JP2005069977A - Device and method for tracking moving route of object - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To accurately track a moving locus of an object. <P>SOLUTION: A marker 61 is adhered onto the moving object 50. Fixed markers 11, 12, 13 are bonded respectively to a floor, a wall and a shelf of a room 70. A camera 21 monitors an inside of the room 70 all the time. computer system 30 calculates distances between the object 50 and the respective fixed markers 11, 12, 13 on a screen photographed by the camera 21, when the object 50 comes into the room 70, and stores the number of the fixed marker corresponding to the minimum distance and a measuring time therein. The computer system 30 prepares a moving route of the object 50 based on the stored fixed marker and measuring time, when the object stops the moving or goes out from the room 70, and displays it on a display. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to a method and an apparatus for tracking a movement path of an object by recognizing a marker attached to the object with a camera.

  Finding quickly movable objects in a room can often be difficult. There is a risk that the object may be stored in a storage or a desk, or moved to another room, and the object may be mixed in a place that is not intended.

  One possible solution to this problem is to attach a tag, such as an RFID, that can emit an identification signal to the object. In this system, when a tag is attached to an object, a plurality of objects can be specified by assigning different transmission frequencies.

Another solution is to detect all the moving footprints of the object entirely from the image. The room is always photographed with a camera, and a moving image of the object is acquired. In order to identify a target object, a feature quantity unique to the object image is extracted in advance. The movement trajectory is acquired by specifying an object image from the video of the camera using the feature amount. In this case, the system is inexpensive.
NTT Technical Journal June 2002 P32 "Ubiquitous Application Using RFID Tags" Murase, V. V. Vinod: “High-speed object search using local color information. Active search method.” IEICE Transactions D-II Vol. J81-D-II, no. 9, pp. 2035-2042, 1998 2001 Annual Conference of the Institute of Electrical Engineers of Japan, Proceedings, p649 “Examination of equipment management system using image data”

  In the former solution, the resolution of a generally available identification system is extremely low, and it is only possible to specify a location on the order of several meters. Further, in such a system, a position detector equipped with a reading system must generally be placed in close proximity, and a plurality of detectors must be installed in a space such as a room.

  In the latter solution, since real-time processing is difficult with the current computer performance, the camera video must be taken into a storage medium, which places a burden on the computer. Furthermore, the accuracy of object feature extraction is a problem, and it is difficult to specify only the intended object from a large amount of video.

  The object of the present invention is to provide an inexpensive object movement that can simultaneously grasp the positions of many moving objects without placing a position detector in the vicinity of the object, and as a result, can accurately track the movement path of the object. It is to provide a path tracking method and apparatus.

  A marker for identifying the object and identifying its position is attached to each object that tracks the movement path, and a plurality of fixed markers are arranged in the space in which the object moves. The inside of the space is photographed with a camera, the distance between the object and each fixed marker on the image is measured, and the identification information of the approaching fixed marker (with the smallest distance) and the measurement time are stored in the memory. When the object stops moving or leaves the space, the moving path information of the object is created from the stored identification information of the fixed marker and the measurement time.

  The reason why the moving path of the object can be known only by measuring the distance between the object and the fixed marker will be described below.

  All markers in the field of view are constantly photographed with a fixed camera. Thus, it is possible to measure to which fixed marker (on the image) how far the object with the marker is (for example, moving near the fixed marker A (fixed to the wall) How many pixels the object marker B has approached the time hh: mm: ss). This is a distance on the image to the last, and information in the depth direction is not taken, so it is different from the distance in the actual space. However, on the camera image, the history of the object approaching there can be pulled out from each fixed marker, and the locus on the image can be followed. As a practical matter, when this tracking information is used for searching for an object or the like, it is practically sufficient to know where and when it passed on the camera image.

  For example, with respect to the object B, the fixed marker F1 in which the object B is close is expressed as the time aa: bb: cc fixed marker F1 and the time dd: ee: ff fixed marker F2 together with the time.

