ISAST LEONARDO, Vol. 36, No. 3, pp. 199,207-210, 2003 (PDF)
INTELLIGENT FIXTURES AND SYSTEMS: Steve Mann, Mediocrat (S. Mann is Currently an Assistant Filing Clerk Trainee of EXISTech Corp.) 284 Bloor St. West, Suite 701, Toronto, Ontario, Canada, M5S 3G4 ABSTRACT EXISTech Corporation's computer networks and control systems, together with infrared image sensors, facilitate hygienic touchless control of plumbing fixtures. Two of EXISTech's sensors are described in detail: an active infrared faucet sensor (320x240 pixels) and a passive infrared autoflush sensor (160x120 pixels). The internetworked plumbing systems help facility managers and law enforcement personnel remotely monitor the operation of fixtures in various bathrooms. A single infrared sensor array can also be used for controlling several showers, faucets, urinals, or water closets in large bathroom complexes. Intelligent bathroom fixtures and systems based on computer vision help enhance the privacy of users by ensuring that law abiding users need not be disturbed by police foot patrols into the restroom areas. The intelligent quantimetric sensing technology eliminates the need for privacy-invading foot patrols. New computer vision algorithms also automatically detect slip-and-fall accidents as well as vandalism and contraband disposal, to assist remote monitoring by law enforcement. INTRODUCTION This paper describes new approaches to the design of automatic sensor operated bathroom fixtures, systems for controlling bathroom fixtures, and methods of bathroom fixture design, control, and management, through the use of new computer vision technologies, and image processing. Networked plumbing systems also help facility managers monitor the operation of various bathroom complexes from a central remote location. SMART BATHROOMS WITH VIDEO BASED MOTION DETECTION By using video based sensors, the intelligent bathroom provides a safe, hygienic, and user friendly environment that responds automatically to the needs of the user. Concomitant functions, such as security, drowning prevention, and other safety features are possible with the intelligent bathroom. It is assumed that the benefits of automation of fixtures will cause sensors to be installed in virtually all bathrooms of the future. It is also expected that the most economical sensors will be single chip video cameras, which now only cost $10 in mass production, whereas other sensors such as infrared position sensing devices now used in electronic plumbing systems cost much more because they are specialized devices. Similarly radar and sonar systems commonly used for occupancy detection (for automatic door openers, lighting control, etc.) now cost more than low cost single chip video cameras. Once these cameras are installed in most bathrooms, new uses, such as automation of lighting, automatic bathroom door openers, automatic call for help in case of slip and fall injury, and automated detection of vandalism will emerge. Sensor systems used in many of EXISTech Corporation's research prototype bathroom facilities comprise standard video cameras with infrared blocking filters removed to make them sensitive in the infrared. Because of mass production, a single camera costs much less than one of the specialized sensors commonly used to automatically flush toilets and urinals. Moreover, further cost savings are introduced by the fact that a single video camera can monitor a number of fixtures. For example, one video camera can monitor a whole row of urinals, to flush only the urinals that have been used. Intelligent computer vision systems monitor optical traffic flow patterns, so that a weaker flush is used when others are standing in line to use a urinal, whereas a stronger flush is provided after the last user of a group of users has finished. Thus intelligent video based sensor technology will reduce initial installation costs as well as operating costs, when compared to other sensor technologies. Camera based sensors can provide a much more intricate and sophisticated form of control, because they can detect user behaviour, usage patterns, optical traffic flow patterns, and other attributes not evident in traditional bathroom presence or occupancy sensors. Different kinds of optical elements are being used in EXISTech Corporation's experimental bathrooms . For example ceiling domes that provide the sensor with a wide field of view are being used for controlling a large number of bathroom fixtures with just one sensor. Many of the lowest cost cameras have wide angle lenses. A camera with a fisheye lens can be placed on the ceiling of a shower room, so that it can monitor the entire shower room. Therefore a single sensor can be used to automate many showers. Such a single sensor is out of the way of vandalism, soap scum buildup, or other problems that would arise if sensors were distributed along walls of the shower room with one sensor under each shower head. Users will enjoy a nice hot shower, without