JPH10164584A - Image processor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prevent motion compensation from becoming impossible near a boundary and to guarantee motion over the entire screen by dividing a screen into plural image areas, adjacent in a vertical direction and parallel motion compensating and decoding image information with them as units. SOLUTION: A slice detector l detects the position on the screen and slices the bit stream of compressed image information corresponding to two upper and lower image areas. Buffers 2A and 2B adjust the time, so as to be matched with the operation timing of decoders 3A and 3B and outputs the image information corresponding to the divided upper and lower image areas by FIFO (first-in first-out). The decoders 3A and 3B directly access the image information stored in memories 5A and 5B, perform the motion compensation and decode them and a connection device 6 connects the image information, corresponding to the image areas and constitutes the image information for one screen.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention relates to MPEG2 (Movi).
The present invention relates to an image processing apparatus for performing high-speed motion compensation and decoding of large-scale moving image information conforming to ng Picture Experts Group 2) and the like.

[0002]

2. Description of the Related Art As an elemental technology of digital compression processing technology of moving picture information represented by MPEG2, when decoding compressed moving picture information, a so-called "movement" in which the motion (movement) of an image is described by a vector amount. There is a technique for constructing image information of a screen at another time position from image information of a screen (frame) at a certain time position according to a "vector", and is called "motion compensation".

As a video decoder for decoding moving picture information compressed on the premise of performing motion compensation when decoding, an image processing apparatus having the configuration shown in FIG. 6 is known. I have. That is, the image processing apparatus shown in FIG. 1 performs motion-compensation decoding of image information compressed in accordance with MPEG2, and decodes the image information by using an MPEG2 decoder 3 for decoding the compressed image information. And a memory 5 such as a dynamic RAM (Dynamic Random Access Memory) for temporarily storing the decoded image information. The MPEG2 decoder 3 is embodied as an LSI (Large Scale Integrated circuit) chip or the like using a method such as a standard cell.

In the conventional image processing apparatus configured as described above, the image information of the screen at a certain time position decoded by the MPEG2 decoder 3 is temporarily stored in the memory 5. Then, an image of a certain local area on the screen at another time position is considered to be an image of a certain local area on the screen at a certain time position recorded in the memory 5, and the image of this local area is moved. The image information stored in the memory 5 is read out in accordance with the motion vector indicating the direction and the movement amount, and motion compensation is performed to construct image information of a screen at another time position. This motion compensation is sequentially performed over the entire screen using the above-mentioned “certain local area” as a unit. In the following description, the “local area” which is a processing unit on the screen in performing motion compensation is referred to as “local area”. Image block ".

[0005]

By the way, in general, M
The data amount of moving image information targeted by PEG2 etc. is JP
The scale is larger than the still image information targeted by the EG or the like. In addition, as the size of the screen increases and the number of frames per second increases, the amount of data increases significantly, and the MPE which constitutes the conventional apparatus shown in FIG.
The amount of data to be processed by the G2 decoder 3 and the memory 5 is significantly increased.

However, a standard MPEG decoder LSI
Is an NTSC (National Television) with a resolution of about 480 pixels vertically, 720 pixels horizontally, and about 30 frames per second.
sionSystem Committee) and has only the decoding processing capability for image information.
With only PEG decoder LSI, 1080 pixels vertically and 1 pixel horizontally
Large-scale image information such as HDTV (High Definition TeleVision) having 920 pixels and a resolution of about 30 frames per second cannot be decoded.

In order to decode large-scale image information of the HDTV class using a standard MPEG decoder LSI, an apparatus having a parallel decoding process as shown in FIG. Can be That is, the image processing apparatus shown in FIG. 1 divides a screen into two areas, image areas A and B, and processes two sets of MPEG2 decoders 3a and 3b for processing image information corresponding to the image areas A and B, and a memory. After the image information corresponding to the image areas A and B are processed in parallel and decoded, the image information obtained by decoding by the respective MPEG2 decoders 3a and 3b is combined by a combiner 6a. 1 constitutes one screen of decoded image information.