  Note that the amount of data to be saved can be reduced by saving the fixed marker identification information and the measurement time only when the minimum distance is equal to or smaller than a predetermined size. In this case, the entire movement locus in the space of the moving object is not displayed.

  As described above, according to the present invention, tracking of the movement path of an object can be realized with a simple system using a marker attached to the object, a fixed marker placed indoors, and a camera. It is possible to quickly find where an object that can move in the room is, and by tracking the movement trajectory, it is possible to easily acquire information such as the location and time used by the object.

  Next, embodiments of the present invention will be described with reference to the drawings.

[First Embodiment]
FIG. 1 shows the configuration of an object movement path tracking system according to a first embodiment of the present invention.

  A marker 61 is attached to the moving object 50 in order to identify the object 50 and specify its position. Fixed markers 11, 12, and 13 for tracking the trajectory of the moving object 50 are attached to the floor, wall, and shelf in the room 70, respectively. A camera 21 is installed in the room 70. This camera 21 has a field of view of the entire room. The computer system 30 is connected to the camera 21, and calculates the distance of the moving object 50 from the fixed markers 11, 12, and 13, stores data, and creates and displays a moving path. Of course, the computer system 30 may be arranged outside the room 70. The camera 21 may be connected wirelessly or by a wire link and may be a stand-alone type, or may be connected to a computer network in order to distribute data storage and processing and perform high-speed data transfer.

  FIG. 2 is a block diagram of an object movement path tracking program that is read and executed by the computer system 30. This program is stored in a recording medium such as a floppy disk, a magneto-optical disk, a CD-ROM, or a storage device such as a hard disk device built in the computer system 30. Further, it may be transmitted via the Internet.

  In this system, as a marker 61, a two-dimensional marker (http://www.hitl.washington.edu/research/shared_space/) developed at the University of Washington and provided as freeware is used as an example. This marker has a pattern drawn in the center. When the camera 61 captures the marker 61, the marker 61 is identified by template matching between the center pattern and a pattern registered in the computer system 30 in advance. The object 50 being identified is identified. Furthermore, the three-dimensional spatial position from the camera 21 can be determined by the computer 31 by comparing the shape of the marker 61 with the registered pattern.

  FIG. 3 is a flowchart showing the processing sequence of this embodiment. The camera 21 constantly monitors the inside of the room 70. When the object 50 enters the room 70 (step 101), the inter-marker distance calculation unit 31 displays the distance between the object 50 (marker 61) and each of the fixed markers 11, 12, and 13 (inter-marker distance). Is calculated (step 102). The data storage determination unit 32 compares the minimum distance among the calculated marker distances with a predetermined value (step 103). If the distance is equal to or less than the predetermined value, the fixed marker number corresponding to the minimum distance, the minimum distance Then, the measurement time information is stored in the position information database 33 (step 104). The calculation of the distance between the markers and the storage of the data described above are such that the object 50 enters the room 70 and is captured by the camera 21 and then placed in the room 70 and stops moving, or is taken out of the room 70 and moved to the marker. The process is continued until 61 cannot be recognized (step 105). Further, if the number of moving objects is small, there is no problem in storing all data, but if the number of moving objects is large, there is a possibility that the data becomes large and places a burden on the computer system 30. In order to prevent such a situation, in this system, data is stored in the position information database 33 only when the moving object 50 is closer than a certain distance to the fixed markers 11, 12, and 13 reflected in the camera 21. Yes. As a result, the data when the moving object 50 approaches the fixed markers 11, 12, 13 is divided for each of the fixed markers 11, 12, 13 and stored in the position information database 33, thereby suppressing the amount of individual data. Can do. The object trajectory information display unit 34 reads the fixed marker number and measurement time information from the position information database 33 to create a movement path of the object 50 and displays it on the display (step 106). At this time, the distance may also be displayed.

[Second Embodiment]
FIG. 4 is a block diagram of an object movement path tracking system according to the second embodiment of the present invention.