having to adjust the temperature, or even touch anything at all. Users simply step into the viewing area, comprised of a plurality of detection zones, and the shower within their detection zone turns on. Instantly, out comes water at the perfect temperature! When a user steps away to lather up with soap, the water turns off. When the user steps toward the spray head for a rinse, the water turns on again. Moreover, maintenance and installation are simplified by having one image sensor controlling various shower spray heads. Additionally, the one image sensor may provide other features such as automatically warning building staff if a person has slipped and fallen, or automatically recognizing faces of users, and providing each user with water tempered to the preference of each individual user. The video based motion detection sensor will also act as a deterrent to crime and vandalism in the shower room. Additionally, multiple spray heads at each station can spray a user with water in such a way that very little is wasted. A beam pattern of spray can adapt to the position and orientation of the user's body. EXISTech's intelligent bathroom control systems can be reprogrammed to respond to users in slightly different ways, and therefore user behaviour can be modified slightly. Through slight modifications in user behaviour, efficiency and restroom throughput can be increased. For example, the system might detect that, in a row of hand faucets, the furthest one is used excessively during certain times of day. It might be determined that a homeless person is using it for hair washing purposes, especially if it is somewhat hidden from view. The system can detect this pattern of deviant use, and correct it by adjusting the timing on that particular fixture so that it will time out sooner than the others. This would effectively move that user to another faucet. Thus slight changes in system parameters can be used to effect slight changes in user behaviour. Data output from an infrared sensor operated faucet is shown in Figure 1. By representing the numerical values in the array as shades of grey, we can see the detection zone, where the hands of a bather are present. [insert FIGURE 1 http://wearcam.org/fig1.tif and CAPTION somewhere near here] [1 column width] The sensor produces its own source of light, so that it operates irrespective of ambient light (if any, e.g. it will also work in a completely dark room). The faucet runs GNU Linux and is connected to the Internet for remote maintenance and monitoring. A central computing facility at an undisclosed branch of EXISTech's headquarters monitors a worldwide network of bathroom facilities. However, each fixture or group of fixtures has its own processor so that the systems will continue to run during network outage. Statistical information is logged locally and files are updated using the UNIX rsynch feature, when the network comes back online. Figure 2 shows the result of statistical analysis performed by a miniature computer system . [insert FIGURE 2 http://wearcam.org/fig2.tif and CAPTION somewhere near here] [1 column width] SMART TOILETS In addition to automation of water flow to sinks, showers, bathtubs, etc., EXISTech sensors may be used to automatically flush toilets and urinals. A single sensor can control a row of fixtures. With toilets that are in stalls, one sensor is needed for each two toilets. However this still provides a savings, in that if there are an even number, N, of toilets, then only N/2 sensors are needed. Typically, a passive infrared sensor is used for automatic flush, because passive sensors tend to perform better at detecting recently deposited waste products (owing to heat from the body which causes waste products to be warmer than their environment). Since toilets and urinals are supplied with cold-only plumbing (as opposed to showers and sinks which usually receive both hot and cold water supply), the passive thermal sensor is the best choice for automatic flush. Computer vision systems with sensor arrays save water by distinguishing the difference between urination and defecation, as illustrated in Figure 3. When urination is detected a smaller quantity of water is used, whereas more water is used to clear the solid waste matter from the bowl after defecation is detected. [insert FIGURE 3 http://wearcam.org/fig3.tif and CAPTION somewhere near here] [3 column widths, across page] Sloppy aim, forgetting to flush, and other acts of negligence can also automatically be detected and appropriate action taken (notification of authorities, automatic flushing of toilets, automatic release of perfume or pepper spray, etc.) Advantageously, ceiling mounted infrared sensors can also be used to automatically categorize inter-stall activity, such as distinguishing changing of clothes from the passing of contraband, as illustrated in Figure 4. [insert FIGURE 4 http://wearcam.org/fig4.tif and CAPTION somewhere near here] [3 column widths, across page] SMART