Patent Grant
9011607
In some industries, such as the food industry and the health care industry, there is a need for workers and/or equipment in a production area to maintain a relatively high level of cleanliness. The invention is directed to automated monitoring and automated control of washing and other cleanliness-related activity in a production area.
An automated process monitors and controls cleaning in a production area by tracking or identifying an object or body part in the production area, monitoring the movement, displacement, velocity profile, or transfer of a fluid (or fluid-like medium) in the production area, analyzing the interaction between the object or body part and the fluid or fluid-like medium, to determine a level of cleanliness achieved, and triggering an event based on at least one member selected from the group consisting of (i) the interaction between the object or body part and the fluid or fluid-like medium and (ii) the level of cleanliness achieved. The event comprises at least one member selected from generating a report, activating an alarm, inactivating equipment in the production area, and blocking access to at least a portion of the production area.
In an embodiment, the tracking or identifying can be carried out using a computer vision camera.
In an embodiment, the automated process can utilize an RFID tag on an object or body part, with the tracking or identifying includes sensing the presence of the RFID tag.
In an embodiment, the tracking or identifying can be carried out with equipment comprising a biometric sensor.
In an embodiment, the tracking or identifying is carried out with equipment comprising a mechanical actuator or electromechanical actuator.
In an embodiment, the displacement, velocity profile, or acceleration of the fluid is carried out with equipment comprising a computer vision camera.
In an embodiment, conductivity is measured in assessing the displacement or velocity profile or acceleration of the fluid.
In an embodiment, electromechanical means (e.g., fly wheel generator, etc.) is used to measure the displacement or velocity profile or acceleration of the fluid.
In an embodiment, chemical or pH measurements are used to determine the displacement or velocity profile or acceleration of the fluid.
In an embodiment, the report includes date and/or time.
In an embodiment, the interaction between the object or body part and the fluid or fluid-like medium is carried out using a computer vision system in combination with at least one member selected from the group consisting of a conductivity sensor, an electromechanical system, a magnetometer, an electrostatic discharge coupler, and a chemical or pH meter.
In an embodiment, the interaction between the object or body part and the fluid or fluid-like medium is carried out using an RFID tag in combination with at least one member selected from the group consisting of a computer vision system, a conductivity sensor, an electromechanical system, a magnetometer, an electrostatic discharge coupler, a chemical meter, and a pH meter.
In an embodiment, the interaction between the object or body part and the fluid or fluid-like medium is carried out using a biometric sensor in combination with at least one member selected from the group consisting of a computer vision system, a conductivity sensor, an electromechanical system, a magnetometer, an electrostatic discharge coupler, a chemical meter, and a pH meter.
In an embodiment, the interaction between the object or body part and the fluid or fluid-like medium is carried out using mechanical or electromechanical activation in combination with at least one member selected from the group consisting of a computer vision system, a conductivity sensor, an electromechanical system, a magnetometer, an electrostatic discharge coupler, a chemical meter, and a pH meter.
In an embodiment, the report is accessible on an interne web page.
In an embodiment, the report comprises a printed report.
In an embodiment, the fluid comprises at least one member selected from the group consisting of water, alcohol, acetone, petroleum distillate (e.g., oil, gasoline, mineral spirits, etc.), turpentine, steam, liquefied gas (e.g., oxygen, hydrogen, helium, nitrogen), hydrogen peroxide, salt solution, sugar solution, syrup, diluted alcohol, hypochlorous acid solution, liquefied metal, a granulated solid (e.g., ice, solid carbon dioxide, etc.), emulsified food, acetic acid solution, fluoric acid solution, carbonic acid solution, and calcium carbonate solution.
In an embodiment, the liquid comprises a dye or marker that is detectable to a camera (e.g., UV reflective material, IR reflective material, etc.).
In an embodiment, the fluid comprises soap.
In an embodiment, the liquid comprises a dye or marker that is detectable to a camera.
In an embodiment, the process further comprises triggering an event based on the assessment of the quality and/or frequency of the cleaning cycle.
A method for insuring that objects, body parts, or individuals (“Item”) are clean and maintained in a clean state within a production environment. The system identifies and/or tracks an item using a combination of computer vision systems, RFID tags, electromechanical actuators or biometric sensors, and discerns the proximity of the item to one or multiple cleaning stations or cleaning devices. The item may engage the cleaning station to activate it or the activation may occur automatically.
