JP6942959B2 - Image processing system - Google Patents

Description

The present invention relates to an image processing system that compresses and encodes an image signal.

In recent years, surveillance cameras have become widespread, and higher resolution, higher frame rates, and multiple viewpoints are desired. However, higher resolution, higher frame rate, and higher multi-viewpoint cause a significant increase in the amount of moving image data, resulting in an increase in communication cost and storage cost.

In order to alleviate this problem, a specific area where, for example, a "face" is displayed is detected as an ROI (Region of Interest) in the moving image, and a large number of bits are assigned to this ROI to perform image compression processing. An image processing apparatus has been proposed (see, for example, Patent Document 1).

In the image processing device, the amount of information in the area other than the ROI, that is, the background area is reduced from the amount of information in the ROI by utilizing the function of the compression unit that sets the parameters for controlling the code amount and the image quality for each block. By controlling the parameters given to the compression unit, the amount of data is reduced.

However, when a compression unit that does not have such a parameter control function is used, the amount of data cannot be reduced by the above method.

Therefore, in order to reduce the amount of information in the background area without depending on the compression unit, the amount of information in the background area should be reduced by filtering the background area with a low-pass filter to remove the information of high-frequency components. An image encoding device has been proposed (see, for example, Patent Document 2). In this image coding apparatus, the generation of artifacts generated at the block boundary is suppressed while reducing the amount of information of the image signal by filtering with a low-pass filter.

Japanese Unexamined Patent Publication No. 2009-49979 Japanese Unexamined Patent Publication No. 4-219089

However, if a scene in which one picture is filled with ROI, for example, a scene in which a close-up face is projected or a scene in which a large number of faces are filled continues, the entire screen continues to be encoded with high quality. It becomes the same as the state in which it is present, and the effect of reducing the code amount cannot be obtained by the above method. Therefore, there is a risk of exceeding the expected communication capacity and storage capacity.

Therefore, it is conceivable to thin out the pictures as a countermeasure against the capacity excess, but in this case, there is a possibility that a decisive scene may be missed, which leads to a decrease in the monitoring ability by the captured image.
It is also possible to prevent the capacity from being exceeded by lowering the quality of the ROI, but since the purpose is to monitor, lowering the quality of the ROI area leads to a decrease in the monitoring ability. Further, when some kind of post-processing such as authentication processing is performed on the decoding side, the accuracy of the post-processing may be impaired due to the decisive missed shooting of the scene and the deterioration of the image quality. For example, when ROI is used as a face area and individual authentication is performed for each face area on the decoding side, decisive scene misses (for example, missed shots of a front facing scene) and deterioration of image quality are authenticated. It may lead to deterioration of accuracy. Further, when the ROI is a license plate, it leads to deterioration of the recognition accuracy of the license plate.

Therefore, an object of the present invention is to provide an image processing system capable of reducing the code amount of an image signal while preventing a decrease in the recognition accuracy of ROI (area of interest) on the decoding side.

The image processing system according to the present invention is an image processing system that encodes an input image signal and outputs it as a bit stream signal, and determines a region of interest designated as a desired region in an image based on the input image signal with predetermined quality. When it is determined whether or not to encode with the predetermined quality, and when it is determined that the coding is performed with the predetermined quality, the information prompting the coding with the predetermined quality is determined, and when it is determined that the information is not encoded with the predetermined quality, the predetermined quality is determined. An attention area determination unit that generates attention area information indicating information that promotes coding at a low quality lower than the quality in association with the attention area, and the attention area in the input image signal according to the attention area information. An image coding unit that outputs the bit stream signal including a signal encoded with the predetermined quality or the low quality, and an area in which a predetermined object is displayed in an image based on the input image signal are defined as the area of interest. The attention area tracking unit that detects and updates the detected information about the attention area by tracking to generate the initial information of the attention area, and the usefulness of the attention area for each of the attention areas indicated by the initial information of the attention area. Is obtained, and the attention area usefulness assigning unit that generates the attention area secondary information including the usefulness in the attention area initial information and the attention area secondary information are buffered by a predetermined picture for buffering. Of the secondary information of the attention region, the portion corresponding to the first picture is output as the attention region determination target information, and the portion corresponding to the picture group following the first picture is output as the attention region look-ahead information. The attention area pre-reading unit includes a read-ahead buffer, and by referring to the attention area pre-read information, the attention area pre-read information is used for each of the attention areas indicated by the attention area determination target information. The image coding unit determines that the region of interest whose usefulness is higher than the usefulness indicated in the information for determining the area of interest is not encoded with the predetermined quality, and the attention is given. When the usefulness indicated by the area look-ahead information is equal to or less than the usefulness indicated by the attention area determination target information, the image coding unit encodes the attention area with the predetermined quality. to determine.

In the present invention, when encoding the ROI (area of interest) included in the input image signal, it is necessary to selectively perform coding with a predetermined quality or with a lower quality lower than the predetermined quality. I have to. Therefore, first, the region of interest is encoded with a predetermined quality, and then the region of interest is encoded with a low quality. As a result, coding with a predetermined quality using a relatively large number of bits is performed at least once with respect to the region of interest, so that a decrease in recognition accuracy with respect to the region of interest can be suppressed on the decoding side. Further, after the region of interest is encoded with a predetermined quality, the coding amount of the image signal is reduced because the coding is performed with a low quality that uses fewer bits than the coding with the predetermined quality. ..

Therefore, according to the present invention, it is possible to reduce the code amount of the image signal while preventing the recognition accuracy of the region of interest on the decoding side from being lowered.

It is a block diagram which shows the structure of the 1st Example of an image processing system S1. It is a flowchart which shows the operation of the ROI detection unit U1. It is a flowchart which shows the operation of the ROI detection unit U1. It is a block diagram which shows the structure of the 2nd Example of the image processing system S1. It is a flowchart which shows the operation of the ROI detection unit U1a. It is a flowchart which shows the operation of the ROI detection unit U1a. It is a figure which shows an example of the function f (L) which obtains the usefulness U. It is a figure which shows another example of the function f (L) which obtains the usefulness U. It is a figure which shows the modification of another example of the function f (L) which obtains the usefulness U. It is operation conceptual diagram of the read-ahead buffer 203. It is a block diagram which shows the structure of the 3rd Example of an image processing system S1. It is a flowchart which shows the operation performed by the ROI detection unit U1b and the code amount monitoring unit 310. It is a flowchart which shows the operation performed by the ROI detection unit U1b and the code amount monitoring unit 310.

