JP2001326903A - Video recording judging device and method, and edge extracting apparatus - Google Patents

Abstract

PROBLEM TO BE SOLVED: To solve a drawback that a method for recording all image information photographed with a monitoring camera requires a huge capacity on a storage disk and causes the problem with respect to cost and management. SOLUTION: The device to record image information on a videotape while acquiring image information from a photographic means to film a monitoring range serially is provided with a frame difference detecting means to calculate a frame difference Df which is the difference between the image information of a reference frame Rf and the image information of a current frame Cf among photographing results by a photographing means, an edge detection means to detect the edge component of the frame difference, and a state judging means to stop the video recording of image information or to switch to the video recording of low frame rate when there are few edge components or few variations of edge components.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a technique for judging the getting on and off of a person in a room such as an elevator where people enter and exit based on image information input from a surveillance camera.

[0002]

BACKGROUND OF THE INVENTION In order to manage security in a building or to obtain information in an emergency, a surveillance camera is installed in a room where a user such as an elevator gets on and off, and the situation in the room can be monitored in real time. In addition, it can be grasped based on the recording information.

[0003] In a conventional monitoring system,
All of the image information captured by the surveillance camera was stored on the disk.

[0004]

However, in the conventional apparatus for storing all the image information captured by the surveillance camera, a very large storage disk is required. Moreover, the stored image data requires a certain storage period due to its importance. For example,
In some cases, the intrusion into the building is detected after a lapse of a considerable time, and in this case, it is necessary to refer to past image information.

[0005] In some cases, a plurality of elevators are installed in a building, and a surveillance camera is installed in other places in a space where security such as a building is required. Therefore, in order to store the image information captured by all of these surveillance cameras on the disk over the entire time, the total capacity of the disk becomes enormous,
There are both cost and management issues.

SUMMARY OF THE INVENTION In view of the above problems, the present invention has been made in view of the above circumstances and has made it possible to reduce the capacity required for recording without losing the preservation of information necessary for monitoring. The purpose is to provide an extraction technique.

[0007]

According to an aspect of the present invention, there is provided an apparatus for acquiring image information from photographing means for continuously photographing an area within a monitoring range and recording the image information in a storage device. A frame difference detection unit that calculates a frame difference that is a difference between image information between a reference frame serving as a reference and a current frame that is sequentially updated, and detects an edge component of the frame difference. Stopping the recording of the image information to the storage device or when it is determined that the situation in the current frame has not substantially changed from the situation of the reference frame by the edge detection means and the quantitative evaluation of the edge component. State determination means for switching the recording to a low frame rate.

[0008] The invention described in claim 2 is the first invention.
The recording determination apparatus according to claim 1, wherein when the state determination unit determines that the edge component is small based on a first determination criterion, the recording of the image information to the storage device is stopped or the recording is switched to a low frame rate. Edge component determining means for performing the following.

[0009] The invention described in claim 3 is the first invention.
3. The recording determination device according to claim 2, wherein when the state determination unit determines that the temporal variation of the edge component is small based on a second determination criterion, the state determination unit determines whether the image information is to be recorded in the storage device. Edge fluctuation determining means for stopping or switching to a low frame rate for recording.

[0010] The invention described in claim 4 is the first invention.
4. The recording determination device according to claim 3, wherein the edge detection unit is a candidate region selection unit that selects the frame difference into a candidate region for edge detection and a non-candidate region according to a predetermined region selection criterion. True edge detecting means for detecting a true edge component from the candidate area according to a predetermined edge classification criterion, and quantitatively evaluating the true edge component.

[0011] The invention described in claim 5 is the same as in claim 4.
Wherein the true edge detection means,
Differential filtering processing means for obtaining the differential value of the image information of the frame difference, local maximum value calculating means for obtaining a local maximum value of the differential value of the non-candidate area, and differential obtaining the average value of the local maximum value of the non-candidate area It is characterized by comprising an average value calculating means and a true edge determining means for determining that a true edge component exists in the candidate area when the image information of the candidate area exceeds the differential average value.