Upon activation of the cleaning cycle which may also include the use of a fluid, or fluid-like cleaning “medium” which may also include a liquid or solid soap, is monitored by detecting the dispensing or velocity profile of the “medium”. This may include using a computer vision system that may detect the trajectory of the medium over the item as it is dispensed. In some cases the disturbance of a fixed pool of the cleaning medium and the detection of the interference waves between the item and the cleaning medium may also be observed. In some cases the medium may be delivered as a miming stream, a vapor, a mist, a gel, through dispensers, nozzles, coding machines, thin films, as bars and the simultaneous observation of multiple mediums may be done.
As used herein, the term “fluid” includes fluid-like media, i.e., including both liquids such as water with or without the presence of soap, as well as other flowable compositions such as lotions and solid flowable granules.
As the item interacts with the medium the interaction is monitored to determine that a proper cleaning cycle has occurred. This may include the observation of how long the item was in contact with the cleaning medium, how frequently the cleaning cycle is performed, how covered the item was with the medium or soap, and how much of the medium is eventually removed from the item. Upon completion of the cleaning cycle, secondary drying processes may be performed and the detection of the level of medium removal may be observed. Once the cleaning process is completed the “item” may be tracked so as to ensure proper cleaning cycle timing or may not be tracked and only monitored when in proximity of the cleaning station. In some cases, the absence of a detection of the item may trigger secondary actions such as paging or automated interception to ensure cleaning is performed on a consistent basis. A report may thereafter be generated detailing the sequence of events or cleaning cycle characteristics.
Image data can be processed using video content analysis (VCA) techniques. For a detailed discussion of suitable VCA techniques, see, for example, Nathanael Rota and Monique Thonnat, “Video Sequence Interpretation for Visual Surveillance,” in Proc. of the 3d IEEE Int'l Workshop on Visual Surveillance, 59-67, Dublin, Ireland (Jul. 1, 2000), and Jonathan Owens and Andrew Hunter, “Application in the Self-Organizing Map to Trajectory Classification,” in Proc. Of the 3d IEEE Int'l Workshop on Visual Surveillance, 77-83, Dublin, Ireland (Jul. 1, 2000), both of which are hereby incorporated, in their entireties, by reference thereto.
Generally, the VCA techniques are employed to recognize various features in the images obtained by the image capture devices.
The computer system may use one or more Item Recognition Modules (IRM) to process image data for the recognition of a particular individual or other object in motion, and/or an article used in production that requires periodic leaning. In addition, the computer system may use one or more Location Recognition Module (LRM) to determine the location of a particular individual, body part, or item that requires cleaning. In addition, the computer system may use one or more Movement Recognition Modules (MRM) to process movement data for the recognition of a particular individual or other object in motion, or article. The computer may use IRM in combination with LRM and/or MRM in identifying and tracking movements of particular individual or other object in motion, or of the fluid medium for the purpose of assessing velocity of movement and/or conformational movement characteristics, as well as in assessing whether contamination control requirements are being violated. The IRM, LRM, and MRM can be configured to operate independently or in conjunction with one another.
The image data can be analyzed using human classification techniques that can be employed for the purpose of confirming whether an object is a human, as well as for analyzing the facial features. Face detection may be performed in accordance with the teachings described in, for example, International Patent WO 9932959, entitled “Method and System for Gesture Based Option Selection”, and Damian Lyons and Daniel Pelletier, “A line-Scan Computer vision Algorithm for Identifying Human Body Features,” Gesture '99, 85-96 France (1999), Ming-Hsuan Yand and Narendra Ahuja, “Detecting Human Faces in Color Images,” Proc. of the 1998 IEEE Int'l Conf. on Image Processing (ICIP98), Vol. I, 127-130, (October 1998); and I. Haritaoglu, D. Harwood, L. Davis, Hydra: Multiple People Detection and Tracking Using Silhouettes,” Computer Vision and Pattern Recognition, Second Workshop of Video Surveillance (CVPR, 1999), each of which is hereby incorporated by reference, in its entirety. Face recognition may be performed on one of the faces detected in accordance with the teachings described in, for example, Antonio Colmenarez and Thomas Huang, “Maximum Likelihood Face Detection”, 2nd Int'l Conf. on Face and Gesture Recognition, 164-169, Kilington, Vt. (Oct. 14-16, 1996), which is also incorporated by reference, in its entirety.