Hereinafter, examples of the present invention will be described in detail with reference to the drawings.

FIG. 1 is a block diagram showing an image processing system S1 according to the present invention. The image processing system S1 is used, for example, to compress a surveillance image captured by a surveillance camera or the like and transmit a bitstream signal with suppressed data capacity to another device. That is, the image processing system S1 receives the monitoring image as an input image signal D12 including a sequence of pixel values representing the brightness level for each pixel, and compresses the input image signal D12 to obtain a bitstream signal. Output D08.

As shown in FIG. 1, the image processing system S1 includes a ROI (Region of Interest) detection unit U1 and an image coding unit U2.

The ROI detection unit U1 detects a region in which a specific object such as a "face" is displayed as the ROI, that is, a region of interest by applying, for example, a face detection algorithm from the input image signal D12. Then, the ROI detection unit U1 has information indicating the position of the ROI in the image for each detected ROI, and when the ROI is encoded by the image coding unit U2, a predetermined quality peculiar to the ROI (hereinafter, ROI quality). ROI information D04 including information indicating whether to encode with (also referred to as) or with a low quality lower than the ROI quality is generated and supplied to the image coding unit U2.

The image coding unit U2 is obtained by compressing the ROI encoded in the input image signal D12 with the ROI quality and the ROI encoded with the lower quality than the ROI quality with different qualities based on the ROI information D04. Outputs the bit stream signal D08. Specifically, the image coding unit U2 assigns a number of bits larger than a predetermined number of coding bits to the ROI to be encoded with the ROI quality and performs coding. On the other hand, for the ROI to be encoded with a low quality lower than the ROI quality, the image coding unit U2 allocates a number of bits smaller than the predetermined number of coding bits and performs encoding.

As shown in FIG. 1, the ROI detection unit U1 includes an ROI tracking unit 101, an ROI determination unit 104, and a determination record information storage unit 105.

The ROI tracking unit 101 detects and tracks the ROI from the input image signal D12 by applying, for example, a face detection algorithm, and updates the information representing the position and size of the detected ROI, the ROI identifier, and the like by the tracking. Generate initial information D01. The ROI tracking unit 101 supplies the ROI initial information D01 to the ROI determination unit 104. The ROI identifier is assigned by the ROI tracking unit 101 to identify one or more ROIs detected in the picture, and the same ROI is given to the same ROI over pictures having different capture times. An identifier is attached. For example, when the ROI tracking unit 101 assigns the ROI identifier "I" to the ROI indicating the face area of a certain person, the ROI tracking unit 101 indicates the face area of the person even if the person is moving in the picture at the next time. The ROI shall continue to be given the ROI identifier "I". In the present proposal, the term tracking is used in the sense that the ROI to which the ROI identifier is assigned is tracked over time. In short, each time the ROI tracking unit 101 detects a new undetected ROI from the input image signal D12, the ROI tracking unit 101 assigns an ROI identifier that identifies the ROI in association with the ROI. In the above example, the ROI tracking unit 101 is described so as to track the ROI using the input image signal D12, but the ROI may be tracked by a different means. For example, in addition to using the face detection algorithm described above, a method of tracking the ROI using a user interface that manually specifies the area of the ROI, or using an image taken with an infrared camera or an image taken with a depth sensor. But it doesn't matter. In this case, the input image signal D12 is not input to the ROI tracking unit 101, but a signal related to the image taken by the infrared camera or the image taken by the depth sensor is input.

Based on the determination record information D05, the ROI determination unit 104 determines whether or not the ROI is encoded by the image encoding unit U2 in the subsequent stage for each ROI indicated by the ROI initial information D01 with ROI quality. Here, when the ROI determination unit 104 determines that the coding is performed with the ROI quality, the ROI determination unit 104 generates the information D04 that represents the information prompting the coding with the ROI quality in association with the ROI. On the other hand, when it is determined that the coding is not performed with the ROI quality, the ROI determination unit 104 generates the ROI information D04 that represents the information prompting the coding with a low quality lower than the ROI quality in association with the ROI. .. The ROI determination unit 104 supplies the ROI information D04 to the determination record information storage unit 105 and the image coding unit U2.

The determination record information storage unit 105 accumulates the ROI information D04 and supplies the accumulated information as the determination record information D05 to the ROI determination unit 104.

As shown in FIG. 1, the image coding unit U2 includes a filter unit 406, a compression unit 407, and a bitstream transmission unit 408.

The filter unit 406 receives the input image signal D12 and the ROI information D04, and among the series of pixel values represented by the input image signal D12, for the pixel values classified in the background region by the ROI information D04. For example, by performing a convolution process with a Gaussian filter or the like, a filter image signal D06 in which a high frequency component is suppressed is obtained.

The compression unit 407 transmits the filter image signal D06 to JPEG (Joint Photographic Experts Group) or H.I. 264 / MPEG (Moving Picture Experts Group) -4 AVC (Advanced Video Coding), or H.A. Video compression data D07 compressed using an image coding method such as 265 / MPEG-H HEVC (High Efficiency Video Coding) is generated, and this is supplied to the bitstream transmission unit 408.

The bitstream transmission unit 408 generates a bitstream signal D08 in which the ROI information D04 and the video compressed data D07 are multiplexed.

Hereinafter, the internal operation of the ROI detection unit U1 shown in FIG. 1 will be specifically described with reference to the flowcharts shown in FIGS. 2 and 3.

First, the ROI tracking unit 101 detects and tracks the ROI from the input image signal D12 to acquire information representing the position and size of the ROI, the ROI identifier, and the like, and generates this as the ROI initial information D01 (step P10). ). The ROI has, for example, a face region, and detection of the face region can be realized, for example, by performing identification using a Haar-like feature amount for each region.

Next, the ROI determination unit 104 selects one ROI identifier to be subjected to determination processing from the ROI initial information D01, and stores the selected ROI identifier as the ROI identifier X in the built-in register (step P11).

Next, the ROI determination unit 104 determines whether or not to encode the ROI indicated by the ROI identifier X with ROI quality based on the determination record information D05 (step P12). Here, the ROI determination unit 104 determines based on the determination record information D05 whether or not the ROI indicated by the ROI identifier X has been determined to be encoded with the ROI quality before the present time, and the ROI has already been determined. For ROIs that have been determined to be encoded by quality, it is determined that they are not encoded by ROI quality, and in other cases, it is determined that they are encoded by ROI quality.