SHOWERS Additional features of image-based motion detection can also be applied to shower rooms to provide user safety and security, by way of watching the user to make sure that the user is attended to when encountering danger through tripping and falling, such as when slipping on a soapy shower room floor. High quality pictures assist facility managers in monitoring usage patterns, to help reduce or eliminate deviant behaviour such as excessively long showering, shaving in the shower room, vagrancy, the washing of clothes in the shower room. Using the appropriate software, with artificial intelligence, management can be sure to maximize user satisfaction by making certain one inconsiderate user does not decrease the user-satisfaction of other users. In addition to deterring crime and vandalism, intelligent plumbing fixtures can also be used to respond to acts of terrorism. A regular shower facility in a typical locker room setting can also double as a mass decontamination facility in times of emergency. In this case, having full color video feeds assists remote decon officers in determining, for example, if a powder on a patient's body is grey powder such as anthrax, or some other color of powder. A unique hexagonal architecture, as shown in Figure 5, speeds throughput, when used with a six person sensor operated column shower installed in each of the men's and women's shower rooms. [insert FIGURE 5 http://wearcam.org/fig5.eps and CAPTION somewhere near here] [2 or 3 column widths, across] A six person column shower having six nozzles around a hexagonal/round column, is used to match this hexagonal architecture. Optics is comprised of a single sheet of smoked polycarbonate that was heated and bent around the outside circumference of the round column, and then inserted inside, after six viewing holes were drilled. A typical installation of this invention uses optics with approximately 15% transmissivity, so that the degree of light coming back from light that first passes into the viewing window and back out is 2.25%, which falls nicely below the 4% level of light reflected from typical such material. This allows color cameras to be concealed within the column, out of sight of vandals. An adhesive sealant makes the inside of the column water tight. Six video cameras are installed in the column with a 45 degree mirror on each one. Every second camera is pointing up from underneath, while the other three point down from above. An embedded computer embodies video capture devices in the column to locally control six separate solenoid valve actuators, while also providing remote connectivity. Appropriate software detects the presence of users, and turns on the appropriate showerheads where flesh is detected. In this way no water is wasted. In a typical installation, one such column is placed in the hexagonal men's and women's shower rooms of a mass decontamination facility . Since there are six cameras in each shower and six cameras in the central triage room there are a total of 18 cameras, which can be displayed on two television sets as a 3 by 3 mosaic of images (a 9-up image on each TV). This allows two TV sets to be used, one for the men's side and the other for the women's side. A square lattice of images ensures the same aspect ratio of any one image, so that the images efficiently use the TV screen real estate at the decon officer's station. A typical screen shot of the sensor operated column shower in actual usage (men's shower room, anthrax mailroom decon exhibit , July 2001) is shown in Figure 6. [insert FIGURE 6 http://wearcam.org/fig6.tif and CAPTION somewhere near here] [3 column widths, across page, or perhaps run sideways to get wider] CONCLUSION: Infrared sensor operated plumbing fixtures can incorporate recent advances in computer vision. Passive infrared sensor arrays are optimal for computer control of toilets and urinals, whereas active infrared sensor arrays are most suited to the control of sinks and showers. However, for emergency preparedness, where telemedicine and remote triage are essential, showers should be equipped with full-color sensing capability, especially helpful in the identification of perpetrators who may be among the victims of a bioterror attack. References and Notes: 1. See http://existech.com and http://wearcam.org/safebath/index.htm 2. This work is based on a new kind of Knowledge Representation theory called "SETS", with example in http://www.wearcam.org/faucet.htm 3. See Canadian Patent 02303611, filed April 1, 2000, and link from a July 2001 exhibit at Gallery TPW, http://wearcam.org/tpw.htm with curatorial essay in http://www.existech.com/tpw/index.html. 4. See the press release, "Mailroom begins operations June 30th; public tours July 5, 2001, at 7:00pm" and the call for volunteers in a mass casualty anthrax decontamination drill, http://www.existech.com/press_release_deliverify.htm BIO: S. Mann was born in Canada, and spent much of his childhood days inventing