As used herein, the phrase “production area” refers to any area in which an automated system is used in a process of monitoring and controlling safety as individuals or machines work in an environment to make any form of measurable progress. While a typical production area would be a factory in which articles of manufacture are being produced, the phrase “production area” includes restaurants, hospitals, gas stations, construction sites, offices, hospitals, etc., i.e., anywhere a product is being produced and/or a service is being rendered. The criteria for controlling cleaning of a production area, and individuals therein, depend upon the particular nature of the production area, i.e., what articles are being produced and/or services offered, and the contamination control requirements associated with those products and/or services.
As used herein, the phrase “work zone” refers to a discrete area that can correspond with an entire production area, one or more discrete regions of a production area, or even an entire production area plus an additional area. Different regions within a production area can have different contamination control requirements. For example, a first work zone could include only a defined area immediately surrounding a particular machine in a factory. The contamination control requirements for the machine operator and others within a specified distance of the machine may be greater than the contamination control requirements just a few meters away from the machine. A factory can have many different work zones within a single production area, such as 2-100 work zones, 2-50 work zones, or 2-10 work zones. Alternatively, a factory can have uniform CCE requirements throughout the production area, which can be one single work zone.
The following examples will be provided hereafter to help further describe the invention.
In one embodiment the system can be used to monitor how frequently a sandwich maker washes their hands. Upon entering the work area each employee can be tracked using a computer vision system. A top view camera can analyze image sequences to localize the individual and individual body parts using several image features, such as (skin) color, blob shape, blob size, blob location, object motion, gradients, blob contours, histogram of oriented gradients (HOG), SIFT, and difference from background images
The image of the production area and the background are obtained by taking images at fixed intervals, using low pass filtering over time:
B(x,y)←τ(x,y)+(1−τ)I(x,y)
where B(x,y) is background image, I(x,y) is the current image, and τ is a predetermined fixed time constant.
Motion can be detected using a motion subtraction method. Motion exists if:
Σ(region of interest){|In(x,y)−In-T(x,y)|}>threshold
Motion detector devices can also be used.
Background subtraction can be carried out by obtaining an image of objects in the foreground, using:
S(x,y)=|I(x,y)−B(x,y)|>th
wherein S(x,y) is the foreground image (i.e., a binary image), B(x,y) is the background image, and th is a predetermined threshold value.
Body parts can also be segmented by their colors, using:
(c−x)TM(c−x)<th
wherein “c” represents predetermined color, “x” represents pixel color to be tested, “M” represents predetermined matrix, and “th” represents a predetermined threshold.
HOG is defined by Ogale, “A Roadmap to the Integration of Early Visual Modules”, IJCV Special Issue of Early Cognitive Vision, vol 72, no. 1, 9-25 (April 2007), hereby incorporated, in its entirety, by reference thereto.
Blob shape can be defined by centroid, angle, long axis, short axis of ellipse approximation, perimeter, pixel number.
SIFT is as defined by Lowe, in U.S. Pat. No. 6,711,293, which is hereby incorporated, in its entirety, by reference thereto.
Tracking the individual can be performed using a TSV transform as that described by Sato and Aggarwal in “Temporal Spatio-Velocity Transform and its Application to Tracking and Interaction”, Computer Vision and Image Understanding, 96, pp 100-128 (2004), hereby incorporated, in its entirety, by reference thereto.
If, after an elapsed time period, which may be determined by the manager on duty, the worker has not approached the wash station (which may be pre-identified visually within an area by the computer vision system) then a reminder may be broadcast via a pager or auditory device. Another embodiment may use an RFID antenna clipped on a name tag and a reader placed near the wash station. For example, the Astra-A5-NA-POE integrated RFID reader/writer manufactured by ThingMagic, Inc, of Cambridge, Mass. When the employee approaches the sink, the system records their presence in a log file and uses this as a basis for further analysis. The secondary step involves the determination of whether the cleaning medium or soap is dispensed and whether the employee has washed their hands under the faucet for a sufficient period of time. A conductivity sensor such as a temperature sensitive faucet light water flow indicator attached to the faucet detects whether the water is flowing and this information, coupled with the verification on the vision camera that the hands of the sandwich maker are under the faucet and covered in water, provide feedback that the washing event has occurred. To determine that the worker's hands were located under the water faucet the following algorithms may be used incorporating blob analysis.