Next, when the ROI determination unit 104 determines that the ROI indicated by the ROI identifier X is encoded by the ROI quality, the process proceeds to the execution of the following step P14, while the ROI indicated by the ROI identifier X is encoded by the ROI quality. When it is determined that the conversion does not occur, the process proceeds to the execution of the following step P15 (step P13).

In step P14, the ROI determination unit 104 generates ROI information D04 that promotes coding with a low quality lower than the ROI quality for the ROI indicated by the ROI identifier X. On the other hand, in step P15, the ROI determination unit 104 generates ROI information D04 that promotes coding with ROI quality for the ROI indicated by the ROI identifier X.

After executing step P14 or P15, the ROI determination unit 104 determines whether or not there is an ROI identifier that has not yet been selected as the target of the determination process from the ROI initial information D01 (step P16).

When it is determined in step P16 that there is an ROI identifier that has not yet been selected, the ROI determination unit 104 selects one ROI identifier to be determined next from the unselected ROI identifiers. The selected ROI identifier is newly set as the ROI identifier X (step P17). After the execution of step P17, the ROI determination unit 104 returns to the execution of step P12 described above, and performs the operations of steps P12 to P16 described above again.

On the other hand, when it is determined in step P16 that the unselected ROI identifier does not exist, the ROI determination unit 104 supplies the ROI information D04 to the image coding unit U2 (step P18).

Then, the determination record information storage unit 105 stores the ROI information D04 as a determination record (step P19).

Therefore, thereafter, the ROI determination unit 104 performs the determination process in step P12 described above based on the past determination record recorded by the determination record information storage unit 105. The number of recorded data (recording period) of the determination recording information storage unit 105 may be limited to N pictures (N is an integer of 1 or more). In this case, after the recording period has passed, even if the code has been encoded with the ROI quality in the past, the ROI determination unit 104 determines that the code is to be encoded with the ROI quality again.

As described in detail above, in the first embodiment shown in FIG. 1, for the ROI encoded with high quality once, the number of bits is replaced with the ROI quality which uses a large number of bits thereafter. Is controlled to switch to low quality coding. As a result, the data capacity of the bitstream signal D08 can be suppressed even if the image scenes in which the screen is filled with a large number of ROIs or large ROIs are continuous in time.

FIG. 4 is a block diagram showing a configuration of a second embodiment of the image processing system S1. In the image processing system S1 shown in FIG. 4, the ROI detection unit U1a is adopted instead of the ROI detection unit U1 shown in FIG. 1, and the other configurations except that the synchronization buffer 206 is newly provided are shown in FIG. Same as shown. That is, the internal configuration and operation of the image coding unit U2 shown in FIG. 4 are the same as those of the image coding unit U2 shown in FIG.

In FIG. 4, the synchronization buffer 206 receives and buffers the input image signal D12, and then supplies a signal delayed by a predetermined time to the filter unit 406 of the image coding unit U2 as the synchronization image signal D06. The predetermined time is a time corresponding to the delay time in the read-ahead buffer 203 included in the ROI detection unit U1a. That is, the synchronization buffer 206 is provided to synchronize the image between the ROI information D04 supplied by the ROI detection unit U1a to the image coding unit U2 and the input image signal D12.

The ROI detection unit U1a employs the ROI determination unit 104a instead of the ROI determination unit 104 shown in FIG. 1, and newly provides the ROI usefulness imparting unit 202 and the look-ahead buffer 203. Since the ROI tracking unit 101 and the determination record information storage unit 105 shown in FIG. 4 are the same as those shown in FIG. 1, the description thereof will be omitted. In the image processing system S1 shown in FIG. 4, the required size information D13 for designating the upper limit size LQ indicating the upper limit of the ROI size required for calculating the usefulness of the ROI together with the input image signal D12 described above. Receive.

The ROI usefulness assigning unit 202 obtains the usefulness for each ROI while referring to the required size information D13, generates the ROI secondary information D02 associated with each ROI and imparts the usefulness, and generates a look-ahead buffer. Supply to 203.

The look-ahead buffer 203 buffers the ROI secondary information D02 by a predetermined number of pictures, and generates the ROI determination target information D03A and the ROI look-ahead information D03B based on the buffered ROI secondary information D02 to generate the ROI. It is supplied to the determination unit 104a.

Based on the determination record information D05 and the ROI read-ahead information D03B, the ROI determination unit 104a encodes the ROI for each ROI included in the ROI determination target information D03A with ROI quality by the image encoding unit U2 in the subsequent stage. Determine whether or not to allow. Here, when the ROI determination unit 104a determines that the coding is performed with the ROI quality, the ROI determination unit 104a generates the information D04 representing the information prompting the coding with the ROI quality in association with the ROI. On the other hand, when it is determined that the coding is not performed with the ROI quality, the ROI determination unit 104a generates information D04 representing information for promoting coding with a low quality lower than the ROI quality in association with the ROI.

In this embodiment, the ROI usefulness imparting unit 202 shows a configuration example when the required size information D13 is used, but the ROI usefulness imparting unit 202 does not consider the required size information D13. When calculating the usefulness, the required size information D13 becomes unnecessary.

Hereinafter, the operation of the ROI detection unit U1a shown in FIG. 4 will be specifically described with reference to the flowcharts shown in FIGS. 5 and 6.

First, the ROI tracking unit 101 detects and tracks the ROI from the input image signal D12 to acquire information representing the position, size, posture, ROI identifier, etc. of the ROI, and outputs this as the ROI initial information D01. (Step P10). The ROI initial information D01 includes information necessary for calculating the usefulness performed by the ROI usefulness assigning unit 202, which will be described later.

Next, the ROI usefulness assigning unit 202 calculates the usefulness of the ROI for each ROI identifier based on the required size information D13 and the information indicating the size and posture of the ROI included in the ROI initial information D01, and this usefulness is obtained. The ROI initial information D01 plus the information indicating the degree is generated as the ROI secondary information D02 (step P21).

As the calculation of the usefulness U, for example, the following calculation methods 1 to 3 are used.
[Calculation method 1]
As shown below, the usefulness U is a function f of the size L of ROI (L is a positive real number).

U = f (L)
As the size L of the ROI, for example, one of the following six types is used.

L = H
L = W
L = min (H, W)
L = max (H, W)
L = H × W
L = H + W
H: Number of pixels in the vertical direction (vertical direction) of the screen
W: Number of pixels in the horizontal direction (horizontal direction) of the screen Here, the function f is expressed by, for example, the following mathematical formula.

f (L) = α ₁ × L + β ₁
α ₁ , β ₁ : Predetermined constant Further, any non-linear function may be adopted as the function f. For example, a function f having an arbitrary shape can be defined by using a look-up table showing the correspondence between the size L and the usefulness U.