The invention according to claim 6 is the same as the invention according to claim 3.
Wherein the edge variation determining means includes: a set extracting means for extracting a common set and a merged set of an edge component of a past frame difference, an edge component of a current frame difference, and a common set for the merged set. Edge fixing degree calculating means for calculating the ratio of the set as the degree of fixing of the edge component; and a fixing degree dependent for judging that the fluctuation of the edge component is small when consecutive frames in which the fixing degree of the edge component exceeds a predetermined threshold value. Determining means.

According to a seventh aspect of the present invention, there is provided a method for acquiring image information from a photographing means for continuously photographing the inside of a monitoring range and causing a storage device to record the image information. A frame difference detecting step of calculating a frame difference which is a difference between image information of a reference frame serving as a reference and a sequentially updated current frame; an edge detecting step of detecting an edge component of the frame difference; When it is determined by the evaluation that the situation in the current frame has not substantially changed from the situation of the reference frame, the recording of image information to the storage device is stopped or the recording is switched to a low frame rate. And a state determining step.

According to a further aspect of the present invention, there is provided an apparatus for extracting an edge from an image, comprising: a differential filtering processing means for obtaining a differential value of image information in a predetermined image range; and a predetermined area selection criterion. A candidate area selecting means for selecting the image range into a candidate area and a non-candidate area for edge detection; a local maximum value calculating means for obtaining a local maximum value of a differential value of the non-candidate area; A differential average value calculating unit that calculates an average value of local maximum values; and an edge determining unit that determines that the edge component exists in the candidate region when image information of the candidate region exceeds the differential average value. And

[0015]

Embodiments of the present invention will be described below with reference to the drawings. First, the overall schematic configuration of the recording determination device will be described. As shown in FIG. 1, a surveillance camera 2 as a photographing means is installed in a surveillance range 1 of an elevator or the like.
Recording is performed by being stored on the disk 6 in the recording determination device 3 via the interface 7 (I / F). The recording determination device 3 includes an MPU 4, a memory 5, and the like, reads image information stored in the disk 6 into the memory 5 as appropriate, performs image analysis, and performs recording control based on the analysis result. .

Next, terms in the following description will be defined. The reference frame is image information of an empty state taken by the surveillance camera 2, that is, a user (passenger)
Is image information of the monitoring range 1 in a state where no image is captured, and is information previously held in the disk 6 inside the recording determination device 3. However, since the steady state changes in accordance with a change in the environment, as will be described later, in this case, the reference frame is updated as needed.
Generally, the reference frame is updated when the recording determination device determines that the image is not recorded.

The current frame is the latest information of the image information captured by the surveillance camera 2, and is sequentially updated and stored on the disk 6. Note that the past image information of a plurality of frames is a fixed degree of an edge component (the definition will be described later).
Is stored for the calculation of.

The frame difference is difference data between the image information of the reference frame and the image information of the current frame, and is information on the entire frame obtained by subtracting the luminance value of each pixel of the current frame from the luminance value of each pixel of the reference frame.

FIG. 2 shows the overall flow of the recording state control. First, a detection area setting process (step s11) is performed as a stage prior to the recording state control.

The detection area setting process is a process of setting an area in the image information for which a recording determination is made. For example, in the case of a door with a window (for an apartment, etc.) or an elevator with an LCD monitor, movement of a person outside the window or movement of the LCD monitor is not detected as an edge component in the frame difference. As described above, this is a process of excluding the area of the window or the monitor from the detection target. In addition, edge parts that appear when the inside of the elevator is empty, such as corners in the elevator, are always excluded from the detection target. The region not to be detected is set in advance as a mask region.

Next, recording determination processing is performed (step s1).
2). The recording determination process is performed for each current frame,
This is a process of setting the result of the recording determination process to a recording flag. Then, according to the value of the recording flag, control is performed to continue or stop recording. (Step s13).