However, in the case of MPEG2 or the like, when performing motion compensation as described above, a memory is accessed in accordance with a motion vector to read out image information of a necessary image block. In the configuration of the decoder 3, the decoder 3 responsible for the processing of the image information of the image area A
a cannot access the memory 5b that stores the image information of the image area B. Therefore, for example, when a motion vector refers to the image information of the image block in the image area B when performing motion compensation for a certain image block belonging to the image area A, the image information specified by the motion vector is referred to. Cannot perform motion compensation,
The motion of the image near the boundary between the image areas A and B becomes unnatural.

The present invention has been made in view of such a problem, and when moving image information is divided in correspondence with a plurality of image regions on a screen and is decoded in parallel, the moving image information is divided near the boundaries of the image regions. An object of the present invention is to provide an image processing apparatus capable of performing appropriate motion compensation over the entire screen without making motion compensation impossible.

[0010]

Means for Solving the Problems The present invention has the following arrangement to achieve the above object. That is, claim 1
The image processing apparatus according to the invention described in (1), the image processing apparatus divides a screen into a plurality of vertically adjacent image areas, and performs motion compensation and decoding on the image information of the screen in parallel in units of the image areas. An information dividing unit that divides the image information in association with the plurality of image regions; a plurality of decoding units that decode each of the image information divided by the information dividing unit; and the plurality of decoding units. A plurality of storage means for storing each of the image information decoded by
Information combining means for combining each of the image information decoded by the plurality of decoding means in association with the plurality of image areas, wherein each of the plurality of storage means has a plurality of independently accessible memory spaces. And having the image information decoded by the decoding means divided and stored in the plurality of memory spaces, and each of the plurality of decoding means, when decoding the image information divided by the information dividing means, An image processing apparatus has a configuration in which any one of the plurality of storage units is accessed in units of a memory space to perform motion compensation in parallel on image information of the plurality of image areas.

The image processing apparatus according to the second aspect of the present invention provides the image processing apparatus according to the first to Nth screens which are vertically adjacent to each other.
An image processing apparatus that divides the image information of the screen by performing motion compensation in parallel with the image area divided into N image areas up to the Nth (N is an integer of 2 or more) units, and Information dividing means for dividing the image information into first to N-th image information in association with the first to N-th image areas; and dividing the first to N-th image information into first to N-th image areas. First to N-th decoding means for respectively decoding the decoded information;
Each of the first to Nth image areas is divided into two so as to be adjacent to each other in the vertical direction, and the first to Nth small image areas are associated with the first to Nth small image areas. First to second N storage means for dividing the N decoded information into first to second N reference information and storing them, respectively;
Information combining means for combining the first to N-th decoded information in association with the first to N-th image areas, wherein the first to N-th decoding means comprises: N
In decoding each of the image information into the first to N-th decoding information, the M-th (M is an integer of 1 or more and N or less) decoding means of the first to N-th decoding means is used. Second
An image in which motion compensation is performed in parallel on the first to Nth image information by accessing any of the M + 1 storage means and referring to the 2M-2 to 2M + 1 reference information. It has a configuration of a processing device.

An image processing apparatus according to a third aspect of the present invention is an image processing apparatus that performs motion compensation on image information and decodes the image information, wherein the image information is divided into luminance information and color difference information. Means for decoding the luminance information and the chrominance information into luminance decoding information and chrominance decoding information, respectively;
And second decoding means, first and second storage means for storing the luminance decoding information and the chrominance decoding information as luminance reference information and chrominance reference information, respectively, and the luminance decoding information and the chrominance decoding information. Information combining means for combining, the first and second decoding means, when decoding the luminance information and the chrominance information into the luminance decoding information and the chrominance decoding information, respectively, the first and second decoding By accessing the storage means and referring to the luminance reference information and the chrominance reference information stored in the first and second storage means, respectively, the motion compensation is performed on the luminance information and the chrominance information in parallel. And a configuration of an image processing apparatus characterized by performing the following.

Further, an image processing apparatus according to a fourth aspect of the present invention is an image processing apparatus for performing motion compensation on image information and decoding the image information, wherein the image information is first to Nth based on color components. Information dividing means for dividing the first to N-th color information into first to N-th decoded information, respectively; and the first to N-th color information. First to N-th storage means for storing decrypted information as first to N-th reference information, respectively;
Information combining means for combining the decoded information of
To N-th decoding means, when decoding the first to N-th color information into the first to N-th decoding information,
By accessing the first to Nth storage means,
By referring to the first to N-th reference information stored in the first to N-th storage means, respectively,
The image processing apparatus has a configuration in which motion compensation is performed in parallel for the Nth to Nth color information.