At this time, when the image processing system S1 targets the surveillance image captured by the surveillance camera, it is considered that the larger the ROI is, the more useful it is. Therefore, as the function f, a function in which the usefulness U increases as the size L of the ROI increases is adopted.

Further, on the decoding side that decodes the bitstream signal D08 output from the image processing system S1, if it is assumed that post-processing such as face recognition or recognition is performed, the size of the image required for post-processing is determined in advance. May be. For example, assuming that an authentication program that can authenticate a face image of the upper limit size LQ is executed as post-processing, an ROI whose own size is larger than the upper limit size LQ only causes an increase in the amount of data, and the necessity is necessary. Low.

In such a case, as the function f, for example, as shown in FIG. 7, when the size L of the ROI is less than the upper limit size LQ, the usefulness U becomes larger as the size L is larger, and when the size L of the ROI is greater than or equal to the upper limit size LQ. The one in which the usefulness U is constant with the constant Q is adopted. Further, as the function f, as shown in FIG. 8 or 9, when the size L of the ROI is less than the upper limit size LQ, the usefulness U becomes larger as the size L is larger, and when the size L of the ROI is the upper limit size LQ. When the usefulness U is a QM larger than the constant Q and the size L of the ROI is larger than the upper limit size LQ, the usefulness U decreases as the size L increases. When the function f shown in FIG. 8 is adopted, the usefulness U decreases as the size L of the ROI is larger than the upper limit size LQ, but the value does not fall below the constant Q. On the other hand, when the function f shown in FIG. 9 is adopted, the usefulness U decreases as the size L of the ROI is larger than the upper limit size LQ, and when the size L exceeds LQm, the usefulness U sets a constant Q. Below.

Although the linear function is adopted in the function f shown in FIG. 7 or 8, any non-linear function that can achieve the same purpose may be adopted. In short, for example, it may be a function that changes from an increasing function to a decreasing function or a constant function at the upper limit size LQ.

Here, the upper limit size LQ is specified by the required size information D13 as described above.
[Calculation method 2]
As shown below, the usefulness U is a function g of the posture parameter Q that expresses the posture of the ROI as a numerical value. The posture parameter Q represents, for example, the deviation angle of the actual ROI in the three axial directions when the front surface of the ROI (for example, a human face) is set to the minimum angle of 0, that is, pitch, yaw, or roll.

U = g (Q)
As the posture parameter Q of the ROI, for example, one of the following seven types is used.

Q = P
Q = Y
Q = R
Q = min (P, Y, R)
Q = max (P, Y, R)
Q = P × Y × R
Q = P + Y + R
P: Pitch (degree)
Y: Yaw (degree)
R: Roll (degree)
Here, the function g is expressed by, for example, the following mathematical formula.

g (Q) = (−α ₂ ) × Q + β ₂
α ₂ , β ₂ : Predetermined constant Further, any non-linear function may be adopted as the function g. For example, a function g having an arbitrary shape can be defined by using a look-up table showing the correspondence between the posture parameter Q and the usefulness U.

At this time, when the image processing system S1 targets the surveillance image taken by the surveillance camera, it is considered that the larger the ROI pitch, yaw or roll, that is, the larger the deviation from the front, the lower the usefulness. , A decreasing function is adopted in which the function g becomes smaller as the attitude parameter Q becomes larger.
[Calculation method 3]
The usefulness U is obtained by combining the above-mentioned function f and function g based on the following equation.

U = h [f (L), g (Q)]
As the function h, for example, h [f (L), g (Q)] = α ₃ × f (L) + β ₃ × g (Q)
α ₃ , β ₃ : Predetermined constant or
h [f (L), g (Q)] = α ₃ × f (L) × β ₃ × g (Q)
Is adopted.

Further, as the function h, any non-linear function may be adopted.

At this time, when the image processing system S1 targets the surveillance image taken by the surveillance camera, the larger the f (L) and g (Q), the higher the usefulness, so the value obtained by f (L). If g (Q) is the same, a function is adopted in which the usefulness U increases as g (Q) increases. Further, if the values obtained by g (Q) are the same, a function in which the usefulness U increases as f (L) increases is adopted.

When the calculation of the usefulness U is completed in step P21, the read-ahead buffer 203 then accumulates a predetermined amount of ROI secondary information D02, and from the accumulated ROI secondary information D02, the ROI determination target information D03A and ROI The read-ahead information D03B is generated and output (step P22).

The operation of generating the ROI determination target information D03A and the ROI read-ahead information D03B performed by the look-ahead buffer 203 in step P22 will be described below with reference to the operation conceptual diagram shown in FIG.

The read-ahead buffer 203 operates as a queue as a queue of, for example, a FIFO (First In First Out), and when new data is enqueued, the oldest data is dequeued. The read-ahead buffer 203 stores ROI secondary information D02 only for predetermined picture data pieces (for example, data 1 to 5 for 5 pictures in FIG. 10), and the oldest dequeued data piece is the ROI determination target. It is generated as information D03A, and the other data pieces in the buffer are generated as ROI look-ahead information D03B. At this time, when viewed from the ROI determination target information D03A, the ROI look-ahead information D03B corresponds to future information. The sequence of pictures constituting the moving image is grouped in units of a plurality of pictures in advance, and the information to be output as the ROI pre-reading information D03B is the information of the pictures belonging to the same group as the pictures corresponding to the ROI determination target information D03A. It may be limited to.

When the above-mentioned ROI determination target information D03A and ROI read-ahead information D03B are generated in step P22, the ROI determination unit 104a next selects one ROI identifier to be processed from the ROI determination target information D03A. Let the selected ROI identifier be the ROI identifier X (step P11a).

Next, the ROI determination unit 104a determines whether or not to encode the ROI indicated by the ROI identifier X with ROI quality based on the ROI look-ahead information D03B and the determination record information D05 (step P12a).