The recording determination process (step 12) will be described with reference to FIG. The recording determination process is performed in advance on the disk 6
Are processed as input data, the reference frame Rf, which is the empty image information held by the monitoring camera 2, and the current frame Cf, which is photographed by the monitoring camera 2 and sequentially updated.

First, in step s21, an edge detection process is performed for each frame using the reference frame Rf and the current frame Cf as input data, and then, a state determination process (step s22) based on past accumulated edge information. : Details will be described later), and then a recording flag is output.

Next, the above-described edge detection processing flow will be described with reference to FIG. In the edge detection processing, first, in step s31, the reference frame Rf
And the frame difference Df of the current frame Cf.

Next, a differential filtering process is performed (step s32). This differential filtering processing is a filtering designed to suppress the low frequency range (compared with general differential type differential filtering) and to have a frequency characteristic in which a high frequency range is raised, and includes three steps as shown in FIG. Processing.

Here, the general difference-type differentiation process is a process in which a difference between the brightness value of each pixel and the brightness value of a coordinate point separated by a certain pixel is set as a differentiation value. Differential filtering in the form means performing filtering such that a steep edge component of a frame difference is more clearly extracted.

The processing flow of the differential filtering shown in FIG. 5 will be described. First, in step s41, a differential value FV in the vertical direction is obtained. The differential value FV is calculated by convolving a matrix RESP expressed by the following equation 1 with each pixel component of the frame difference Df.

[0028]

(Equation 1)

The matrix RESP indicates a coefficient to be given to the luminance of each coordinate of the frame difference Df. For example, at an arbitrary coordinate (i, j) of the frame difference Df, a matrix is added to the luminance of the coordinate (i, j). The central component of R, ie, 2 rows 3
The components of the column are multiplied as coefficients. Then, 14 points (points surrounded by 3 rows and 5 columns) around the coordinates (i, j) are multiplied by the corresponding matrix RESP components as coefficients. 15 obtained by multiplying this coefficient
Is the differential value FV of the coordinates (i, j).

Similarly, in step s42, a horizontal differential value FH is obtained. The differential value FH is calculated by convolving each pixel component of the frame difference Df with the transposed matrix RESP (T) of the matrix R, and is given by the following equation (2).

[0031]

(Equation 2)

Through the above processing, the differential values FV and FH of the frame difference Df are calculated for each pixel (for each coordinate).
The maximum value of the differential values FV and FH is obtained for each pixel.
This maximum value is set as the pixel differential maximum value D1 (step s4
3).

As described above, since the pixel differential maximum value D1 is obtained for each pixel of the frame difference Df, even when an element having a large luminance change in either the vertical direction or the horizontal direction is included. By using the differential value on the maximum side, it is possible to react sensitively to a change in luminance. The numerical values of the components of the matrix R are shown in the equation (1) as an example, and the numerical values of the components are not limited. Any filtering may be used as long as it is designed to have a frequency characteristic that is higher than the frequency characteristic. As a result, the differential value of a slightly gradual change such as the primary reflection of sunlight is suppressed, and it is easy to distinguish the change from a change due to getting on and off a person.

After the end of the differential filtering processing, in the edge detection processing flow (FIG. 4), a local maximum value D2 which is the maximum value of the pixel differential maximum value D1 for each block is obtained for the area excluding the mask (FIG. 4). Step s33).
A block is a frame difference Df of YB × XB (Y
B and XB are each an integer of 2 or more) and are divided into a matrix arrangement of a plurality of pixels. FIG. 6 shows an example in which the frame difference Df is divided into 5 × 5 blocks. . Further, “excluding the mask” means that pixels specified as non-detection targets in the detection area setting process shown in step s11 of the above-described overall flow are excluded.

Based on such conditions, a local maximum value D2 of the pixel differential maximum value D1 is obtained for each block, and the calculated local maximum value is set in D2. A variable i in the figure is a number assigned to each divided block, and indicates that a loop process is performed on each block corresponding to a number from 1 to YB × XB.