In addition a light emitting diode may be combined with the conductivity sensor and the light may be used as a marker that the computer vision system can detect. This marker may further indicate the temperature of the water; as an example red light for hot and blue light for cold. The system may catalog the water temperature used by the sandwich maker to determine the level of cleanliness achieved. A report may be generated in the following format:
In meat processing facilities it is common that a boot cleaning area be designated prior to entrance to the de-boning or meat carving area. This usually consists of a shallow 1-3 inch deep soap bath placed on the floor, through which workers are required to walk and move their feet. The solution contains chemicals that disinfect and kills germ that could migrate to the food processing area. One embodiment would use a vision system to track the approach of an individual.
Using blob analysis, features are extracted from each blob, following which the data is processed to determine whether the smallest feature distance from a model is less than a threshold value th. If the smallest feature distance is not less than the threshold value, the boot is determined to be on an individual, and further analysis can be done to determine the position of the boot in the bath.
The extraction of features from each blob is carried out by determining the long radius of the fitted ellipse, determining the short radius of fitted ellipse, determining the distance from a model contour by (a) fining the closest point in the object contour from model contour, and (b) summing the distances.
The smallest feature distance is determined by assessing the blob feature as:
x=(1,x1,x2,x3,·T,
assessing the model feature as:
y=(1,y1,y2,y3,·T,
and assessing the feature distance as:
d=(x−y)TM(x−y).
Since there can be more than one model, find minimum of d. M is matrix, often used as inverse covariance.
Judging whether the smallest feature distance is less than the threshold value can be carried out as follows:
if (x1>th1) and (x2<th2) and (x3<th3),
then the boot is determined to be on. Otherwise, the boot is determined to be off.
Tracking a boot blob and maintaining stable properties of the boot-associated with the bath so that these properties can be used to make consistent determinations of whether the boot is inside or outside the bath, are carried out as follows:
Sequence breaks are found by supposing t0, t1, t2, . . . are instances when a motion is detected. If (tn+1−tn)>threshold, then there is a sequence break between tn+1 and tn. Otherwise, tn+1, and tn are in the same sequence. The results are grouped by sequence. Focusing on each sequence, count the number of boot OFF images (=NOFF). If NOFF>threshold, then output warning with image. Find a warning image in the sequence.
As the individual steps in the bath the interface between the boot and the fluid medium is detected by the camera and the system records the contact time. An indicator light can be placed ahead of the bath and activated when the proper amount of time has passed. Inappropriate shifting of boots wherein minimal fluid coverage of the boot is detected can be recorded and quickly reported. An RFID tag placed on the employee's hard hat or apron can be used to further provide additional information about the individual.
In both food service restaurants (such as ice cream shops, sandwich shops, or salad shops) and meat processing plants it is common for utensils to be cleaned properly between users to prevent cross contamination between foods. A strain of E. coli or other bacteria may be present on a particular food item or utensil and the use of knives, forks, or scoops used to cut or serve the foods can cause harm on a large scale. To prevent this, utensils should be placed in soak baths which contain low concentrations of disinfectants including acidic solutions. This may be after each use or after a specified time period. In one embodiment a utensil may be tracked by a vision camera when it is brought in contact with food items. Food can be identified by color detection and assessed as follows. First, for each pixel p1=[R G B] and p2=[R G B], pixel distance d is defined as
d=(p1−p2)tΣ(p1−p2)
where Σ is a matrix, in which inverse of covariance matrix is often used. N of pre-determined pixel sample represents food: (s1, s2, s3, . . . , sN). Pixel distance (d1, d2, d3, . . . , dN) is computed from each pre-determined pixel (s1, s2, s3, . . . , sN). The minimum distance within N set of distances is found using: dmin=min{d1, d2, d3, . . . , dN}. Thresholding can be carried out using a pre-determined value th. If the distance is smaller than th, the pixel is food, otherwise, the pixel is not food.