As the determination method performed in step P12a, for example, there are the following determination methods 1 to 4. [Judgment method 1]
When the usefulness of the ROI identifier X included in the ROI look-ahead information D03B is higher than the usefulness of the ROI identifier X included in the ROI determination target information D03A, the ROI pointed to by the ROI identifier X is encoded with the ROI quality. Judge not to. Otherwise, it is determined to be encoded with ROI quality. When the determination method 1 is adopted, the determination record information storage unit 105 and the determination record information storage unit 105 shown in FIG. 4 are unnecessary.
[Judgment method 2]
If the ROI identifier X included in the ROI look-ahead information D03B is more useful than the ROI identifier X included in the ROI determination target information D03A, the ROI pointed to by the ROI identifier X must be encoded with ROI quality. judge. However, even in other cases, it is determined whether or not the ROI indicated by the ROI identifier X has been determined to be encoded with the ROI quality in the past based on the determination record information D05, and the ROI is encoded with the ROI quality in the past. It is determined that the ROI that has been determined is not encoded by the ROI quality. Otherwise, it is determined to be encoded with ROI quality.
[Judgment method 3]
If the ROI identifier X included in the ROI look-ahead information D03B is more useful than the ROI identifier X included in the ROI determination target information D03A, the ROI pointed to by the ROI identifier X must be encoded with ROI quality. judge. However, even in other cases, it is determined whether or not the ROI indicated by the ROI identifier X has been determined to be encoded with the ROI quality in the past based on the determination record information D05, and the ROI is encoded with the ROI quality in the past. When the usefulness of the ROI identifier X included in the ROI determination target information D03A is lower than the usefulness when it is determined to be encoded with the ROI quality in the past, the ROI is encoded with the ROI quality. Judge not to. In other cases, it is determined that the code is encoded with ROI quality. When the determination method 3 is adopted, the determination recording unit 105 also accumulates the usefulness when the determination is performed as a part of the determination record, and outputs it as the determination record information D05.
[Judgment method 4]
Combine with any of the determination methods 1 to 3 described above. For example, even if the determination methods 1 to 3 satisfy the condition that the ROI is not encoded by the ROI quality, the ROI pointed to by the ROI identifier X first appears in the picture, or after it is determined that the ROI is encoded by the ROI quality. When the time corresponding to a predetermined number of consecutive pictures has elapsed, it is determined that the coding is performed with ROI quality. When the determination method 4 is adopted, the determination record information storage unit 105 shown in FIG. 4 also stores time information indicating how many pictures have elapsed from the time when the ROI determination unit 104a determines that the coding is performed with the ROI quality. do.

When the determination as to whether or not to encode the ROI with the ROI quality is completed in step P12a, the ROI determination unit 104a executes step P14 when determining that the ROI indicated by the ROI identifier X is encoded with the ROI quality. On the other hand, when it is determined that the ROI indicated by the ROI identifier X is not encoded by the ROI quality, the process proceeds to the execution of step P15 (step P13).

The operations performed in steps P14 to P18 shown in FIG. 6 are the same as those shown in FIG. 3, except that the ROI determination unit 104a executes this operation instead of the ROI determination unit 104. Further, the operation performed in step P19 shown in FIG. 6 is the same as that in step P19 shown in FIG. Therefore, the description of the operations of steps P14 to P19 shown in FIG. 6 will be omitted.

As described in detail above, in the second embodiment shown in FIG. 4, the usefulness of the ROI is calculated, and whether or not to encode with high quality based on the usefulness is selected, thereby performing a bit stream. While suppressing the data capacity of the signal D08, it is possible to improve the accuracy of monitoring and post-processing authentication and recognition processing.

FIG. 11 is a block diagram showing a configuration of a third embodiment of the image processing system S1. In the image processing system S1 shown in FIG. 11, the ROI detection unit U1b is adopted instead of the ROI detection unit U1a shown in FIG. 4, and the other configurations except that the code amount monitoring unit 310 is newly provided are shown in FIG. It is the same as that shown in 4. Further, in the ROI detection unit U1b, the read-ahead buffer 203a and the RIO determination unit 104b are adopted instead of the read-ahead buffer 203 and the RIO determination unit 104a, and the other configurations except that the mode determination unit 311 is newly added are different. It is the same as that shown in FIG. Therefore, the image processing system S1 shown in FIG. 11 will be described below focusing on the difference from the configuration shown in FIG.

The code amount monitoring unit 310 receives the bitstream signal D08, monitors the actual code amount by detecting the length of the bitstream, and determines the mode of the ROI detection unit U1b for the measured code amount D10 indicating the code amount. It is supplied to the unit 311.

The mode determination unit 311 receives the actually measured code amount D10 and the set code amount information D14 indicating the code amount for setting the code amount. The mode determination unit 311 determines a normal mode or a suppression mode as an operation mode for operating the ROI detection unit U1b based on the actually measured code amount D10 and the set code amount information D14, and ROI the mode information D11 indicating the operation mode. It is supplied to the determination unit 104b.

The read-ahead buffer 203a stores ROI secondary information D02 only for predetermined picture data pieces (for example, data 1 to 5 for 5 pictures in FIG. 10), and the oldest dequeued data piece is the ROI determination target. It is generated as information D03A and supplied to the ROI determination unit 104b.

When the mode information D11 indicates the normal mode, the ROI determination unit 104b generates ROI information D04 indicating that all ROIs indicated by the ROI determination target information D03A are encoded with ROI quality, and this is determined recording information. It is supplied to the storage unit 105 and the image coding unit U2. On the other hand, when the mode information D11 indicates the suppression mode, the ROI determination unit 104b determines each ROI included in the ROI determination target information D03A based on the determination record information D05 in the same manner as the ROI determination unit 104a. Determines whether or not to encode with. Here, when the ROI determination unit 104b determines that the coding is performed with the ROI quality, the ROI determination unit 104b generates the information D04 that represents the information prompting the coding with the ROI quality in association with the ROI. On the other hand, when it is determined that the coding is not performed with the ROI quality, the ROI determination unit 104b generates information D04 representing information for promoting coding with a low quality lower than the ROI quality in association with the ROI. In addition, with respect to the second embodiment shown in FIG. 4, only the configurations (104b, 300, 311) newly added in the third embodiment shown in FIG. 11 are shown in FIG. It may be added to the configuration.

Hereinafter, the operations performed by the ROI detection unit U1b and the code amount monitoring unit 310 shown in FIG. 11 will be specifically described with reference to the flowcharts shown in FIGS. 12 and 13.

First, the code amount monitoring unit 310 monitors the code amount of the bitstream based on the bitstream signal D08 output from the image coding unit U2, generates the measured code amount D10 indicating this code amount, and generates the ROI detection unit U1b. (Step P31).

