JP2000207665A - Falling detecting device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To accurately detect not only a falling state but also falling action itself by performing differential processing to a fetched image and detecting the falling action of a human body on the basis of an obtained differential area. SOLUTION: A differential means extracts the differential area from a newly picked-up image (b) and a reference image (a) picked up before (e). Similarly, each time a new input image (c) is picked up, the differential area from the input image (b) picked up before is extracted. Next, a differential area extracting means binarizes the differential image for each new input image and calculates the total sum of differential areas of respective differential images. A judging means detects the falling of the human body while utilizing the differential area at every time calculated by an image processing means. Namely, a threshold value in the case of considerably changing the differential area in a short time is set. When the differential area exceeds the threshold value, falling is judged to have happened.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a fall detecting device capable of automatically detecting that a person has fallen.

[0002]

2. Description of the Related Art In order to automatically detect an abnormal condition occurring in a patient requiring care, such as an elderly person, a device using image processing technology has been devised. These apparatuses acquire three-dimensional information in a room by image processing, and determine an abnormal state of a patient based on the information.

[0003] In this type of device, there is a device for detecting a falling motion of a human body. In this method, three-dimensional information indicating a position where a patient is present is calculated by making full use of the principle of triangulation from an image captured by a camera, and the state in which the patient is lying on the floor surface is calculated. When the state continues for a predetermined time after the detection, it is determined that the patient has fallen, and the fact is notified.

[0004]

However, in the fall detecting device having the above-mentioned structure, the light emitting means for projecting the patient's room to obtain three-dimensional information and the projected image are displayed. Since a camera or the like for imaging is required, the apparatus itself becomes large-scale, and there is a problem that a patient in a living room where the apparatus is installed due to the enlargement of the apparatus itself may give a feeling of oppression. Was. Further, the conventional fall detecting device detects that the patient is in a fall state, and has a problem that the fall operation itself cannot be detected.

SUMMARY OF THE INVENTION The present invention has been made in view of the above-mentioned problems, and has as its object to provide a low-cost method capable of accurately detecting not only a falling state but also a falling operation itself. An object of the present invention is to provide a fall detection device.

[0006]

According to the first aspect of the present invention,
A camera, image processing means for capturing a video signal output by the camera, and performing a difference process on the captured image;
Determining means for detecting a falling motion of the human body based on the area of the difference region obtained by the difference processing.

According to a second aspect of the present invention, in the fall detecting device according to the first aspect, the determining means stores a threshold value for determining whether or not a fall operation has occurred, and changes the area of the difference area within a predetermined time. Is determined to be that the human body has fallen when the threshold value is exceeded.

[0008]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a fall detecting apparatus according to an embodiment of the present invention will be described in detail with reference to FIGS. FIG. 1 is a schematic configuration diagram of a fall detection device. FIG.
FIG. 2 is a schematic configuration diagram of an image processing unit. FIGS. 3A to 3C are schematic diagrams of images captured by a camera. FIGS. 3A to 3C are input images captured at predetermined time intervals. FIGS. 3D to 3E illustrate differences between input images. It is a difference image extracted by performing. FIG. 4 is a graph showing the relationship between the time when the human body falls over and the area of the difference region. FIG. 5 is a graph showing the relationship between the time when the human body takes a seating motion and the area of the difference region. FIG. 6 is a schematic configuration diagram of another image processing means. FIG. 7 is a graph showing the relationship between the time when the human body falls down and the change in the area of the difference region. FIG. 8 is a graph showing the relationship between the time when the human body takes a seating motion and the change in the area of the difference region.

[First Embodiment] The fall detecting device according to the present embodiment includes a camera 1, an image processing means 20, and a judging means 30, as shown in FIG. In the present embodiment, the camera 1 for photographing the living room is installed on the ceiling of the living room of the resident 10 and images the resident 10 from above. Then, the camera 1 outputs a video signal of the resident 10 and outputs the video signal.
0 is to capture the video.

