JPH08320935A - Method and device for processing moving image - Google Patents

Abstract

PURPOSE: To simply and surely detect a change in a video at a sufficiently high processing speed even when an exclusive device for processing the video is not prepared. CONSTITUTION: This moving image processing method is provided with a change detection step 2 for detecting a change in a video by comparing a still picture inputted from the video in a picture input step 1 with the newest changed picture obtained at the time of detecting the newest change out of video changes generated in the past, a newest change picture storing step 3 for storing the still picture to be compared at the time of detecting a change in the video as the newest changed picture. A moderate video change also can be surely detected by comparing a still picture inputted from a current video with the newest changed picture and detecting the existence of a change in the current picture.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a moving image processing method and apparatus, and more particularly, to image transmission capable of reducing the amount of transmitted data, the amount of stored data or the amount of display data by detecting a change in an image. It is suitable for use in a device, a video storage device, or a moving image display device. That is, the present invention can be used in, for example, a monitoring device that transmits or stores video in the monitoring area, a TV conference device, a general-purpose computer that handles moving images, a video server, or the like.

[0002]

2. Description of the Related Art Conventionally, in the field of monitoring such as road monitoring and nighttime monitoring, the cost of monitoring is monitored by transmitting and monitoring a video image taken by a television camera or the like in a monitoring area or storing it in a storage device. Devices have been used to reduce In this case, it has been practiced to detect the change in the video and output the video only when the video changes to reduce the amount of transmission data or the amount of stored data.

In recent years, such as in TV conferences,
WAN (Wide Area Network) without monitoring
), LAN (Local Area Network), and other communication networks are often transmitting and storing images between remote locations. Further, as the performance of a general-purpose computer is improved, it is becoming possible to transmit and store a moving image even with a general-purpose computer because the moving image is simply displayed.

[0004]

By the way, since the video data has a very large amount of data, a dedicated device is required to perform the video change detection processing at the same speed as the video processing. . Further, if there is no dedicated device, the once stored image is processed over time.

However, as described above, the video conferencing system using a general-purpose computer has been increasingly used in recent years, and thus the general-purpose computer is often used to transmit, store, or display an image. For this reason, there is a need for a method of performing image change detection processing at the same speed as image processing without using a dedicated device.

On the other hand, regarding the above-mentioned image change detection method,
Many methods have been proposed in the past, but as a relatively simple method, a method of detecting a change area by taking a difference between two images has been proposed (Sakuma, Ito,
Masuda, "Intruding Object Detection Method Using Interframe Difference," Technical Report of Television Society of Japan, vol.14, No.49, pp1-6, 1990). According to this simple method, even a general-purpose computer can be executed at a sufficient processing speed.

As described above, as a method of detecting a change area based on a difference between two images, a method of detecting a change area based on a difference between a previously photographed background image and a current photographed image and a method of temporally approaching 2 A typical method is to detect a change area based on the difference between two frames.

As the latter method of detecting the change area based on the difference between the frames, for example, the video of the monitoring area is VT.
There has been proposed a device for recording in R, which detects a change in video and records the video in a VTR only when the video changes (JP-A-2-2486).

However, the method of detecting the change area based on the difference from the background image has a drawback in that there are many restrictions in use such as the need to prepare a background image without a moving object in advance. In addition, the method of detecting a change area based on a difference between temporally adjacent frames has a drawback that it is difficult to detect a change area because the difference becomes small when a change in video is gradual. Kaihei 2-24
No. 86 publication also uses this method).

The present invention has been made in view of the above circumstances, and it is possible to easily and reliably detect a change in an image at a sufficient processing speed without a dedicated device. To aim.

[0011]

According to the moving image processing method of the present invention, an image input step of extracting and inputting a still image from a moving image, a still image input in the image input step, and a still image generated in the past. A change detection step for detecting a change in video by comparing the latest change image when the latest change is detected among the video changes, and a comparison at that time when a change in video is detected in the change detection step. A latest changed image storing step of storing the still image as a target as a latest changed image.

Another feature of the present invention is that an image input step for extracting and inputting a still image from a moving image and a still image input at the image input step are differentiated to obtain a differential image. Video change detected by comparing the differential image creation step to be created with the differential image created in the differential image creation step and the latest change image when the latest change is detected among the video changes that occurred in the past And a latest change image storage step of storing the still image, which is a comparison target at that time, as the latest change image when a change in the video is detected in the change detection step. And

Further, the moving image processing apparatus of the present invention comprises image input means for extracting and inputting a still image from the moving image, and input image storage means for storing the still image input by the image input means. Change detecting means for detecting a change in video by comparing the still image input from the image input means with the latest change image when the latest change is detected among the video changes that have occurred in the past; The latest change image storage means for storing the still image stored in the input image storage means as the latest change image when the change in the video is detected by the means, and the still image stored in the input image storage means. Of these, an image output means for outputting only an image to be compared when a change in the video is detected by the change detection means is provided.