The code amount monitoring unit 310 acquires the actually measured code amount D10 by, for example, the following code amount calculation method 1 or 2.
[Code amount calculation method 1]
As shown in the following formula, the value obtained by adding the lengths of the bitstreams corresponding to M consecutive pictures (M is an integer of 2 or more) in the bitstream signal D08, or corresponding to M consecutive pictures. The average value of the lengths of the bitstreams to be generated, or the average value thereof, multiplied by a constant using the constant C is calculated as the code amount A.

Ｖ_i：Ｍ個のピクチャのうちのｉ番目のピクチャのビットストリームの長さ
Ｃ：定数
すなわち、符号量算出方法１では、部分ピクチャベースで符号量を算出する。
［符号量算出方法２］
以下の数式に示されるように、符号化した全ピクチャ数をＫ（Ｋは２以上の整数）個とした場合に、Ｋ個のピクチャに夫々対応するビットストリームの長さを加算した値、又はＫ個のピクチャに夫々対応するビットストリームの長さの平均値、および平均値を、定数Ｃを使って定数倍した値を符号量Ｂとして算出する。

V _i : Bitstream length of the i-th picture out of M pictures
C: Constant That is, in the code amount calculation method 1, the code amount is calculated on a partial picture basis.
[Code amount calculation method 2]
As shown in the following formula, when the total number of encoded pictures is K (K is an integer of 2 or more), the value obtained by adding the lengths of the bitstreams corresponding to each of the K pictures, or The average value and the average value of the bitstream lengths corresponding to the K pictures are multiplied by a constant using the constant C, and the value is calculated as the code amount B.

Ｖ_i：Ｋ個のピクチャのうちのｉ番目のピクチャのビットストリームの長さ
Ｃ：定数
すなわち、符号量算出方法２では、総ピクチャベースで符号量を算出する。

V _i : Bitstream length of the i-th picture out of K pictures
C: Constant That is, in the code amount calculation method 2, the code amount is calculated on a total picture basis.

The code amount monitoring unit 310 supplies the mode determination unit 311 with an actually measured code amount D10 representing one or both of the above code amounts A and B. Here, how to calculate the actually measured code amount D10 depends on the mode determination method in the mode determination unit 311 as described later.

When the calculation of the code amount is completed in step P31, steps P10, P21, and P22 are continuously executed in order. Since the operation of the example in steps P10, P21, and P22 is the same as that shown in FIG. 5, the description of the operation in each of steps P10, P21, and P22 will be omitted.

Here, when step P22 is completed, the mode determination unit 311 determines one of the normal mode and the suppression mode as the operation mode by comparing the actually measured code amount D10 and the set code amount information D14, and determines the operation mode. Mode information D11 representing the operation mode is generated (step P32).

The operation mode is determined by, for example, the following operation mode determination methods 1 to 3.
[Operation mode determination method 1]
If the measured code amount D10 is larger than the set code amount information D14, it is determined to be the suppression mode, and if it is not, it is determined to be the normal mode.
[Operation mode determination method 2]
One of the normal mode and the suppression mode is set as the initial mode, and when the measured code amount D10 is larger than the set code amount information D14, the mode shifts to the suppression mode, and the measured code amount D10 is the set code amount. When the value is smaller than the value obtained by subtracting a certain amount including zero from the information D14, the mode shifts to the normal mode, and in other cases, the mode is left unchanged.
[Operation mode determination method 3]
One of the normal mode and the suppression mode is set as the initial operation mode, and the code amount A calculated on the partial picture base in the measured code amount D10 is the set code amount information corresponding to the partial picture base. If it is larger than D14, the mode shifts to the suppression mode. Further, among the measured code amounts D10, the partial picture-based code amount A is smaller than the value obtained by subtracting a certain amount including zero from the set code amount information D14 corresponding to the partial picture base, and among the measured code amounts D10. When the code amount B of the total picture base is smaller than the value obtained by subtracting a certain amount including zero from the set code amount information D14 corresponding to the total picture base, the mode shifts to the normal mode. Otherwise, leave the mode unchanged.

It should be noted that, for example, the transition to the suppression mode is controlled by interlocking with other mode control mechanisms such as rate control that attempts to keep the bit rate constant by monitoring the bit rate and controlling the video quality parameter. May be good. For example, H. When interlocking with the rate control algorithm of the encoder conforming to 264 / MPEG-4 AVC, the maximum value (the value with the smallest code amount) of the quantization parameter defined in the standard is "51". Therefore, the transition to the suppression mode is controlled by adding the condition for executing the suppression mode to the rate control algorithm as the quantization parameter "52". In this case, the normal mode is when the quantization parameter is from "0" to "51". The mode determination of the mode determination unit 311 may be determined not for each picture but for each predetermined number of pictures.

When the generation of the mode information D11 is completed in step P32, the ROI determination unit 104b determines whether or not the mode information D11 indicates the suppression mode, and if it is determined that the mode information D11 indicates the suppression mode, the process proceeds to the execution of step S12. On the other hand, if it is determined that the suppression mode is not shown, the process proceeds to the execution of the following step P34 (step P33). Since the operations of steps P12 to P19 performed in step S12 and subsequent steps are the same as those shown in FIG. 3, the description of the operations in each of these steps P12 to P19 will be omitted.

In step P34, the ROI determination unit 104b generates ROI information D04 that promotes coding of all ROIs indicated by ROI determination target information D03A with ROI quality. After the execution of step P34, the ROI determination unit 104b shifts to the execution of step P18.

In the flowcharts shown in FIGS. 12 and 13, step P31 is executed first, but it is not always necessary to execute step P31 first if it is before step P32.

As described in detail, in the third embodiment shown in FIG. 11, the mode is controlled using the set code amount information D14 as an index, and when there is a margin in the code amount, normal bit allocation is performed ( (Normal mode), the code amount is suppressed by using the methods shown in the first embodiment and the second embodiment only when there is no margin in the code amount (suppression mode). As a result, it is possible to improve the accuracy of monitoring and post-processing authentication and recognition processing while preventing the code amount from being exceeded, and as long as there is a margin in the code amount, a large amount of ROI information can be transmitted and stored. , Effective in preventing deterioration of monitoring ability.

In all the embodiments, the ROI determination unit (104, 104a, 104b) determines whether or not to encode each ROI included in the input image signal (D12) with ROI quality, and generates ROI information D04. However, the determination that the coding is not performed with ROI quality does not necessarily mean that the coding is performed with the same bit allocation as the background region. Therefore, the image coding unit U2 sets the ROI region determined to be encoded by the ROI quality, the ROI region determined not to be encoded by the ROI quality, and the background region (region other than the ROI), respectively. It may be encoded with different qualities, and even in this case, a certain effect can be expected.