By the above processing, the local maximum value D2 for each block is obtained. If the local maximum value D2 is large to some extent, it is considered that the possibility that the block contains an edge component is large. Therefore, the next edge detection processing is performed only on the blocks in which the local maximum value D2 is larger than the candidate area setting value T1.

The candidate area setting value T1 is a value set in advance, and is used to judge how large the local maximum value D2 is to be subjected to edge detection. An optimal value shall be determined appropriately from past data and experience values.

In step s34, a differential average value T2 is obtained as an index value for detecting a true edge component. The candidate area setting value T1 is a predetermined value, is a fixed value for determining whether or not to detect an edge component, and extracts a block (candidate area) that is a candidate for edge component detection. It's a role. On the contrary,
The differential average value T2 is a value for determining a pixel actually detected as an edge in a block that is a candidate for edge component detection, and is calculated for each current frame Cf.

Here, in the example shown in FIG. 6, among the difference frames Df divided into 5 × 5, the hatched blocks have the local maximum value D2 of the pixel differential maximum value D1 and the candidate area setting value T1. This indicates a larger area, that is, a block that is a candidate for edge component detection.

The differential average value T2 is: <Condition 1> Local maximum value D2 (i) ≦ candidate region setting value T
It is calculated as the average value of the local maximum value D2 (i) of the block satisfying 1 :. That is, in an area where the local maximum value D2 is smaller than the candidate area setting value T1 (a non-candidate area determined not to include an edge component), the average value of the local maximum value D2 is used as an index value for detecting a true edge component. It is.

As described above, since the index value for true edge component detection is the average of the maximum differential values of the non-candidate areas,
It is possible to reduce the possibility of detecting an edge component for a region included in a non-candidate region. Further, since the index value is not too high and the detection of the edge component is not missed, it can be said that the index is an optimal index.

After calculating the differential average value T2 in step s34, a loop process of edge component detection is performed on all blocks satisfying <condition 2> local maximum value D2 ≧ candidate region setting value T1 :. At this time, the number of edges CN of the current edge component is initialized (0).

First, in step s35, a true edge component determination process is performed. The determination of the edge component is based on the pixel differential maximum value D1 and the differential average value T
2, and a pixel exceeding the differential average value T2 is determined as a true edge component. When it is determined that the pixel is a true edge component, 1 is set to the edge flag EG of the corresponding pixel, and 0 is set to the edge flag EG of the pixel lower than the differential average value T2. As described above, the edge flag EG is represented by a two-dimensional array having the same size as a frame (a difference frame or the like) in which an edge component is 1 and a non-edge component is 0.

FIG. 7 shows an example shown in FIG. 6, in a block which is a candidate area for edge component detection.
FIG. 3 is a diagram illustrating points (pixels) detected as true edge components.

Whether each pixel is an edge component or not is determined, and in step s36, the number of edges CN of the current edge component is added. That is, step s35 is performed on each block that is a candidate area.
The addition process is performed using the number of true edge components detected as an edge component in the number of edges CN to calculate the number of edges CN of the entire frame.

When the processing for all the blocks satisfying the above-mentioned <condition 2> is completed, the edge flags EG extracted as a two-dimensional array are stored in the edge stock ES. That is, the edge stock ES stores the edge flag EG, which is a two-dimensional array, over a plurality of past frames.
It becomes a dimensional array.

After the edge detection processing is completed, as shown in the image determination processing flow (FIG. 3), the current (current frame)
And state determination processing based on past edge information (step s
22), and outputs a recording flag which is a status of determining whether or not to perform recording.

The state determination process outputs a recording flag based on two conditions as shown in FIG. First, in step s51, a comparison determination process is performed between the number of edges CN detected in the edge detection flow and a fixed threshold. When the number of edges CN is smaller than the fixed threshold, that is, when the edge component of the frame difference is small, there is little difference from the reference frame in the image information of the current frame, and substantially no person such as a person is included in the monitoring target range. It is determined that it is possible to stop recording because there is no surveillance object, and the recording flag is set to OFF (0) (step s53). At this time, in order to make the determination more strictly, the number of edges C over the past several frames is determined.
The condition may be that N is below a fixed threshold.