Further, according to a fifth aspect of the present invention, the image processing apparatus divides a screen into a plurality of vertically adjacent image areas, and parallelizes image information of the screen in units of the image areas. What is claimed is: 1. An image processing apparatus for performing motion compensation decoding, comprising: first information dividing means for dividing said image information into luminance information and color difference information; and luminance information or color difference information divided by said first information dividing means. A second information dividing unit that divides the information into a plurality of image areas, a plurality of decoding units that decodes the luminance information or the color difference information divided by the first and second information dividing units, A plurality of storage means for storing the luminance information or the color difference information decoded by the decoding means, and combining the luminance information or the color difference information decoded by the plurality of decoding means in association with the plurality of image areas. Information combining means, each of the plurality of storage means has a plurality of memory spaces which can be independently accessed, and stores the luminance information or the chrominance information decoded by the plurality of decoding means in the plurality of memory spaces. When decoding the luminance information or the color difference information divided by the first and second information dividing means, each of the plurality of decoding means stores the plurality of storage means in units of the memory space. And performing motion compensation on the image information of the plurality of image areas in parallel.

Further, according to a sixth aspect of the present invention, the image processing apparatus divides a screen into a plurality of vertically adjacent image areas, and parallelizes image information of the screen in units of the image areas. An image processing apparatus for decoding by performing motion compensation, comprising: a first information dividing unit that divides the image information based on a color component; and an image processing unit that divides the image information divided by the first information dividing unit into a plurality of images. A second information dividing unit that divides the image information in association with the region, a plurality of decoding units that decode the image information divided by the first and second information dividing units, and an image that is decoded by the plurality of decoding units. A plurality of storage means for storing information; and information combining means for combining image information decoded by the plurality of decoding means in association with the plurality of image areas, wherein each of the plurality of storage means is independent. It has a plurality of accessible memory spaces, divides image information decoded by the plurality of decoding units into the plurality of memory spaces, and stores the divided image information, and each of the plurality of decoding units includes the first and second decoding units. When decoding the image information divided by the information dividing unit, any one of the plurality of storage units is accessed in units of the memory space, and motion compensation is performed on the image information of the plurality of image regions in parallel. The configuration of the image processing apparatus characterized by the following.

In the image processing apparatus according to the present invention, the screen is divided into first to Nth (N is an integer of 2 or more) image areas vertically adjacent to each other. What is claimed is: 1. An image processing apparatus which divides and decodes image information of said screen by performing motion compensation in parallel with said image area as a unit, wherein said first information dividing means divides said image information into luminance information and color difference information And second information for dividing the luminance information or color difference information divided by the first information dividing means into first to Nth image information in association with the first to Nth image areas. Dividing means;
First to N-th decoding means for decoding the image information of the first to N-th decoding information, respectively, and dividing each of the first to N-th image areas into two so as to be adjacent in the vertical direction. The first to Nth decoded information is divided into first to second N reference information in association with the first to second Nth small image areas obtained by 2N storage means, and information combining means for combining the first to N-th decoding information in association with the first to N-th image areas, wherein the first to N-th decoding means , When decoding the first to N-th image information into the first to N-th decoding information, respectively, the M-th (M is an integer of 1 or more and N or less) decoding of the first to N-th decoding means. Means accessing any of the 2M-2 to 2M + 1 storage means By reference to 2M + 1 references from 2M-2, it has the configuration of an image processing apparatus and performs parallel motion compensated respectively for the image information of the N from the first.