Another feature of the present invention is image input means for extracting and inputting a still image from a moving image, input image storage means for storing the still image input by the image input means, Differential image creating means for creating a differential image by applying differential processing to the still image stored in the input image storing means; differential image storing means for storing the differential image created by the differential image creating means; Change detecting means for detecting a change in video by comparing the differential image created by the image creating means with the latest change image when the latest change is detected among the video changes that occurred in the past, and the change detecting means. The latest change image storage means for storing the differential image stored in the differential image storage means as the latest change image when a change in the video is detected by the input image. Of the still images stored in 憶 means, characterized in that it comprises an image output means for outputting the image only when a change in image is detected by the change detecting means.

[0015]

According to the present invention constructed as described above, FIG.
As shown in Fig. 3, the change in video is detected by comparing the current image and the latest change image when the latest change is detected among the video changes that occurred in the past, so the difference between adjacent frames can be easily calculated. Although realized by the processing, it becomes possible to reliably detect even a slight change in the case where the image changes gently.

Further, when the change of the video is detected by using the differential image obtained by performing the differential processing on the input still image, the influence of the change of the illumination is removed, and the change of the image based on the change of the illumination is eliminated. Can be prevented from being detected.

[0017]

An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a flow chart showing the contents of the moving image processing method according to the first embodiment.

In FIG. 1, in the image input step 1,
A still image is extracted and input from an image obtained by shooting with a video camera (not shown) or a digital moving image stored in a disk device (not shown) (hereinafter, the input still image is referred to as an input image) .

In the change detection step 2, the input image input in the image input step 1 and the image when the latest change is detected among several video changes that have occurred in the past (hereinafter referred to as the latest change image). ) Is detected to detect the current change in the image. If a video change is detected, the process proceeds to the next latest change image storing step 3, and if no video change is detected, the process returns to the image input step 1.

In the latest changed image storing step 3, the input image which is the object of comparison when the change in the image is detected in the change detecting step 2 is stored as a new latest changed image. In the next image output step 4, the input image when the change in the image is detected in the change detection step 2 is output to a communication path (e.g. WAN or LAN) not shown and transmitted, or outputted to an image storage device not shown. Then, it is stored and output to an image display device (not shown) for display.

When the process of the image output step 4 is completed, unless there is an instruction to end the process, the process returns to the process of the image input step 1 again and the above process is repeated.

FIG. 2 is a functional block diagram showing an example of the configuration of a moving image processing apparatus that performs the processing shown in FIG. Further, FIG. 3 is a diagram showing a configuration example of actual hardware that realizes the functions shown in FIG.

In FIG. 3, reference numeral 21 denotes a CPU (central processing unit) which controls the operation of the entire moving image processing apparatus according to this embodiment. Reference numeral 22 denotes a ROM (Read Only Memory) in which various processing programs are stored. 23 is R
It is an AM (Random Access Memory) and stores various information in the course of processing.

A disk device 24 stores information such as digital moving images. A disk input / output device (disk I / O) 25 inputs and outputs digital moving image information stored in the disk device 24. Two
Reference numeral 6 denotes a video camera for obtaining video information by photographing a subject. Reference numeral 27 denotes a video capture device, which acquires a still image from a video obtained by the video camera 26.

Reference numeral 28 denotes a communication device, which receives a still image input from the disk device 24 via the disk I / O 25 or a still image input from the video camera 26 via the video capture device 27 by WAN or LAN. And the like via a communication path. 29 is a bus, and the above-mentioned C
PU21, ROM22, RAM23, disk I / O2
5, the video capture device 27 and the communication device 28 are connected.

Next, referring to FIG. 2, the image input means 11
Is to acquire a still image from a video obtained by a video camera or a digital moving image stored in a disk device and store the still image in the input image storage means 14.

For example, in FIG. 3, under the control of the CPU 21 which operates according to a program stored in the ROM 22 or the RAM 23, the video capture device 2 is operated from an image obtained by photographing with the video camera 26.
The still image (input image) is acquired at 7, and it is stored in the RAM 23.
It can be configured by a known image inputting means for storing in.

Alternatively, a still image (input image) is read from the digital moving image stored in the disk device 24 through the disk I / O 25 under the control of the CPU 21 which operates according to a program stored in the ROM 22 or the RAM 23, It can be configured by a known image input means for storing it in the RAM 23.