various kinds of smart clothing and wearable computers. He went to the United States to study at Massachusetts Institute of Technology, receiving his PhD degree in 1997, prior to returning to Canada as an Assistant Filing Clerk Trainee for EXISTech Corp. He is also a faculty member at University of Toronto. --------figure captions-------- All photo credits are to S. Mann, and artwork is by S. Mann. See file mannfigs.txt, reproduced below: FIGURE 1, http://wearcam.org/fig1.tif CAPTION: Data output from an infrared sensor operated faucet, wherein an infrared emitter, and infrared detector are up inside the spout of a gooseneck faucet. The infrared detector returns a byte array having 240 rows and 320 columns. By representing the numerical values in the array as shades of grey, we can see the detection zone, where the hands of a bather are present. A small part of the spout (visible at the bottom of the array), as well as most of the sink, is visible to the infrared sensor. Note also the specular highlights from the infrared source that is built into the sensor. FIGURE 2, http://wearcam.org/fig2.tif CAPTION: Statistical analysis of faucet sensor array data. This array represents a Boolean array of bather present/absent. Such an array may be used to automate sinks, shower facilities, and bath tubs. Statistics of the bather-absent basin with the faucet running, subtracted from a known average of known samples of the array, of the empty basin with water running, are used to automate the operation of the fixture. FIGURE 3, http://wearcam.org/fig3.tif CAPTION: Classification of waste type, and detection of negligence. Passive infrared heat sensors are used for automatic flush, where fixtures are connected to cold water only. The computer vision system can detect waste products based on their thermal signature. Urination, e.g. as happening in Stall 1, where the stream of warm urine as well as the urine in the bowl, is visible can automatically be distinguished from the defecation taking place in Stall 3 where solid waste matter is visible in the bowl, by virtue of the thermal contrast between warm bodily waste and the colder surrounding water. Note also that in Stall 4, there is a visible thermal butt print on the toilet seat, and two thermal footprints where the cement floor is still warm. This heat signature indicates evidence of a recent usage of the toilet in Stall 4. FIGURE 4, http://wearcam.org/fig4.tif CAPTION: A person in Stall 1 undresses and places clothes up on the stall divider, temporarily. The computer can recognize that all of the articles of clothing are eventually retrieved by the user of Stall 1. However, when articles are passed from one stall to another, the computer vision algorithms track the passing of articles, such as in Stalls 3 and 4, where contraband is passed underneath the stall divider. In this way an alarm is sent to the authorities, together with live video of only Stalls 3 and 4, while masking out the information in Stall 1, to protect the privacy of the person who is changing his clothes. FIGURE 5, http://wearcam.org/fig5.eps CAPTION: Hexagonal architecture increases bathroom throughput and efficiency for mass casualty bioterror response preparedness, such as in response to a spilled salt shaker or other mysterious white or grey powder. Separate high security Rotogate (TM) turnstiles for men and women lead into gender-specific undressing areas. There six men, and six women, remove all clothing, jewellery, wearable computers, and other personal effects. When all six have complied by stripping completely, they are allowed to pass into the shower rooms, through turnstiles that are unlocked by a guard in the central control room. Another six men and six women are then herded into the undressing rooms while the first group are showering. To protect the privacy of those undergoing decon, the walls of the central guard tower are made of darkly smoked bulletproof glass or polycarbonate and there are black cloth baffles inside the control room. Thus men cannot see through to the women's side, or vice versa. After showering, victims are then allowed to enter the examination rooms, through another remotely unlocked turnstile. Telemedicine facilitated by high resolution videocameras allows remote triage staff to perform a medical exam, and permit healthy persons to leave. FIGURE 6, COLOR FIGURE, http://wearcam.org/fig6.tif (if it is not possible to have 1 color fig, use fig6grey.tif) CAPTION: Screen shot from the male decontamination officer's station. The screen window is approximately 2048 pixels across, for being displayed on a high resolution computer screen (the kind of display typically used for an air traffic control screen). Here a time-lapse video (live video of examination combined with slightly delayed shower video, and much delayed undressing video) displays the same victims appearing at three different stages of decon at the same time. S. Mann, 80 Spadina Avenue, Toronto, July 5th, 2001.