If the number of edges CN is larger than the fixed threshold, it is next determined in step s52 whether or not the temporal variation of the edge component of the frame difference is small. And set the recording flag to OFF (0) (step s5).
4). In the determination of the temporal variation, a state determination process based on the degree of edge fixation as described below is performed.

The state determination processing based on the degree of edge fixation will be described with reference to FIGS. 9 and 10. In the edge detection processing described above, the reference frame R assumed to be empty
The processing is performed based on the difference between f and the current frame Cf. Therefore, when a frame that is not empty becomes the initial reference due to a restart or the like, when the fluorescent lamp goes out in the energy saving mode, when a poster is put in the elevator, or when an object is left unattended, recording is stopped. Can be performed, more accurate recording control can be performed. If recording is performed continuously for such a reason, it is desirable to end recording and update the reference frame Rf, and perform a state determination process as shown in FIG.

First, a past edge flag Ep and an edge flag Ec of the current frame Cf are obtained. The edge flags Ep and Ec both mean the edge flag EG obtained in the above-described edge detection flow, and the edge flags Ep and Ec can be obtained from the edge stock ES.

Then, in step s61, the number Ea of common edge flags included in the common set EpｃEc of the edge flag Ep and the edge flag Ec is calculated. That is, the number Ea of common edge flags is the number of pixels detected as edges in both the past and current frames.

Next, in step s62, the number Eo of merged edge flags included in the merged set EpＥEc of the edge flag Ep and the edge flag Ec is calculated. That is, the number Eo of merged edge flags is the number of pixels detected as edges in the past or current frame.

In step s63, the ratio of the number Ea of common edge flags to the number Eo of all edge flags is stored in the edge fixing degree RB. This state is schematically shown in FIG.

Then, it is determined whether or not the edge fixing degree RB has exceeded the fixed degree set value in all past plural frames (for example, the past N frames) (step s64). , Edges hardly fluctuate,
That is, it is in a steady state, but for the above-mentioned reason (the fluorescent light is turned off, the poster is pasted, etc.), it is determined that the recording state is in progress because a large number of edge components continue to be detected. 1 for the reference update flag (to be updated)
Is set (step s65).

Further, when the reference update flag is set to 1 over a plurality of frames (same as the past N frames or may be set separately) (step s6)
6) Since it means that the steady state continues and the recording is continuous due to erroneous detection, it is determined that the recording can be stopped, and the recording flag is set to OFF (0) (step s67 = Step s53 in FIG. 8).

In step s64, if the edge fixed degree RB does not exceed the fixed degree set value in at least one of the past N frames, the edge component is expected to fluctuate, so that recording is continued. And set the recording flag to ON (1) (step s).
68 = step s54 in FIG. 8).

In step s66, if the reference frame update flag is set to 1 (to be updated), but the number of past consecutive frames for which the update flag is set to 1 is less than N, Determines that recording should be continued, and sets the recording flag to ON (1) (step s68 = step s54 in FIG. 8).

By performing the above processing, in the state determination processing shown in FIG. 8, ON (1) is set as the flag to be recorded in the recording determination flag (step s54), or the recording is stopped. OFF (0) is set as a flag to be stopped (step s53).

Then, as shown in the overall flowchart of FIG. 2, recording control is performed based on the recording flag output in the recording determination processing (step s13). In other words, the surveillance camera is controlled according to the set value of the recording flag, and when the recording flag is set to OFF (0), that is, when there is no user getting on and off, the recording is not performed. The capacity can be greatly reduced.

The above-described routine is repeatedly executed periodically. When the user gets on and off again, the recording flag is set to 1 in step s68. The recording is resumed from.

When the user does not get on and off, the recording is performed at a lower frame rate than when the user gets on and off (the amount of edge component and the amount of fluctuation are large), thereby reducing the capacity of the disk 6. May be performed.