Although not shown in FIG. 3, under the control of the CPU 21 which operates according to a program stored in the ROM 22 or the RAM 23, a known image stored in the RAM 23 by capturing a still image (input image) with a digital still camera. It can also be configured by input means. Of course, a combination of a plurality of image input means as described above may be used.

Next, the change detection means 12 compares the input image stored in the input image storage means 14 with the latest change image stored in the latest change image storage means 15 to obtain the current image. Detect changes in. When a change in the video is detected, the input image stored in the input image storage means 14 at that time is stored in the latest change image storage means 15 as a new latest change image.

The change detecting means 12 as described above is, for example, in FIG. 3, a CPU 21 which operates according to a program stored in a ROM 22 or a RAM 23, and a RAM 23 or a disk device 2 which is used as a work memory.
4 and can be configured. Of course, each may be configured by a dedicated CPU, RAM and disk device, or may be configured by dedicated hardware.

Next, the image output means 13 sends the input image stored in the input image storage means 14 to the communication path (W) when the change detection means 12 detects a change in the image.
It is output to an AN, LAN, etc.) for transmission, output to an image storage device for storage, or output to an image display device for display.

For example, in FIG. 3, under the control of the CPU 21 which operates according to a program stored in the ROM 22 or the RAM 23, the W is transmitted through the communication device 28.
It can be constituted by a known image output means for transmitting an image to a communication path such as AN or LAN.

Alternatively, it can be constituted by a known image output means which is stored in the disk device 24 as a part of the digital moving image under the control of the CPU 21 which operates according to a program stored in the ROM 22 or the RAM 23. Here, the disk device 24 may be one that can be used through a network such as a LAN.

Although not shown in FIG. 3, a known image output means may be used to display a moving image by continuously displaying a still image on the same portion of the display. Of course, a combination of a plurality of image output means as described above may be used.

The input image storage means 14 and the latest change image storage means 15 are the RAM 2 in FIG. 3, for example.
3 or the disk device 24. Of course, each means may be configured by a dedicated storage device.

The input image storage means 14 and the latest change image storage means 15 may be configured to use two image storage means 16a and 16b as shown in FIG. 4 and switch between them. . That is, in this configuration, each time the change detecting unit 12 detects a change in video, the roles of the image storing units 16a and 16b are switched in the latest change image storing step 3 in FIG.

For example, when an input image is sequentially stored in one of the image storage means 16a and a change in video is detected at a certain time point, the one image storage means 16a stores the latest change image. Switched to the storage means of
The other image storage means 16b is switched to a storage means for storing the input image.

As a result, the input image stored in the image storage means 16a at the time when the video change is detected is used as the latest change image thereafter, as shown in FIG.
In this case, it is possible to reduce the processing of copying the input image from the input image storage means 14 to the latest change image storage means 15, which is a benefit.

The processing contents of each step shown in FIG. 1 will be described in detail below with reference to the configurations of FIGS. 2 and 3.

<Image Input Step 1> In the image input step 1, the image input means 11 acquires a still image from an image obtained by the video camera 26 or a digital moving image stored in the disk device 24, or is not shown. A still image is taken using a digital still camera or the like, and the still image is stored in the input image storage means 14.

<Change Detection Step 2> In the change detection step 2, by comparing the input image stored in the input image storage means 14 with the latest change image stored in the latest change image storage means 15, To detect changes in video.

FIG. 5 shows an example of processing contents executed by the CPU 21 in accordance with the program stored in the ROM 22 or the RAM 23 of FIG. 3 in the change detecting step 2. In this process, the pixel value difference (absolute value) between corresponding pixels is calculated using the input image and the latest change image, and if the sum of the pixel value differences in the entire image is greater than a certain value, the input image Is judged to have changed compared to the latest changed image. That is, it is determined that the image has changed.

Here, the calculation of the pixel value difference is performed by processing each pixel of the image in raster order as shown in FIG. 6, and the sum of the pixel value differences during the processing is called the total change amount. To do. Of course, each pixel may be processed in parallel.

In FIG. 5, in step S101, the total change amount is initialized to zero. In step S102, the pixel value difference between the pixels currently being processed (hereinafter referred to as the target pixel) is calculated.

The value of the pixel value difference is, for example, 2 for the input image.
In the case of a value image, 1 is set if the value of the target pixel is different, and 0 is set if the value is the same. If the input image is a grayscale image,
For example, the absolute value of the difference between the values of the pixel of interest is set. If the input image is a color image, for example, RGB of the target pixel
The absolute value of each difference in value is calculated, and the absolute value of each difference is summed.

In step S103, the above step S1
The pixel value difference calculated in 02 is added to the total change amount. In step S104, it is determined whether or not the total change amount calculated in step S103 is larger than a preset value (threshold value), and if it is larger, it is determined that there is a change in the image, and the process shown in FIG. 5 ends. If the total change amount is not larger than the threshold value, the process proceeds to step S105.