Further, the image processing apparatus according to the invention described in claim 8 is arranged such that the screen is divided into first to N-th (N is an integer of 2 or more) image areas vertically adjacent to each other. An image processing apparatus that divides and decodes image information of the screen by performing motion compensation in parallel by using the image area as a unit, and divides the image information based on a color component. A second information dividing unit that divides the image information divided by the first information dividing unit into first to Nth image information in association with the first to Nth image areas; First to N-th decoding means for decoding the first to N-th image information into first to N-th decoding information, respectively, wherein each of the first to N-th image areas is adjacent in the vertical direction; From the first to the second N obtained by dividing into two First to second N storage means for dividing the first to N-th decoded information into first to second N reference information and storing them, respectively, in association with the small image areas up to the eyes; Information combining means for combining the N-th decoding information in association with the first to N-th image areas, wherein the first to N-th decoding means comprises the first to N-th image information. Are respectively decoded into the first to N-th decoding information, the M-th (M is an integer of 1 or more and N or less) decoding means of the first to N-th decoding means
By accessing any of the 2 to 2M + 1 storage means and referring to the 2M-2 to 2M + 1 reference information, it is possible to perform motion compensation in parallel for the first to Nth image information, respectively. It has a configuration of an image processing device as a feature.

Further, the image processing apparatus according to the ninth aspect of the present invention is characterized in that the number of screen divisions when decoding luminance information is larger than the number of screen divisions when decoding color difference information. An image processing apparatus according to any one of claims 5 and 7.

In the image processing apparatus according to the present invention, the picture is divided into image areas adjacent in the horizontal direction instead of the vertical direction and decoded. An image processing apparatus according to any one of 2, 5, 6, 7, 8, and 9.

In the image processing apparatus according to the present invention, the picture may be divided into two-dimensionally adjacent image areas and decoded in place of the vertical direction. The image processing apparatus according to any one of 2, 5, 6, 7, 8, and 9 is provided.

Hereinafter, the operation of the present invention configured as described above will be described. That is, according to the image processing apparatus according to the first aspect of the present invention, the information dividing unit divides the image information in association with each image region of the image divided in the vertical direction, and outputs each of the plurality of decoding units. However, the image information of each image area divided by the information dividing means is decoded in parallel and given to each of the plurality of storage means. Each storage unit divides the image information of one image area decoded by the decoding unit into a plurality of independently accessible memory spaces and stores them. When decoding the image information divided by the information dividing means, each decoding means accesses any of the plurality of storage means in units of memory space, and performs motion compensation on the image information of each block in parallel. To decrypt. Here, each of the plurality of memory areas of each storage means can be accessed independently. For this reason, when the “certain decoding unit” performs motion compensation on the image information of the “certain image region” and decodes the image information, even if the motion vector straddles the “other image region”, the “other image region” Without interfering with the decryption operation of
"Another storage means" for storing image information of "another image area" can be accessed, and motion compensation can be performed according to a motion vector extending over these two image areas. The information combining means combines the image information decoded by motion compensation by each of the plurality of decoding means,
Reconstruct image information.

According to the image processing apparatus of the second aspect of the present invention, the information dividing means is provided for each of the first to Nth image areas of the screen divided so as to be adjacent in the vertical direction. The image information is divided in association with the first to Nth image information.
Each of the decoding means decodes the image information of the first to Nth image areas divided by the information dividing means in parallel, and supplies the decoded information to the first to second N storage means. Here, the first to second N storage units store the image information decoded by the first to Nth decoding units from the first to Nth image regions obtained by further dividing each of the first to Nth image regions into two. The information is stored as first to second N reference information in association with the 2Nth small image area. As a result, the image information for one image area decoded by the decoding means is divided and stored in a pair of continuous odd-numbered and even-numbered storage means. Then, when each of the first to N-th decoding units decodes the image information divided by the information dividing unit, the M-th (M is an integer of 1 or more and N or less) decoding means By accessing any of the 2M + 1 storage units and referring to the 2M-2 to 2M + 1 reference information, motion compensation is performed in parallel on the first to Nth image information. The information combining means combines the first to Nth decoded information decoded by performing motion compensation by the first and second decoding means, and reconstructs image information.