[0063]

As described above, according to the first and seventh aspects of the present invention, the situation in the current frame is substantially changed from the situation in the reference frame by the quantitative evaluation of the edge component in the difference frame. When it is determined that there is no change, the recording is stopped or the frame rate is switched to a low frame rate, so that the capacity of the storage means for storing the image information can be significantly reduced, which is effective in terms of cost and management. Configuration.

Also, when the fluctuation of the edge component is small, that is, when the steady state is changed, the recording is stopped, so that the configuration is very effective in reducing the storage capacity.
Then, when the above situation does not occur, the recording is continued as usual, so that the preservation of information necessary for monitoring is not impaired.

According to a second aspect of the present invention, when the state determination means determines that the edge component is small based on the first determination criterion, the recording of the image information to the storage device is stopped or the recording of the image information is stopped. Since an edge component determining means for switching to the frame rate is included, a substantial change in the image of the current frame from the reference frame is determined by the amount of the edge component of the difference frame (claim 2) and the monitoring target ( The recording can be stopped or the frame rate can be switched according to the presence or absence of a person.

According to a third aspect of the present invention, when the state determination means determines that the temporal variation of the edge component is small according to the second determination criterion, the recording of the image information to the storage device is stopped. Alternatively, an edge change determination unit that switches the recording to a low frame rate is included, so that the recording can be stopped or the frame rate can be switched in accordance with the movement of a monitoring target (a person or the like) within the monitoring range.

According to a fourth aspect of the present invention, the edge detecting means comprises: a candidate area selecting means for selecting the frame difference into a candidate area for edge detection and a non-candidate area according to a predetermined area selecting criterion; A true edge detection means for detecting a true edge component from the candidate area according to the edge classification criteria, and performing a quantitative evaluation on the true edge component. And the processing efficiency is improved. Further, the processing speed is improved as compared with the case where edge components are detected for all image information (for each pixel).

According to a fifth aspect of the present invention, the true edge detecting means obtains a differential filtering processing means for obtaining a differential value of image information of a frame difference, and obtains a local maximum value of a differential value of a non-candidate area. A local maximum value calculating means, a differential average value calculating means for calculating an average value of a local maximum value of the non-candidate area, and when image information of the candidate area exceeds the differential average value,
Since a true edge determination unit that determines that a true edge component exists in the candidate area is provided, it is possible to detect an edge component with high accuracy. In particular, since the index value for detecting a true edge component is used as the differential average value of the non-candidate area, the index value is too high, causing omission of detection of the edge component, or the index value is too low, resulting in an erroneous edge component. The problem that detection occurs can be prevented.

According to a sixth aspect of the present invention, the edge variation determining means includes a set extracting means for extracting a common set and a merged set of the edge components of the past frame difference and the edge components of the current frame difference. Edge fixing degree calculating means for calculating the ratio of the common set to the merged set as the fixed degree of the edge component; and determining that the fluctuation of the edge component is small when consecutive frames in which the fixed degree of the edge component exceeds a predetermined threshold value. Therefore, it is possible to avoid the problem of making an appropriate determination even for a change in the steady state and continuing to record the image in the monitoring range in the empty state. As a result, the storage capacity can be reduced.

The invention according to claim 8 is an apparatus that can be directly used for implementing the method according to claim 7.

[Brief description of the drawings]

FIG. 1 is a schematic configuration diagram of a recording determination device according to the present invention.

FIG. 2 is a diagram showing an overall flow of a recording state control of the recording determination device according to the present invention.

FIG. 3 is a diagram showing a recording determination processing flow.

FIG. 4 is a diagram showing an edge detection processing flow.

FIG. 5 is a diagram illustrating a differential filtering processing flow.

FIG. 6 is a diagram showing a candidate area for edge detection in a block frame.

FIG. 7 is a diagram illustrating a true edge component detected in a candidate area.

FIG. 8 is a diagram showing a state determination processing flow.

FIG. 9 is a diagram showing a state determination processing flow based on the degree of edge fixation.

FIG. 10 is a diagram schematically illustrating a state determination process based on an edge fixing degree.