In step S105, it is determined whether all pixels have been processed. When all the pixels have been processed, it is considered that there is no change in the image, and the processing shown in FIG. 5 ends. On the other hand, if there are still unprocessed pixels, the process proceeds to step S106. In step S106,
The process is moved to the next pixel (the target pixel is changed to the next pixel), and the process returns to step S102.

<Latest change image storage step 3> In the latest change image storage step 3, when the change of the image is detected in the change detection step 2, the input stored in the input image storage means 14 in the image input step 1 is input. The image is stored in the latest changed image storage means 15 as a new latest changed image.

<Image Output Step 4> In the image output step 4, when the change in the image is detected in the change detecting step 2, the input image stored in the input image storage means 14 is transmitted through the communication device 28 or the like to the communication path. Output to (WAN, LAN, etc.) and send, or disk device 24
It is output to and stored in an image display device (not shown).

As described above, according to the first embodiment, it becomes unnecessary to prepare in advance an image that does not change, such as a background image, as the comparative image.
It is possible to reliably detect even a slight change when the image changes gently.

Therefore, the amount of video data can be reduced by simply and reliably detecting a change in video at a sufficient speed without outputting a dedicated device and outputting the video only when the change in video is detected. It can be output. For example, it is possible to reduce the amount of transmission data, the amount of storage data, or the amount of display data by outputting only the image in which the change is detected to the communication path, the storage device, or the display device.

Next, a second embodiment of the present invention will be described. The second embodiment shows another implementation example of the process of the change detection step 2 in the first embodiment described above.

FIG. 7 shows an example of processing contents executed by the CPU 21 in accordance with the program stored in the ROM 22 or the RAM 23 of FIG. 3 in the change detecting step 2 according to the present embodiment.

In this process, the pixel value difference (absolute value) between corresponding pixels is calculated using the input image and the latest change image, and each pixel value difference has a certain value (first threshold value).
If it is above, it is assumed that the pixel of interest has changed (hereinafter, the changed pixel is referred to as a changed pixel). Furthermore, if the number of changed pixels in the entire input image is greater than or equal to a certain value (second threshold value), it is determined that the input image has changed compared to the latest changed image. That is, it is determined that the image has changed.

As in the first embodiment, the determination of the changed pixel is made by processing each pixel of the image in the raster order as shown in FIG. The total number of changed pixels in the process is called the number of changed pixels. Of course, each pixel may be processed in parallel.

In FIG. 7, in step S201, the number of changed pixels is initialized to zero. In step S202, the pixel value difference between the target pixels currently being processed is calculated by the same method as in the first embodiment.

In step S203, the above step S2
It is determined whether the pixel value difference calculated in 02 is larger than a preset value (first threshold value). If the pixel value difference is larger than the first threshold, it is determined that the pixel of interest has changed, and the process proceeds to step S204, and the number of changed pixels is incremented by 1. If the pixel value difference is not larger than the first threshold value, it is determined that there is no change in the pixel of interest and step S206.
Jump to.

Step S2 following step S204
In 05, it is determined whether or not the number of changed pixels calculated in step S204 is larger than a preset value (second threshold value). If larger, it is determined that there is a change in the image, and the process shown in FIG. 7 ends. To do. If the number of changed pixels is not larger than the second threshold value, step S206.
Proceed to.

In step S206, it is determined whether all pixels have been processed. Then, when all the pixels have been processed, it is determined that there is no change in the image, and the processing shown in FIG. 7 ends. On the other hand, if all the pixels have not been processed, the process proceeds to step S207. In step S207,
The process is moved to the next pixel (the target pixel is changed to the next pixel), and the process returns to step S202.

In the second embodiment, as in the first embodiment, the change in the image can be detected easily and reliably at a sufficient speed without the dedicated device, and the change in the image can be detected. By outputting the image to the communication path, the storage device or the display device only when it is detected, the transmission data amount, the storage data amount or the display data amount can be reduced.

Next, a third embodiment of the present invention will be described. The third embodiment shows yet another implementation example of the process of the change detection step 2 in the first embodiment.

FIG. 8 shows an example of processing contents executed by the CPU 21 in accordance with the program stored in the ROM 22 or the RAM 23 of FIG. 3 in the change detecting step 2 according to the present embodiment.

In this process, as shown in FIG. 9, the input image and the latest change image are divided into a plurality of blocks, and a change in video is detected for each block. In each block, similarly to the first embodiment, the pixel value difference (absolute value) between the corresponding pixels is calculated using the input image and the latest change image, and the sum of the pixel value differences in each block is calculated. Is a value (first
If it is equal to or more than the threshold value), it is determined that the video in the corresponding block has changed.