In short, the image processing system (S1) that encodes the input image signal and outputs it as a bitstream signal may include the following region of interest determination unit and image coding unit. The attention area determination unit (104, 104a, 104b) determines whether or not to encode the attention area attention area designated as a desired area with a predetermined quality (ROI quality) (P13), and encodes with the predetermined quality. If it is determined that the information is encoded with a predetermined quality, the information prompting the coding with a predetermined quality is associated with the region of interest, and if it is determined that the information is not encoded with the predetermined quality, the information prompting the coding with a lower quality lower than the predetermined quality is associated with the region of interest. The area of interest information (D04) represented by The image coding unit (U2) outputs a bitstream signal (D08) including a signal in which the region of interest in the input image signal is encoded with a predetermined quality or low quality according to the region of interest information.

101 ROI tracking unit 104 ROI determination unit 406 Filter unit 407 Compression unit 408 Bitstream transmission unit S1 Image processing system U1 ROI detection unit U2 Image coding unit

Claims (28)

An image processing system that encodes an input image signal and outputs it as a bitstream signal.
In the image based on the input image signal, it is determined whether or not the region of interest designated as a desired region is encoded with a predetermined quality, and when it is determined that the region of interest is encoded with the predetermined quality, the predetermined quality is used. When it is determined that the information for prompting coding is not encoded with the predetermined quality, the information for promoting encoding with a lower quality lower than the predetermined quality is shown in association with the attention region. The area of interest determination unit to be generated and
An image coding unit that outputs the bitstream signal including a signal in which the region of interest in the input image signal is encoded with the predetermined quality or the low quality according to the region of interest information.
An area of interest tracking unit that detects an area in which a predetermined object is displayed in an image based on the input image signal as the area of interest, updates the detected information about the area of interest by tracking, and generates initial information of the area of interest. When,
The area of interest usefulness assigning unit that obtains the usefulness of the area of interest for each of the areas of interest indicated by the initial information of the area of interest and generates secondary information of the area of interest in which the degree of usefulness is included in the initial information of the area of interest. When,
The attention area secondary information is buffered by a predetermined picture, and the portion of the buffered attention area secondary information corresponding to the first picture is output as the attention area determination target information, and the first picture is output. Includes a read-ahead buffer that outputs the portion corresponding to the picture group following the to as the read-ahead information of the region of interest.
By referring to the attention area look-ahead information, the attention area determination unit can determine the usefulness indicated by the attention area look-ahead information for each of the attention areas indicated by the attention area determination target information. The image coding unit determines that the attention region having a higher usefulness than the attention region determination target information is not encoded with the predetermined quality, and is indicated by the attention region look-ahead information. An image characterized in that the image coding unit determines that coding with the predetermined quality is performed on the attention region whose usefulness is equal to or less than the usefulness indicated by the attention region determination target information. Processing system. The image processing system according to claim 1, wherein the attention region determination unit determines whether or not to encode the attention region indicated by the attention region initial information with the predetermined quality. A determination record information storage unit that accumulates the attention area information generated by the attention area determination unit and supplies the accumulated information as determination record information to the attention area determination unit is included.
The featured region determination unit is characterized in that it determines that the region of interest that is determined to be encoded with the predetermined quality before the present time is not encoded with the predetermined quality based on the determination record information. The image processing system according to claim 2. Each time the attention area tracking unit detects an undetected attention area from the input image signal, the attention area identifier indicating the detected attention area is assigned in association with the attention area.
By referring to the determination record information, the attention area determination unit determines whether or not the attention area indicated by the attention area identifier has been determined to be encoded with the predetermined quality in the past, and in the past It is determined that the region of interest that has been determined to be encoded with the predetermined quality is not encoded with the predetermined quality, and the other regions of interest are determined to be encoded with the predetermined quality. The image processing system according to claim 3, wherein the image processing system is characterized. The image processing system according to claim 3 or 4, wherein the determination record information storage unit limits the number of recorded data of the determination record information to a predetermined finite number of pictures. It is characterized by including a synchronization buffer that buffers the input image signal, delays it for a predetermined period, generates it as a synchronization image signal, and supplies the synchronization image signal to the image coding unit in place of the input image signal. The image processing system according to any one of claims 1 to 5. When the usefulness is U and the size of the attention area is L, the attention area usefulness imparting unit is used.
U = f (L) = α ₁ × L + β ₁
α ₁ , β ₁ : The image processing system according to claim 6, wherein the usefulness is obtained by a function f (L) represented by a predetermined constant. The image processing system according to claim 7, wherein the function f (L) is an increasing function whose usefulness increases as the size of the region of interest increases. Receives the required size information that specifies the upper limit size indicating the upper limit of the size of the attention area, which is required when calculating the usefulness of the attention area.
The image processing system according to claim 7, wherein the function f (L) has a maximum value when the size of the region of interest is the upper limit size. The function f (L) is an increasing function in which the usefulness increases according to the size of the attention region when the size of the attention region is smaller than the upper limit size, and the size of the attention region is the upper limit size. The image processing system according to claim 9, wherein the function is such that the usefulness becomes constant when the value is larger than. The function f (L) is an increasing function in which the usefulness increases according to the size of the attention region when the size of the attention region is smaller than the upper limit size, and the size of the attention region is the upper limit. The image processing system according to claim 7, wherein the image processing system has a decreasing function in which the usefulness decreases according to the size of the region of interest when the size is larger than the size. When the usefulness is U, and the posture parameter including the pitch, yaw, or roll representing the posture of the object represented by the attention region is Q, the attention area usefulness assigning unit is used.
U = g (Q) = (-α ₂ ) × Q + β ₂
α ₂ , β ₂ : The image processing system according to claim 6, wherein the usefulness is obtained by a function g (Q) represented by a predetermined constant. The attitude parameter is minimized when the object is facing the front, and increases as the deviation angle from the front increases.
The image processing system according to claim 12, wherein the function g (Q) is a decreasing function whose usefulness decreases as the posture parameter increases. The area of interest usefulness imparting unit
A function f (L) in which the size of the attention region is a variable L, and a function g (Q) in which a posture parameter including a pitch, yaw or roll representing the posture of the object represented by the attention region is a variable Q. Using,
U = h [f (L), g (Q)]
U: Usefulness
f (L) = α ₁ × L + β ₁
α ₁ , β ₁ : Predetermined constant
g (Q) = (−α ₂ ) × Q + β ₂