The image processing means 20, as shown in FIG.
An AD converter 21 for converting a video signal into a digital signal;
An image memory 22 for storing the converted video signal, a difference means 23 for calculating a difference between a newly captured input image and an input image previously captured, and a difference image for storing the obtained difference It comprises a memory 24 and a difference region area extracting means 25 for calculating the area of the difference region. Further, the image processing means 20 of the present embodiment includes an address control means 26, and is capable of controlling a memory address of a capture destination so that a plurality of image signals can be stored in time series.

The operation of the fall detecting device having the above-described configuration will be described with reference to FIG. The difference unit 23 extracts a difference area from a newly captured image (see FIG. 3B) and an image captured before that (see FIG. 3A) (see FIG. 3D). ). Similarly, a new input image (FIG. 3)
Each time ((c)) is imaged, a difference area from the input image (see FIG. 3 (b)) captured before that is extracted (see FIG. 3 (e)). These extracted difference images (see FIGS. 3D to 3E) are written to the difference image memory 24. Next, in the difference area area extraction means 25, every time a new input image is present, the difference image is subjected to a binarization process, and the sum of the areas of the difference areas of each difference image is calculated.

The judging means 30 detects the fall of the human body using the area of the area of the difference image at each time calculated by the image processing means 20. In other words, the human body is detected by paying attention to the fact that the motion of the human body imaged by the camera 1 changes greatly in a short time when the vehicle falls.
First, a threshold value (Th) is set in advance as a criterion for determining how much the area of the difference region changes to determine a fall. In the present embodiment, the threshold (T
h) is the time from the start of the fall to the end of the fall (ta), the area difference between the standing state and the falling state obtained by measuring in advance (S0), and the time interval of image capture (tc). At this time, it is set so that Th <S0 × Tc / Ta. The threshold value (T
According to h), when the area of the difference region exceeds the threshold value (Th), it indicates that a large area change has occurred in a short time.

As shown in FIG. 4, the judging means 30 judges that the resident 10 has fallen when the area area (S) of the difference image exceeds a set threshold value (Th). On the other hand, as shown in FIG. 5, when the human body performs a sitting motion, since the motion of the person per unit time is smaller than that of the fall, the person does not exceed the threshold value (Th) set earlier and is determined to be a fall. Not done. Therefore, only the falling motion of the human body can be accurately detected.

In the present embodiment, as described above, the area of the difference region between the image captured before the human body falls and the image captured after the human body falls significantly changes in a short time. In view of this, it is possible to accurately detect the fall of the human body from the change in the area of the difference area between the newly input image and the image input earlier. Thus, it is possible to automatically detect that the resident 10 in need of nursing has fallen, and to take prompt action.

Note that, as shown in FIG.
, A storage area for storing an image of the living room when the occupant 10 is not present as a reference image is provided, and the difference means 23 performs difference processing between the newly captured input image and the previously captured reference image. May be performed together. The result obtained by the difference processing with the reference image is written in the difference image memory 27. Then, the difference image written in the difference image memory 27 is subjected to binarization processing by the difference area area extraction means 28 to calculate a feature amount such as each area of the area of the difference image. The determination means 30 performs the above-described processing, and compares whether the area (S) of the difference area between the input images does not exceed the threshold value (Th). Here, when the area (S) exceeds the threshold value (Th), the area of the corresponding background difference region becomes equal to the predetermined threshold value (Th).
It is checked whether or not b) is exceeded, and if it is, it is determined that the resident 10 has fallen. Here, the predetermined threshold (Thb) is set to be larger than the area when the person is standing and smaller than the area when the person is lying down. Therefore, even if the occupant 10 performs a motion other than a fall and performs a quick motion in which the change in the area of the difference region becomes large in a short time, it is possible to reduce erroneous determination that a fall has occurred even if the resident 10 performs a quick motion. is there.