Further, according to the image processing apparatus according to the third aspect of the present invention, the information dividing means divides the image information into luminance information and chrominance information, and the first and second decoding means
The luminance information and the chrominance information are decoded in parallel to the luminance decoding information and the chrominance decoding information, respectively. The first and second storage units store the luminance decoding information and the chrominance decoding information as luminance reference information and chrominance reference information, respectively. Here, when decoding the luminance information and the chrominance information divided by the information dividing means, the first and second decoding means respectively access the first and second storage means to obtain the luminance reference information and the chrominance information. With reference to the reference information, the image information is subjected to motion compensation in parallel and decoded. The information combining unit combines the luminance decoding information and the processing reference information decoded by performing motion compensation by the first and second decoding units, and reconstructs image information.

Further, according to the image processing apparatus of the present invention, the information dividing means divides the image information into first to Nth color information based on the color components, and Each of the N-th decoding means decodes the first to N-th color information divided by the information dividing means into first to N-th decoding information in parallel, and each of the first to N-th storage means Stores the first to N-th decoded information as the first to N-th reference information, respectively. Here, each of the first to N-th decoding means is the first decoding means divided by the information dividing means.
When decoding the N-th color information from the first to the N-th color information, the first to the N-th color information is stored in the first to the N-th storage means, and the first to the N-th color information is subjected to motion compensation in parallel. And decrypt. The information combining unit combines the first to Nth decoded information decoded by performing motion compensation by the first to Nth decoding units, and reconstructs image information.

According to the image processing apparatus of the present invention, the first information dividing means divides the image information into luminance information and color difference information, and the second information dividing means The luminance information or the color difference information divided by the first information dividing means is further divided in association with each image region of the screen divided so as to be adjacent in the vertical direction. Each of the plurality of decoding means decodes the luminance information or the chrominance information divided by the first and second information dividing means in parallel,
Each of the plurality of storage units stores luminance information or color difference information for one image area decoded by the plurality of decoding units into a plurality of independently accessible memory spaces and stores the divided information. Here, when decoding the luminance information or the chrominance information divided by the information dividing means, each of the plurality of decoding means accesses the plurality of storage means in units of a memory space to perform the first and second information division. The luminance information or the color difference information divided by the means is subjected to motion compensation in parallel and decoded. The information combining unit combines the luminance information and the chrominance information decoded by the motion compensation by the plurality of decoding units, and reconstructs the image information. In this case, each storage means
Since each memory space is accessed as a unit, a plurality of decoding units can simultaneously access one storage unit. Therefore, even when a motion vector straddles “another image region” in motion compensation of a “certain image region”, the motion vector is not interfered with a decoding operation in the “another image region”. , The motion compensation of the “certain image area” can be performed.

Further, according to the image processing apparatus of the present invention, the first information dividing means divides the image information based on the color component, and the second information dividing means operates in the vertical direction. The image information divided by the first information dividing means is further divided in association with each image region of the screen divided so as to be adjacent to the image information. Each of the plurality of decoding units decodes the image information divided by the first and second information division units in parallel, and each of the plurality of storage units stores one image area corresponding to one image area decoded by the plurality of decoding units. Image information
The data is divided and stored in a plurality of independently accessible memory spaces. Here, when decoding the image information divided by the information dividing means, each of the plurality of decoding means accesses the plurality of storage means in units of memory space, and is divided by the first and second information dividing means. The obtained image information is subjected to motion compensation in parallel and decoded. Then, the information combining unit combines the image information decoded by performing the motion compensation by the plurality of decoding units, and reconstructs the image information. In this case, since each storage unit is accessed using the memory space of each unit as a unit, it becomes possible for a plurality of decoding units to access one storage unit simultaneously. Therefore,
In motion-compensating a “certain image region”, even if the motion vector spans “another image region”,
The motion compensation of the "certain image region" can be performed by accessing the storage means according to the motion vector without interfering with the decoding operation in the "another image region".