  In this embodiment, in addition to the camera 21 that can detect normal visible light, a camera 22 that can detect infrared rays is provided. This camera has a field of view of the entire room 70. Fixed markers 41, 42, and 43 for tracking the trajectory of the moving object 50 are attached to the floor, wall, and shelf of the room 70. A marker 62 is attached to the moving object 50. The computer system 30 is used for the calculation of the position of the space, the storage of the data, the creation of the movement route, and the display process as in the first embodiment. Of course, the computer system 30 may be arranged outside the room 70. It may be connected to the cameras 21 and 22 wirelessly or by a wire link, may be a stand-alone type, or may be connected to a computer network in order to distribute data storage and processing and perform high-speed data transfer.

  In this system, infrared tags are used as the markers 41 to 43 and 62. As an example, an infrared tag proposed in Japanese Patent Laid-Open No. 2002-340965 is used this time. When the tag receives the information including the light emission command command from the computer system 30, the tag emits light when the identification information included in the light emission command command is the identification information assigned to itself, and the cycle is different for each tag. Emits and transmits a typical infrared signal. This light is not visible to the human eye but is easily visible to the infrared camera 22. When the infrared camera 22 captures this signal, the object 50 can be identified by comparing the signal pattern with the transmission pattern of the object registered in the computer system 30 in advance. Since the infrared tag transmits a signal itself, it can be used not only for providing position information but also as a remote sensor (for example, a thermometer or motion detector) for providing position-dependent data.

  FIG. 5 is a block diagram of processing performed by the computer 32 and is basically the same as the block diagram of FIG. 2, but in this embodiment, an image of the infrared camera 22 is input to the data storage determination unit 32. The data storage determination unit 32 also stores the instantaneous image taken by the infrared camera 22 when it is determined that the data is stored.

  In the above embodiment, the processing of FIGS. 2 and 5 is performed by a program. However, it can be performed by an apparatus having the configuration of FIGS.

It is a figure which shows the structure of the object movement path | route tracking system of the 1st Embodiment of this invention. It is a block diagram which shows the structure of the computer system 30 of 1st Embodiment. It is a flowchart of the process which detects and displays the movement locus | trajectory of the object with a marker. It is a figure which shows the structure of the object movement path | route tracking system of the 2nd Embodiment of this invention. It is a block diagram which shows the structure of the computer system 30 of 2nd Embodiment.

Explanation of symbols

11, 12, 13 Two-dimensional fixed marker 21, 22 Camera 30 Computer system 31 Two-dimensional marker distance calculation unit 32 Data storage determination unit 33 Two-dimensional position information database 34 Object trajectory information display unit 41, 42, 43 Infrared tag 50 Movement Object 61, 62 Marker 70 Indoor 101-106 steps

Claims (4)

For each object that tracks the movement path, a marker for identifying the object and specifying its position is attached.
A plurality of fixed markers are arranged in the space where the object moves,
Take a picture of the space with a camera,
Measure the distance between the object and each fixed marker on the image, store the identification information of the fixed marker corresponding to the smallest of the measured distances, and the measurement time in the memory,
An object movement path tracking method for creating movement path information of the object from the stored fixed marker identification information and measurement time.   The object movement path tracking method according to claim 1, wherein the identification information of the fixed marker and the measurement time are stored in a memory only when the minimum distance is equal to or smaller than a predetermined size. A plurality of fixed markers arranged in a space in which an object with markers for identifying and locating moves; and
A camera for photographing the space;
Memory,
Means for measuring a distance between the object on the image and each of the fixed markers, storing fixed marker identification information corresponding to a minimum distance among the measured distances, and a measurement time in the memory;
An object movement path tracking device having means for creating movement path information of the object from identification information of a fixed marker stored in the memory and information of a measurement time.   The means for measuring the distance and storing the identification information of the fixed marker and the measurement time in the memory can store the identification information of the fixed marker and the measurement time in the memory only when the minimum distance is a predetermined size or less. The object movement path tracking device according to claim 3, wherein the object movement path tracking device is stored.

Images