Another method of color detection, which is faster, utilizes color vector analysis wherein p=[R G B], with pre-determined vectors a1, a2, a3,·p is food pixel if
(a1tp<th1)∩(a2tp<th2)∩(a3tp<th3)∩
In determining whether the food is on or off, either of the following methods can be used. Using simple thresholding, assume features x1, x2, x3, x4 and predetermined threshold th1, th2, th3, th4, judge food as present if:
(x1>th1)∩(x2>th2)∩(x3>th3)∩(x4>th4)
This may also be cross-referenced with an accelerometer and transmitter placed within the utensil or a visual marker placed on the handle of the utensil. A food item can be further detected using the vision camera and identified as a potential pathogenic source. Algorithms used to detect the food can include color based sensing. A secondary step, once the utensil has been determined to require cleaning; a proactive or training procedure may be enacted. In a proactive step, the identification of the utensil would allow the transfer of a signal that would activate a small light emitting diode on the utensil. A washing bath placed close to the employee could also have a light activated upon it to signal appropriate washing times. In a training mode, the system could record the non-compliance and create a report of the infraction and any potential foods that may have been contaminated by the occurrence.
This application claims the benefit of, and incorporates by reference the entirety of Provisional application No. 61/404,683 filed Oct. 7, 2010.
| Number | Name | Date | Kind |
|---|---|---|---|
| 5023597 | Salisbury | Jun 1991 | A |
| 5164707 | Rasmussen et al. | Nov 1992 | A |
| 5305390 | Frey et al. | Apr 1994 | A |
| 5465115 | Conrad et al. | Nov 1995 | A |
| 5781650 | Lobo et al. | Jul 1998 | A |
| 5973732 | Guthrie | Oct 1999 | A |
| 6104966 | Haagensen | Aug 2000 | A |
| 6166729 | Acosta et al. | Dec 2000 | A |
| 6208260 | West et al. | Mar 2001 | B1 |
| 6283860 | Lyons et al. | Sep 2001 | B1 |
| 6392546 | Smith | May 2002 | B1 |
| 6600475 | Gutta et al. | Jul 2003 | B2 |
| 6650242 | Clerk et al. | Nov 2003 | B2 |
| 6697104 | Yakobi et al. | Feb 2004 | B1 |
| 6853303 | Chen et al. | Feb 2005 | B2 |
| 6970574 | Johnson | Nov 2005 | B1 |
| 7015816 | Wildman et al. | Mar 2006 | B2 |
| 7019652 | Richardson | Mar 2006 | B2 |
| 7065645 | Teicher | Jun 2006 | B2 |
| 7317830 | Gordon | Jan 2008 | B1 |
| 7319399 | Berg | Jan 2008 | B2 |
| 7375640 | Plost | May 2008 | B1 |
| 7464001 | Adams | Dec 2008 | B1 |
| 7495569 | Pittz | Feb 2009 | B2 |
| 7534005 | Buckman | May 2009 | B1 |
| 7689465 | Shakes et al. | Mar 2010 | B1 |
| 7832396 | Abernethy | Nov 2010 | B2 |
| 8208681 | Heller et al. | Jun 2012 | B2 |
| 8279277 | Nam et al. | Oct 2012 | B2 |
| 20020190866 | Richardson | Dec 2002 | A1 |
| 20030058111 | Lee et al. | Mar 2003 | A1 |
| 20030061005 | Manegold et al. | Mar 2003 | A1 |
| 20030093200 | Gutta et al. | May 2003 | A1 |
| 20030163827 | Purpura | Aug 2003 | A1 |
| 20030169906 | Gokturk et al. | Sep 2003 | A1 |
| 20030184649 | Mann | Oct 2003 | A1 |
| 20050027618 | Zucker et al. | Feb 2005 | A1 |
| 20050094879 | Harville | May 2005 | A1 |
| 20050134465 | Rice et al. | Jun 2005 | A1 |
| 20050248461 | Lane et al. | Nov 2005 | A1 |
| 20060033625 | Johnson et al. | Feb 2006 | A1 |
| 20060219961 | Ross et al. | Oct 2006 | A1 |
| 20060220787 | Turner et al. | Oct 2006 | A1 |
| 20060244589 | Schranz | Nov 2006 | A1 |
| 20060272361 | Snodgrass | Dec 2006 | A1 |
| 20070018836 | Richardson | Jan 2007 | A1 |