α ₂ , β ₂ : The image processing system according to claim 6, wherein the usefulness is obtained by a function h [f (L), g (Q)] represented by a predetermined constant. If the values of the functions f (L) are the same, the higher the value of the function g (Q), the higher the usefulness of the function h [f (L), g (Q)]. The image processing system according to claim 14, wherein if the functions g (Q) are the same, the larger the value of the function f (L), the higher the usefulness. The read-ahead buffer operates as a queue of FIFO (First In First Out), and when the last data piece in the series of data pieces representing the region of interest secondary information is enqueued, the first data piece is dequeued. Is a buffer that is
Any one of claims 6 to 15, characterized in that the first data piece to be dequeued is output as the attention area determination target information, and the other data pieces are output as the attention area look-ahead information. The image processing system described in. The look-ahead buffer groups and buffers a series of pictures constituting a moving image for each of a plurality of pictures, and the information output as the attention area look-ahead information is a picture corresponding to the attention area determination target information. The image processing system according to claim 16, wherein the image processing system belongs to the same group. The attention area determination unit represents the attention area to be determined whether or not to encode with the predetermined quality by the attention area identifier X.
The attention included in the attention area pre-reading information and indicated by the attention area identifier X rather than the usefulness of the attention area indicated by the attention area identifier X and included in the attention area determination target information. When the usefulness of the region is higher, it is determined that the region of interest indicated by the region of interest identifier X is not encoded with the predetermined quality, and in other cases, the region is encoded with the predetermined quality. The image processing system according to any one of claims 6 to 17, wherein the image processing system is determined to be so. The attention area determination unit represents the attention area to be determined whether or not to encode with the predetermined quality by the attention area identifier X.
The attention included in the attention area pre-reading information and indicated by the attention area identifier X rather than the usefulness of the attention area indicated by the attention area identifier X and included in the attention area determination target information. When the usefulness of the region is higher, it is determined that the region of interest indicated by the region of interest identifier X is not encoded with the predetermined quality, and even in other cases, based on the determination record information. It is determined whether or not the attention area indicated by the attention area identifier X has been determined to be encoded with the predetermined quality in the past, and the attention area has been determined to be encoded with the predetermined quality in the past. The image processing system according to any one of claims 3 to 5, wherein the image processing system is determined not to be encoded with the predetermined quality, and is determined to be encoded with the predetermined quality in other cases. The attention area determination unit represents the attention area to be determined whether or not to encode with the predetermined quality by the attention area identifier X.
The attention included in the attention area pre-reading information and indicated by the attention area identifier X rather than the usefulness of the attention area indicated by the attention area identifier X and included in the attention area determination target information. When the usefulness of the region is higher, it is determined that the region of interest indicated by the region of interest identifier X is not encoded with the predetermined quality, and even in other cases, based on the determination record information. When it is determined whether or not the region of interest indicated by the region of interest identifier X has been determined to be encoded with the predetermined quality in the past, and it is determined that the region of interest is encoded with the predetermined quality in the past. When the usefulness of the attention area identifier X included in the attention area determination target information is lower than the usefulness when encoded with the predetermined quality in the past, the predetermined quality is obtained for the attention area. It is determined that the coding is not performed with, and in other cases, it is determined that the coding is performed with the predetermined quality.
3. The image processing system according to any one of. Even when the attention area determination unit determines that the attention area indicated by the attention area identifier X is not encoded with the predetermined quality, when the attention area indicated by the attention area identifier X first appears as a picture, Alternatively, after a predetermined number of pictures have elapsed from the time when it is determined that the coding is performed with the predetermined quality, it is determined that the coding is performed with the predetermined quality.
The image processing system according to claim 20, wherein the determination record information storage unit also stores time information indicating an elapsed time from a time when it is determined to be encoded with the predetermined quality. A code amount monitoring unit that monitors the code amount based on the bitstream length of the bitstream signal and obtains the monitored code amount as an actually measured code amount.
Upon receiving the set code amount information indicating the code amount at the time of coding as the set code amount, if the measured code amount is larger than the set code amount information, it is determined to be the suppression mode, and in other cases, it is determined to be the normal mode. Including the mode judgment unit
The attention area determination unit, while generating the attention area information when prompting the encoding in said predetermined quality operation mode shows the normal mode, when the operation mode shows the suppression mode, The image processing system according to any one of claims 1 to 21, wherein the attention region information that promotes coding at the predetermined quality or the low quality is generated based on the result of the determination. The image according to claim 22, wherein the mode determination unit determines the suppression mode if the measured code amount is larger than the set code amount, and determines the normal mode in other cases. Processing system. The mode determination unit sets one of the normal mode and the suppression mode as the initial state of the operation mode, and when the measured code amount is larger than the set code amount, shifts to the suppression mode and the actual measurement. If the code amount is smaller than the value obtained by subtracting the predetermined amount including zero from the set code amount, the operation mode is shifted to the normal mode, and in other cases, the state of the operation mode at the present time is left unchanged. The image processing system according to claim 22. The code amount corresponding to the bitstream length corresponding to a predetermined number of pictures is defined as a partial picture-based code amount, and the code amount corresponding to the bitstream length corresponding to each picture of all encoded pictures is the total picture. Use as the base code amount
The mode determination unit shifts to the suppression mode when the partial picture-based code amount of the actually measured code amount is larger than the code amount corresponding to the partial picture-based code amount of the set code amount. death,
The partial picture-based code amount of the actually measured code amount is smaller than the value obtained by subtracting a predetermined amount including zero from the code amount corresponding to the partial picture-based code amount of the set code amount and said. When the total picture-based code amount of the measured code amount is smaller than the value obtained by subtracting the predetermined amount from the code amount corresponding to the total picture-based code amount of the set code amount, the usual Go to mode and
The image processing system according to claim 22, wherein in other cases, the state of the operation mode at the present time is deferred. The image processing system according to claim 22, wherein the mode determination unit cooperates with a mode control mechanism that controls video quality parameters, and sets the suppression mode as one mode of the mode control mechanism. The image processing system according to any one of claims 22 to 26, wherein the mode determination unit performs the determination for each predetermined number of pictures. The image coding unit includes the attention region determined by the attention region determination unit to be encoded with the predetermined quality, the attention region determined not to be encoded with the predetermined quality, and a region other than the attention region. The image processing system according to any one of claims 1 to 27, wherein the image processing system is encoded with different qualities.

Images