If the number of changed blocks (hereinafter referred to as changed blocks) in the entire input image is greater than or equal to a certain value (second threshold value), the input image changes as compared with the latest changed image. Determine that That is, it is determined that the image has changed.

Here, the calculation of the pixel value difference in each block is performed by processing each pixel in raster order as shown in FIG. 9 (a). Further, as shown in FIG. 9B, each block is also processed in raster order. Note that the sum of pixel value differences in a block in the process of processing is called a total change amount, and the sum of changed blocks is called a changed block number. Of course, each pixel or each block may be processed in parallel.

In FIG. 8, in step S301, the number of changed blocks is initialized to 0. Also, step S30
At 2, the total change amount is initialized to 0. Step S30
In 3, the pixel value difference between the target pixels is calculated by the same method as in the first embodiment. Next, in step S304, the pixel value difference calculated in step S303 is added to the total change amount.

In step S305, the above step S3 is performed.
It is determined whether the total change amount calculated in 04 is larger than a preset value (first threshold value).
It is assumed that there is a change in the block of interest, the process proceeds to step S307, and 1 is added to the number of changed blocks. If the total change amount is not larger than the first threshold value, step S3
Proceed to 06.

In step S306, it is determined whether all the pixels in the target block have been processed. When all the pixels have been processed, it is determined that there is no change in the block of interest, the process proceeds to step S311, and the process is moved to the next block (the block of interest is changed to the next block).
It returns to the process of step S302. If all the pixels have not been processed, the process proceeds to step S310, the process is moved to the next pixel (the target pixel is changed to the next pixel), and the process returns to step S303.

Step S3 following step S307
In step 08, it is determined whether or not the number of changed blocks calculated in step S307 is larger than a preset value (second threshold value). If larger, it is determined that the image has changed, and the process shown in FIG. 8 is terminated. . If the number of changed blocks is not larger than the second threshold value, step S
Proceed to 309.

In step S309, it is determined whether all blocks have been processed. Then, when all the blocks have been processed, it is determined that there is no change in the image, and the process shown in FIG. 8 ends. If all blocks have not been processed, the process proceeds to step S311, the process moves to the next block, and the process returns to step S302.

Since the purpose here is to detect whether or not there is a change in the image, the processing is terminated when the number of changed blocks exceeds the second threshold value. It is also possible to change so that the process is continued until the last block as in the flowchart shown in FIG.

By doing so, although the processing amount increases, it is possible to detect all the changed blocks in the entire image. Then, by transmitting, storing, or displaying only the changed block, it is possible to further reduce the transmission data amount, the storage data amount, or the display data amount.

Next, a fourth embodiment of the present invention will be described. The fourth embodiment shows another implementation example of the process of the change detection step 2 in the first embodiment described above.

FIG. 11 shows an example of the processing contents executed by the CPU 21 in accordance with the program stored in the ROM 22 or the RAM 23 of FIG. 3 in the change detecting step 2 according to the present embodiment.

In this process, as shown in FIG. 9, the input image and the latest change image are divided into a plurality of blocks, and the change in the video is detected for each block. In each block, similarly to the second embodiment, the pixel value difference (absolute value) between corresponding pixels is calculated using the input image and the latest change image, and the value of each pixel value difference is a certain value. If it is (first threshold) or more, it is assumed that the pixel of interest has changed.

Further, if the number of changed pixels in each block is equal to or larger than a certain value (second threshold value), it is determined that the corresponding block is changed. Then, a value having a certain number of changed blocks in the entire input image (third threshold value)
When it is above, it is determined that the input image has changed compared with the latest changed image. That is, it is determined that the image has changed.

The calculation of the pixel value difference in each block is performed by processing each pixel in raster order as shown in FIG. 9A, as in the third embodiment.
As shown in (b), each block is processed in raster order. The total number of changed pixels in the block being processed is called the number of changed pixels, and the total number of changed blocks is called the number of changed blocks. Of course, each pixel or each block may be processed in parallel.

In FIG. 11, in step S401,
The number of changed blocks is initialized to 0. Also, step S4
In 02, the number of changed pixels is initialized to 0. Step S4
In 03, the pixel value difference between the target pixels is calculated by the same method as in the first embodiment.

In step S404, the above step S4
It is judged whether or not the pixel value difference calculated in 03 is larger than a preset value (first threshold value).
If there is a change in the pixel of interest, the process proceeds to step S405 and the number of changed pixels is incremented by 1. If the pixel value difference is not larger than the first threshold, it is determined that the target pixel has not changed, and the process jumps to step S407.