Further, according to the image processing apparatus of the present invention, the first information dividing means divides the image information into luminance information and color difference information, and the second information dividing means The luminance information or the color difference information divided by the first information dividing means in association with the first to Nth image areas of the screen divided so as to be adjacent in the vertical direction is converted to the first to Nth image information. Is further divided into Each of the first to N-th decoding means decodes the first to N-th image information divided by the first and second information dividing means in parallel, and independently accesses the first to second N-th image information. Is stored separately. That is, the first to second N storage units store the image information decoded by the first to Nth decoding units in the first to Nth image regions obtained by further dividing each of the first to Nth image regions into two. The information is stored as first to second N reference information in association with the 2N-th small image area. Therefore, the image information of one image area decoded by the decoding means is divided and stored in a pair of continuous odd-numbered and even-numbered storage means. When each of the first to Nth decoding units decodes the first to Nth image information divided by the first and second information division units, the Mth (M is 1)
(N is an integer equal to or less than N).
By accessing any of the M + 1 storage units and referring to the (2M-2) th to (2M + 1) th reference information, motion compensation is performed in parallel for the first to Nth image information. The information combining means combines the first to Nth decoded information decoded by performing motion compensation by the first and second decoding means, and reconstructs image information. As described above, the image information for one image area is divided and stored in a pair of odd-numbered and even-numbered storage units, so that each decoding unit accesses the storage unit as a unit, and In motion compensation of the "image area", even if the motion vector extends over "another image area", the storage means is accessed according to the motion vector without interfering with the decoding operation in the "another image area". Thus, motion compensation for a “certain image region” can be performed.

Further, according to the image processing apparatus of the present invention, the first information dividing means divides the image information based on the color component, and the second information dividing means operates in the vertical direction. The image information divided by the first information dividing means is further divided into first to Nth image information in association with the first to Nth image areas of the screen divided so as to be adjacent to the image information. Each of the first to N-th decoding means includes:
The first to Nth image information divided by the first and second information dividing means are decoded in parallel, and divided and stored in independently accessible first to secondN storage means. That is, the first to second N storage units store the image information decoded by the first to Nth decoding units in the first to Nth image regions obtained by further dividing each of the first to Nth image regions into two. 2
The information is stored as first to second N reference information in association with the Nth small image area. Therefore, the image information of one image area decoded by the decoding means is divided and stored in a pair of continuous odd-numbered and even-numbered storage means.
When each of the first to Nth decoding units decodes the first to Nth image information divided by the first and second information division units, the Mth (M is an integer of 1 or more and N or less) Decoding means accesses any one of the 2M-2 to 2M + 1 storage means and refers to the 2M-2 to 2M + 1 reference information, so that the first to Nth image information can be read in parallel. Motion compensation. The information combining unit combines the first to Nth decoded information decoded by performing motion compensation by the first and second decoding units, and reconstructs image information.
As described above, the image information for one image area is divided and stored in a pair of odd-numbered and even-numbered storage units, so that each decoding unit accesses the storage unit as a unit.
In motion-compensating a “certain image region”, even if the motion vector spans “another image region”,
The motion compensation of the "certain image region" can be performed by accessing the storage means according to the motion vector without interfering with the decoding operation in the "another image region".

Further, according to the image processing apparatus of the ninth aspect, in the image processing apparatus of any one of the fifth and seventh aspects, a screen is divided when decoding luminance information. Since the number is larger than the number of divisions of the screen at the time of decoding the chrominance information, even if the luminance information has a large data amount as compared with the chrominance information, the amount of data to be processed by one decoding unit is excessive. Without decrypting.

Further, according to the image processing apparatus according to the tenth aspect of the present invention, the image processing apparatus according to the first, second, fifth, sixth, seventh, and seventh aspects
In the image processing device according to any one of Items 8 and 9, image information of each image region of a screen divided so as to be adjacent in the horizontal direction is subjected to motion compensation in parallel and decoded.

Furthermore, according to the image processing apparatus of the invention described in claim 11, the image processing apparatus of claims 1, 2, 5, 6, 7,
10. In the image processing apparatus according to any one of items 8 and 9,
The image information of each image area of the screen divided so as to be adjacent in the dimensional direction is subjected to motion compensation in parallel and decoded.

[0032]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an image processing apparatus according to an embodiment of the present invention will be described in detail with reference to FIGS. Here, FIG. 1 is a block diagram showing the configuration of the image processing apparatus according to the first embodiment, and FIG. 2 is an explanatory diagram for explaining the motion compensation operation of the image processing apparatus according to the first embodiment. FIG. 3 is a block diagram showing a case where the number of screen divisions is extended to three in the configuration of the apparatus according to the first embodiment shown in FIG. 1, and FIG. 4 shows a configuration of an image processing apparatus according to the second embodiment. FIG. 5 is a block diagram showing a case where a screen is divided into two for luminance information in the configuration of the apparatus according to the second embodiment shown in FIG. In each of the drawings, the same or corresponding elements have the same reference characters allotted.