[Explanation of symbols]

 Cf Current frame D1 Pixel differential maximum value D2 Local maximum value Df Frame difference EG Edge flag ES Edgestock FV Vertical differential value (of frame difference) HV Horizontal differential value of (frame difference) Rf Reference frame T2 Differential average value

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) H04N 7/18 H04N 5/91 K F term (Reference) 5B057 BA02 CA12 CA16 DA20 DC16 DC32 5C053 FA11 FA23 GA20 GB17 KA03 KA08 KA11 KA22 KA24 5C054 CC00 FC01 FC14 FC16 FF03 GA01 GA04 GD05 GD09 HA18 HA19 5L096 BA02 CA02 GA02 GA08 HA02

Claims (8)

[Claims] 1. A device for acquiring image information from a photographing means for continuously photographing within a monitoring range and causing a storage device to perform recording, wherein a reference frame serving as a reference is sequentially included in a photographing result by the photographing means. A frame difference detection unit that calculates a frame difference that is a difference between the image information and the current frame to be updated; an edge detection unit that detects an edge component of the frame difference; State determining means for stopping the recording of the image information in the storage device or switching the recording to a low frame rate when it is determined that the situation in the reference frame has not substantially changed from the situation of the reference frame. And a recording determination device. 2. The recording judging device according to claim 1, wherein the state judging unit judges that the edge component is small based on a first judgment criterion. An edge component determining means for stopping recording or switching the recording to a low frame rate. 3. The recording determination device according to claim 1, wherein the state determination unit determines that a temporal variation amount of the edge component is small according to a second determination criterion. A video recording determining device for stopping video recording of the image information in the storage device or switching the video information to a low frame rate. 4. The recording judging device according to claim 1, wherein said edge detecting means is configured to determine said frame difference by a predetermined area selection criterion as a candidate area for edge detection and a non-candidate area. And a true edge detection means for detecting a true edge component from the candidate area according to a predetermined edge classification criterion, wherein the quantitative evaluation is performed on the true edge component. Characteristic recording determination device. 5. The recording judging device according to claim 4, wherein the true edge detecting means comprises: a differential filtering processing means for obtaining a differential value of the image information of the frame difference; and a differential filtering processing means for obtaining a differential value of the non-candidate area. A local maximum value calculating means for obtaining a local maximum value; a differential average value calculating means for obtaining an average value of the local maximum values of the non-candidate areas; and if the image information of the candidate area exceeds a differential average value,
A true edge determining means for determining that the true edge component exists in the candidate area. 6. The recording determination device according to claim 3, wherein the edge variation determination unit extracts a common set and a union set of an edge component of a past frame difference and an edge component of a current frame difference. Set extraction means; edge fixity calculation means for determining the ratio of the common set to the union set as the fixedness of the edge component; and, when frames in which the fixedness of the edge component exceeds a predetermined threshold value continue, A recording degree determination device comprising: a degree-of-fixation dependence determination unit configured to determine that a change in a component is small. 7. A method for acquiring image information from a photographing means for continuously photographing the inside of a monitoring range and causing a storage device to perform recording, wherein a reference frame serving as a reference is sequentially included in a photographing result by the photographing means. A frame difference detection step of calculating a frame difference that is a difference between the image information and the current frame to be updated; an edge detection step of detecting an edge component of the frame difference; A state determination step of stopping recording of the image information to the storage device or switching the recording to a low frame rate when it is determined that the state in the reference frame has not substantially changed from the state of the reference frame. And a recording determination method. 8. An apparatus for extracting an edge from an image, comprising: differential filtering processing means for obtaining a differential value of image information for a predetermined image range; and edge detection of the image range by a predetermined area selection criterion. Candidate area selecting means for selecting a candidate area and a non-candidate area; a local maximum value calculating means for obtaining a local maximum value of a differential value of the non-candidate area; and an average value of the local maximum value of the non-candidate area. Calculating a differential average value, and when the image information of the candidate area exceeds the differential average value,
An edge determination unit that determines that the edge component exists in the candidate area.