Step S4 following step S405
In 06, it is determined whether the number of changed pixels calculated in step S405 is larger than a preset value (second threshold value). If larger, it is determined that the target block has changed, and the process jumps to step S408. Add 1 to the number of changed blocks. If the number of changed pixels is not larger than the second threshold, the process proceeds to step S407.

In step S407, it is determined whether all the pixels in the target block have been processed. When all the pixels have been processed, it is determined that there is no change in the target block, the process proceeds to step S412, and the process is moved to the next block (the target block is changed to the next block).
It returns to the process of step S402. If all the pixels have not been processed, the process proceeds to step S411, the process is moved to the next pixel (the target pixel is changed to the next pixel), and the process returns to step S403.

Step S4 following step S408
In step 09, it is determined whether the number of changed blocks calculated in step S408 is larger than a preset value (third threshold value). If larger, it is determined that the image has changed, and the process shown in FIG. 11 is terminated. . If the number of changed blocks is not larger than the third threshold, the process proceeds to step S410.

In step S410, it is determined whether all blocks have been processed. Then, when all blocks are processed, it is assumed that there is no change in the image.
The process shown in is ended. If all blocks have not been processed, the process proceeds to step S412, the process is moved to the next block, and the process returns to step S402.

Similar to the third embodiment, the purpose here is to detect whether or not there is a change in the image. Therefore, if the number of changed blocks becomes equal to or larger than the third threshold value, the process is terminated. However, as in the flowchart shown in FIG. 12, it is possible to change the processing so that it continues to the last block. Then, by transmitting, storing or displaying only the detected changed block, the third block is displayed.
Similar to the embodiment described above, the amount of transmitted data, the amount of stored data, or the amount of display data can be further reduced.

Next, a fifth embodiment of the present invention will be described. In the fifth embodiment, as shown in FIG. 13, between the processing of the image input step 1 and the processing of the change detection step 2 in the processing procedure of FIG. 1 shown in the first to fourth embodiments. A differential image creation step 5 is added.

In the differential image creating step 5, the input image input in the image input step 1 is subjected to a differential process such as a so-called Sobel operator (hereinafter, the image subjected to the differential process is referred to as a differential image). Other processing steps 1 to 4
Is similar to that described in the first to fourth embodiments, but in the change detection step 2, the same processing as in the first to fourth embodiments is performed on the differential image instead of the input image. To do. Further, in the latest change image storing step 3, the differential image is stored instead of storing the input image.

By doing so, although the processing becomes complicated, it is possible to prevent the change of the image due to the change of the illumination from being detected. This is because in some applications it may be advantageous not to detect changes in the image due to changes in illumination. First to fourth described above
The same effect can be expected depending on the threshold setting method in this embodiment, but this embodiment has an advantage that it is not necessary to consider the change in illumination when setting the threshold.

FIG. 14 is a block diagram showing an example of the configuration of a moving image processing apparatus that performs the processing shown in FIG. The configuration example shown in FIG. 14 is similar to the first to fourth embodiments,
It can be realized by the hardware shown in FIG.

That is, the differential image creating means 17 of FIG.
Is a CPU 21 that operates according to a program stored in the ROM 22 or the RAM 23 of FIG. 3, and a RAM 23 or a disk device 24 that is used as a work memory.
It can be composed of and. This differential image creating means 17
Performs differential processing on the input image stored in the input image storage means 14, and stores the differential image obtained by this in the differential image storage means 18. Further, the differential image storage means 18 can be constituted by the RAM 23 or the disk device 24 in FIG. 3, for example.

The other means shown in FIG. 14 is the same as that described in the first to fourth embodiments, but the change detecting means 12 is
The same processing as in the first to fourth embodiments is performed not on the input image stored in the input image storage means 14 but on the differential image stored in the differential image storage means 18. The latest change image storage unit 15 does not store the input image stored in the input image storage unit 14 as the latest change image, but stores the differential image stored in the differential image storage unit 18.

The configuration shown in FIG. 14 has the first to fourth aspects.
It is possible to replace the configuration as shown in FIG. That is, the differential image storage means 18 and the latest change image storage means 15 in FIG. 14 can be changed to a mode in which the two image storage means 16a and 16b are used by switching as shown in FIG. By doing so, it is possible to reduce the processing of copying the differential image from the differential image storage means 18 to the latest change image storage means 15, which has been performed in the case of FIG.

[0093]

As described above, the present invention realizes the detection of a video change by a simple process called a difference process, so that it is sufficiently fast even without a dedicated device for processing a video with a large amount of data. Despite being able to detect changes at various processing speeds, it compares the still image input from the current video with the latest change image when the latest change in video changes that occurred in the past is detected. By doing so, it is detected whether there is a change in the current image,
Even when the image changes gently, the change can be detected.

