agencies. However, Canon is showing an awareness that people will accept increased surveillance if it is done in accordance with local privacy laws.
Surveillance systems were among a broad range of existing products, ideas for future products, and way-out-there research projects on show at Canon Expo, an event the company put on for customers in Paris this week.
One of the demos showed how surveillance cameras can be used to precisely monitor a sensitive area -- a safe or cash till for example -- without recording images of people nearby. Such a system might be useful in a country where privacy laws prohibit the recording of people except for narrowly defined purposes such as theft prevention.
In the demo, a camera pointed at an open space in the middle of the booth, where one square meter of bright pink carpeting stood out from the surrounding gray. Two displays on the wall showed images of the booth, one directly from the camera, the other after processing by a server that also received data from a distance sensor mounted atop the main camera.
The processed image transformed anyone standing outside the square into a pale green ghost.
Systems designed only to monitor specific areas already exist, but they merely restrict the camera's field of view, either physically or electronically: Anyone walking in front of, or behind, the monitored zone would still be recorded as they crossed the camera's field of view.
Canon's demo, though, adds additional restrictions by limiting the distance from the camera at which objects can be recorded. The server used information from the depth sensor to work out how far away part of the image was, "ghosting" it if it was outside a volume roughly one meter square and two meters high. Stand at the front of the square and lean towards the camera, and the server makes your torso disappear as you leave the monitored zone; stand outside and lean in, and your head suddenly reappears, atop a ghostly green body. People passing by, whether in front of or behind the pink square, are not recorded at all.
Staff on the stand wouldn't say how the depth detection was performed, but the sensor on top of the camera had the distinctive red-and-black form of a SwissRanger SR4000 time-of-flight sensor from Mesa Imaging. This bounces small bursts of infrared light off a target, measuring the time taken for them to return. It has a relatively low video resolution of 176 by 144 pixels, accounting for the blockiness of the green ghosts on Canon's HD video screen.
Time-of-flight video sensing has become something of a must-have technology for game console manufacturers in recent years. Microsoft already has it in the Kinect component of the Xbox One, while last week Sony bought Softkinetic Systems, a Belgian vendor of depth- and motion-sensing cameras.
In Canon's demo, the camera and depth sensor are separate components, with the camera output filtered externally but, "Ideally, the processing would be done in the camera," with the ghosted video stream as the only output, ensuring respect for local privacy laws, said Canon spokesman Yoshinobu Kitamaru.
Another system he worked on captures images from a network of cameras, extracting as it does so metadata about anyone in view, such as the color of their clothing, the length and color of their hair, their apparent age and the characteristics of their face. So far, nothing new: IBM has used technology from Milestone to do something similar for years. But by constructing a 3D model of a person's head from images taken with a battery of four cameras, Canon's prototype uses image analytics developed in house on Milestone software to locate images matching that person, regardless of the angle from which they were seen.
The images required to create the model might be taken following the arrest of a suspect, or captured for the creation of future forms of identity document.
The system might make it easier to track a specific person, but the privacy flipside of this is that investigators would not need to view images of thousands of other people going about their private business.