| 20070122005 | Kage et al. | May 2007 | A1 |
| 20080001763 | Raja et al. | Jan 2008 | A1 |
| 20080031838 | Bolling | Feb 2008 | A1 |
| 20080136649 | Van De Hey | Jun 2008 | A1 |
| 20080189142 | Brown et al. | Aug 2008 | A1 |
| 20080189783 | Music et al. | Aug 2008 | A1 |
| 20080247609 | Feris et al. | Oct 2008 | A1 |
| 20090040014 | Knopf et al. | Feb 2009 | A1 |
| 20090051545 | Koblasz | Feb 2009 | A1 |
| 20090079822 | Yoo et al. | Mar 2009 | A1 |
| 20090128311 | Nishimura et al. | May 2009 | A1 |
| 20090135009 | Little et al. | May 2009 | A1 |
| 20090161918 | Heller et al. | Jun 2009 | A1 |
| 20090195382 | Hall | Aug 2009 | A1 |
| 20090224868 | Liu et al. | Sep 2009 | A1 |
| 20090224924 | Thorp | Sep 2009 | A1 |
| 20090237499 | Kressel et al. | Sep 2009 | A1 |
| 20090273477 | Barnhill | Nov 2009 | A1 |
| 20100155416 | Johnson | Jun 2010 | A1 |
| 20100167248 | Ryan | Jul 2010 | A1 |
| 20100183218 | Naito et al. | Jul 2010 | A1 |
| 20100245554 | Nam et al. | Sep 2010 | A1 |
| 20110057799 | Taneff | Mar 2011 | A1 |
| 20120062382 | Taneff | Mar 2012 | A1 |
| 20120062725 | Wampler et al. | Mar 2012 | A1 |
| 20120146789 | De Luca et al. | Jun 2012 | A1 |
| Number | Date | Country |
|---|---|---|
| 1 939 811 | Jul 2008 | EP |
| 100 789 721 | Jan 2008 | KR |
| 9932959 | Jul 1999 | WO |
| 2007090470 | Aug 2007 | WO |
| 2007129289 | Nov 2007 | WO |
| 2008152433 | Dec 2008 | WO |
| 2010026581 | Nov 2010 | WO |
| Entry |
|---|
| A. Criminisi, A. Zisserman, L. Van Gool, Bramble S., and D. Compton, “A New Approach To Obtain Height Measurements from Video”, Proc. of SPIE, Boston, Massachussets, USA, vol. 3576, pp. 227-238 (Nov. 1-6, 1998). |
| A Revolution in Traceability, Foodproductiondaily.com, 1 page, (Mar. 10, 2004). |
| Eye in the Sky (camera), Wikipedia, 1 page (Dec. 11, 2009). |
| Edge Detection, Wikipedia, 8 pages (Feb. 10, 2010). |
| Corner Detection, Wikipedia, 12 pages (Feb. 9, 2010). |
| Athanasia et al, “P1714 Compliance of healthcare workers with hand hygiene rules in the emergency room of two tertiary hospitals in the area of Athens”, International Journal of Antimicrobial Agents, Elsevier Science, Amsterdam, NL, vol. 29, Mar. 1, 2007, p. S486, SP022038903, ISSN: 0924-8579, DOI:DOI:10.1016/S0924-8579(07)71553-4. |
| Grange, Sebastian, Baur, charles: Robust Real-time 3D Detection of Obstructed Head and Hands in Indoors Environments:, J. Multimedia, vol. 1, No. 4, Jul. 2006, pp. 29-36, XP002639938, US. |
| United States Department of Agriculture: “Machine Vision sees food contamination we can't see”, Agricultural Research Magazine, vol. 50, No. 8 Aug. 2002, XP8137410, US, retrieved from the internet: URL:http://www.ars.usda.gov/is/AR/archive/aug02/food0802.pdf {retrieved on May 31, 2011]. |
| Bhatt J et al: “Automatic recognition of a baby gesture”, Proceedings 15th IEEE International Conference on Tools with Artificial Intelligence. ICTAI 2003. Sacramento, CA, Nov. 3-5, 2003; Los Alamitos, CA, IEEE Comp. Soc, US, vol. CONF. 15, Nov. 3, 2003, pp. 610-615, XP010672284, DOI: DOI:10.1109/TAI.2003.1250248 ISBN: 978-0-7695-2038-4. |
| Lohr, S., “Couputers That See You and Keep Watch Over You,” The New York Times, 5 pp, Jan. 1, 2011. |
| “GE Healthcare's Smart Patient Room to Begin Data Collection,” 3 pages, Sep. 15, 2010. |
| U.S. Appl. No. 61/275,582, filed Sep. 1, 2009, Taneff. |
| Number | Date | Country | |
|---|---|---|---|
| 20120085369 A1 | Apr 2012 | US |
| Number | Date | Country | |
|---|---|---|---|
| 61404683 | Oct 2010 | US |