[Brief description of drawings]

FIG. 1 is a flow chart showing processing of a moving image processing method according to first to fourth embodiments of the present invention.

FIG. 2 is a diagram showing a configuration example of a moving image processing apparatus according to first to fourth embodiments.

FIG. 3 is a diagram illustrating a hardware implementation example of a moving image processing apparatus to which the present invention has been applied.

FIG. 4 is a diagram showing another configuration example of the moving image processing apparatus according to the first to fourth examples.

FIG. 5 is a flowchart showing processing of a change detection step according to the first embodiment.

FIG. 6 is a diagram for explaining a pixel processing order according to the first and second embodiments.

FIG. 7 is a flowchart showing a process of a change detecting step according to the second embodiment.

FIG. 8 is a flowchart showing a process of a change detection step according to the third embodiment.

FIG. 9 is a diagram for explaining an example of block division, pixel processing order, and block processing order according to the third and fourth embodiments.

FIG. 10 is a flowchart showing another processing content of a change detection step according to the third embodiment.

FIG. 11 is a flowchart showing processing of a change detection step according to the fourth embodiment.

FIG. 12 is a flowchart showing another processing content of a change detection step according to the fourth embodiment.

FIG. 13 is a flowchart showing the processing of the moving image processing method according to the fifth embodiment of the present invention.

FIG. 14 is a diagram showing a configuration example of a moving image processing apparatus according to a fifth embodiment.

FIG. 15 is a diagram showing another configuration example of the moving image processing apparatus according to the fifth embodiment.

FIG. 16 is a diagram for explaining an outline of a moving image processing method to which the present invention has been applied.

[Explanation of symbols]

 1 image input step 2 change detection step 3 latest change image storage step 4 image output step 5 differential image creation step 11 image input means 12 change detection means 13 image output means 14 input image storage means 15 latest change image storage means 16a, 16b image Storage means 17 Differential image creating means 18 Differential image storage means

Claims (21)