[Second Embodiment] The fall detecting device according to the present embodiment has the same configuration as that shown in FIGS. 1 and 2, and a detailed description thereof will be omitted. This will be described below.

As shown in FIG. 7, the judging means 30 determines whether the change (Sd) in the area of the region of the difference image is equal to a predetermined threshold (Td).
hp), and after a time (Ta), the change (Sd) in the area of the difference image becomes smaller than a preset threshold (Thm), and no change is observed in the change (Sd) in the area over a time Tb or more. Sometimes it is determined that a fall has occurred. On the other hand, when the occupant 10 performs the sitting operation, as shown in FIG. 8, the change (Sd) in the region area gradually decreases over a longer period of time as compared with the fall, so that the time (Ta ) After that, it does not become smaller than the threshold value (Thm), and does not satisfy the above-mentioned condition for judging the fall, so that it is not judged as a fall.

In the present embodiment, as in the first embodiment, in the case of the image taken before the human body falls and the image taken after the human body falls, the image In view of the large change in the difference region, it is possible to accurately detect the fall of the human body from the change in the area of the difference region between the newly input image and the image input earlier.

[0019]

As described above, according to the first aspect of the present invention, a camera, image processing means for capturing a video signal output by the camera, and performing difference processing on the captured image, Since the determination means detects the overturning motion of the human body based on the area of the difference area obtained by the processing, the configuration is simplified because no light projection means is required other than a camera for photographing the living room. At the same time, since the fall motion of the human body can be detected only by a simple process of calculating the area of the difference region that causes a characteristic change when falling,
It is possible to provide an inexpensive fall detection device that can accurately detect not only a fall state but also a fall operation itself with high accuracy.

According to the second aspect of the present invention, the first aspect is provided.
In the fall detection device described in the above, in the determination means,
A threshold value for determining whether the operation is a fall operation is stored, and when the area change of the difference region exceeds the threshold value within a predetermined time, it is determined that the human body has fallen. Since it becomes possible to accurately detect a large change in the area of the difference region in a short time, which is a considerable decrease,
This has the effect that it is possible to clearly distinguish between a similar motion of the human body and a falling motion when falling.

[Brief description of the drawings]

FIG. 1 is a schematic configuration diagram of a fall detection device.

FIG. 2 is a schematic configuration diagram of an image processing unit.

FIG. 3 is a schematic diagram of an image captured by a camera;
(A) to (c) are input images captured at predetermined time intervals, and (d) to (e) are difference images extracted by performing difference processing between the input images.

FIG. 4 is a graph showing a relationship between a time when a human body falls down and an area of a difference region.

FIG. 5 is a graph showing a relationship between a time when a human body takes a seating motion and an area of a difference region.

FIG. 6 is a schematic configuration diagram of another image processing means.

FIG. 7 is a graph showing the relationship between the time when the human body falls down and the change in the area of the difference region.

FIG. 8 is a graph showing a relationship between a time when a human body takes a seating motion and a change in the area of a difference region.

[Explanation of symbols]

 1 camera 20 image processing means 30 judgment means

Continuing from the front page (72) Inventor Tadahiro Arakawa 1048 Kazuma Kadoma, Osaka Prefecture F-term in Matsushita Electric Works, Ltd. 5C087 DD03 DD24 EE08 EE18 FF01 FF04 GG02 GG03 GG08 GG12 GG24 GG30 GG31 GG32 GG37

Claims (2)

[Claims] 1. A camera, image processing means for capturing a video signal output by the camera, and performing difference processing on the captured image, and a human body overturning operation based on the area of a difference area obtained by the difference processing. And a determining means for detecting the falling. 2. A method according to claim 1, wherein the determining means stores a threshold value for determining whether or not the human body has fallen, and determines that the human body has fallen when a change in the area of the difference region within a predetermined time exceeds the threshold value. The fall detecting device according to claim 1, wherein