[Claims] 1. An image input step of extracting and inputting a still image from a moving image, and a latest image when a latest change is detected among the still image input in the image input step and a video change that has occurred in the past. When a change detection step of detecting a change in the video by comparing the change image and a change in the video in the change detection step,
And a latest change image storing step of storing the still image to be compared as the latest change image at that time. 2. An image input step of extracting and inputting a still image from a moving image, and a latest image when a latest change is detected among the still image input in the image input step and a video change that has occurred in the past. When a change detection step of detecting a change in the video by comparing the change image and a change in the video in the change detection step,
The latest change image storing step for storing the still image as the comparison target at that time as the latest change image, and the still image input in the image input step only when a change in video is detected in the change detecting step. An image output step for outputting the moving image processing method. 3. In the change detecting step, the pixel value difference between corresponding pixels is calculated using the still image and the latest change image, and the sum of the pixel value differences in the entire image is equal to or more than a predetermined threshold value. 3. The moving image processing method according to claim 1, wherein it is determined that there is a change in the video. 4. In the change detecting step, a pixel value difference between corresponding pixels is calculated using the still image and the latest change image, and each pixel value difference value is equal to or larger than a first threshold value. 3. It is determined that the corresponding pixel has changed at a certain time, and it is determined that the image has changed when the number of changed pixels in the entire image is equal to or larger than the second threshold value. The moving image processing method described in. 5. The change detecting step divides the still image and the latest change image into a plurality of blocks,
The sum of the pixel value differences between the corresponding pixels of the still image and the latest change image is calculated for each block, and when the total value is equal to or more than the first threshold value, it is determined that the corresponding block has changed. 3. The moving image processing method according to claim 2, wherein it is determined that the image has changed when the number of changed blocks in the entire image is equal to or larger than the second threshold value. 6. The change detecting step divides the still image and the latest change image into a plurality of blocks,
Each pixel value difference between the corresponding pixels of the still image and the latest change image is calculated, and when the value of each pixel value difference is equal to or more than the first threshold value, it is determined that the corresponding pixel has changed, When the number of changed pixels in the block is equal to or larger than the second threshold, it is determined that the corresponding block has changed, and when the number of changed blocks in the entire image is equal to or larger than the third threshold, the image of the image is changed. The moving image processing method according to claim 2, wherein it is determined that there is a change. 7. An image input step of extracting and inputting a still image from a moving image, a differential image creating step of applying differential processing to the still image input in the image input step to create a differential image, A change detection step of detecting a change in video by comparing the differential image created in the differential image creation step with the latest change image when the latest change is detected among the video changes that occurred in the past; When a change in the image is detected at the step,
And a latest change image storing step of storing the still image to be compared as the latest change image at that time. 8. An image input step of extracting and inputting a still image from a moving image, a differential image creating step of applying differential processing to the still image input in the image input step to create a differential image, A change detection step of detecting a change in video by comparing the differential image created in the differential image creation step with the latest change image when the latest change is detected among the video changes that occurred in the past; When a change in the image is detected at the step,
The latest change image storing step for storing the still image as the comparison target at that time as the latest change image, and the still image input in the image input step only when a change in video is detected in the change detecting step. An image output step for outputting the moving image processing method. 9. In the change detection step, pixel value differences between corresponding pixels are calculated using the differential image and the latest change image, and the sum of pixel value differences in the entire image is equal to or greater than a predetermined threshold value. 9. The moving image processing method according to claim 7, wherein it is determined that there is a change in the image. 10. In the change detecting step, pixel value differences between corresponding pixels are calculated using the differential image and the latest change image, and the value of each pixel value difference is not less than a first threshold value. 9. It is determined that the corresponding pixel has changed at a certain time, and it is determined that the image has changed when the number of changed pixels in the entire image is equal to or larger than the second threshold value. The moving image processing method described in. 11. The change detecting step divides the differential image and the latest change image into a plurality of blocks, and sums pixel value differences between corresponding pixels of the differential image and the latest change image for each block. Is calculated, it is determined that the corresponding block has changed when the total value is equal to or more than the first threshold value, and when the number of changed blocks in the entire image is equal to or more than the second threshold value, the image change is The moving image processing method according to claim 8, wherein it is determined that there is. 12. In the change detection step, the differential image and the latest change image are divided into a plurality of blocks, pixel value differences between corresponding pixels of the differential image and the latest change image are calculated, and It is determined that the corresponding pixel has changed when the pixel value difference value of is greater than or equal to the first threshold, and the number of changed pixels in the block is greater than or equal to the second threshold. The moving image processing method according to claim 8, wherein it is determined that there is a change, and it is determined that there is a change in the image when the number of changed blocks in the entire image is equal to or larger than a third threshold value. 13. The change detecting step, when it is determined that there is a change in the image, also determines the change position of the image according to the position of the block determined to have changed. 13. The moving image processing method according to any one of 6, 11, and 12. 14. The image output step outputs only an image of a change position detected in the change detection step among the still images input in the image input step. Video processing method. 15. An image input unit for extracting and inputting a still image from a moving image, an input image storage unit for storing the still image input by the image input unit, and a still image input by the image input unit. Change detection means for detecting a change in the video by comparing the image with the latest change image when the latest change is detected among the video changes that occurred in the past; and the change in the video is detected by the change detection means. At this time, among the still images stored in the input image storage means, the still image stored in the input image storage means is stored as the latest changed image. An image output unit that outputs only an image to be compared when a change is detected, the moving image processing apparatus. 16. The input image storage means and the latest change image storage means are composed of two image storage means, and the roles of the two image storage means are switched each time the change of the image is detected by the change detection means. 16. The moving image processing apparatus according to claim 15, wherein the moving image processing apparatus is configured to be configured to operate. 17. An image input unit for extracting and inputting a still image from a moving image, an input image storage unit for storing the still image input by the image input unit, and an image stored in the input image storage unit. Differential image creating means for creating a differential image by applying differential processing to a still image, differential image storing means for storing the differential image created by the differential image creating means, and differential image created by the differential image creating means Change detection means for detecting a change in the video by comparing the latest change image when the latest change is detected among the video changes that occurred in the past, and when the change in the video is detected by the change detection means. The latest change image storage means for storing the differential image stored in the differential image storage means as the latest change image, and the still image stored in the input image storage means. A moving image processing apparatus, comprising: an image output unit that outputs only an image when an image change is detected by the change detection unit. 18. The differential image storage means and the latest change image storage means are composed of two image storage means, and the roles of the two image storage means are switched each time the change detection means detects a change in an image. 18. The moving image processing apparatus according to claim 17, wherein the moving image processing apparatus is configured to be configured to operate. 19. The image output means outputs only an image of a still image stored in the input image storage means when a change in the image is detected by the change detection means to a communication path to form an image. It transmits, It is characterized by the above-mentioned.
The moving image processing apparatus according to any one of items 1 to 18. 20. The image output means outputs, to the storage device, only the image when the change in the image is detected by the change detection means among the still images stored in the input image storage means, and outputs the image. The information is stored in the memory.
The moving image processing apparatus according to any one of 5 to 18. 21. The image output means outputs, to the display device, only the image when the change in the image is detected by the change detecting means, among the still images stored in the input image storage means, and outputs the image. Displayed according to claim 1.
The moving image processing apparatus according to any one of 5 to 18.