(Regarding the First Embodiment) First, FIG.
The image processing apparatus according to the first embodiment of the present invention will be described with reference to FIGS. The image processing apparatus according to the present embodiment is configured such that a plurality of decoders can refer to image information corresponding to each image area obtained by dividing a screen, and when each decoder performs motion compensation, the decoder performs motion compensation. The image information of the image area other than the target image area can be referred to according to the motion vector. This enables motion compensation according to the motion vector near the image area boundary.

That is, as shown in FIG. 2 described later, the image processing apparatus of the present embodiment shown in FIG. 1 performs parallel processing of image information corresponding to image areas RA and RB obtained by dividing a screen into upper and lower parts. A slice detector 1 (information division) that detects a position on a screen of a compressed bit stream of image information and divides (slices) the bit stream into two upper and lower image areas RA and RB. (Before means) and the image information corresponding to the upper and lower image areas RA and RB divided by the slice detector 1, respectively, and time-adjusted to match the operation timing of decoders 3A and 3B, which will be described later, and output them. FIFO (First-In Fi
rst-Out) and the image information corresponding to the upper and lower image areas RA and RB time-adjusted by the buffers 2A and 2B, and decoded by motion compensation. Decoders 3A and 3B
(A plurality of decoding means), a selector 4A-2 (a part of the decoding means) for selecting one of the decoders 3A or 3B and connecting to a memory 5A-2 described later, and one of the decoders 3A or 3B. And a storage unit 5A (a plurality of units) that stores the image information decoded by the decoder 3A as reference information for motion compensation. Part of the storage means)
A storage unit 5B (part of a plurality of storage units) for storing image information decoded by the decoder 3B;
And a combiner 6 (information combining means) for combining image information corresponding to the upper and lower image areas RA and RB, which have been motion compensated and decoded by A and 3B, to form image information for one screen. You.

Each of the storage units 5A and 5B has
It is configured to have independently accessible memories 5A-1, 5A-2 (a plurality of memory spaces) and memories 5B-1, 5B-2 (a plurality of memory spaces). Of these, memory 5
A-2 and 5B-1 are selectively connected to one of the decoders 3A and 3B via selectors 4A-2 and 4B-1, respectively. Conversely, memories 5A-2 and 5A-2
B-1 is configured to be selectively accessible from any of the decoders 3A and 3B. The memory 5A-1
And 5B-2 can be directly accessed only by the decoders 3A and 3B, respectively.

Here, the correspondence between the image information stored by the storage units 5A and 5B as reference information at the time of motion compensation and each image area of the screen will be described. As shown in FIG. 2, the correspondence between the image information stored in each memory and the screen (image area), the storage units 5A and 5B divide the screen into two, for example, vertically adjacent (up and down). The image information corresponding to the obtained image areas RA and RB is decoded by the decoder 3A.
And 3B, respectively, and store them as reference information.

The memory 5A-1 constituting the storage section 5A
And 5A-2 are small areas RA1 and RA2 obtained by dividing the image area RA further into two so as to be adjacent in the vertical direction.
The image information of the image area RA input from the decoder 3A is divided and stored in association with the (small image area).
The memories 5B-1 and 5B-2 constituting the storage unit 5B are:
Small areas RB1 and R obtained by dividing the image area RB into two
The image information of the image area RB input from the decoder 3B is divided and stored in association with B2.

By the way, in MPEG2, the maximum value that a motion vector can take is defined, and the vertical size (height) of each of the small areas RA1 to RB2 shown in FIG. 2 can be taken by the motion vector of each image block. It is set larger than the maximum value. As a result, the motion vector of the image block belonging to a certain small area does not refer to the image information of the small area two or more apart from each other, and the decoders 3A and 3B make the decoders 3A and 3B In the process of processing image information in parallel, simultaneous access to the same memory (so-called memory batting) is eliminated. As described above, the relationship between the maximum value of the motion vector and the size of the small area is defined from the viewpoint of memory batting.

However, as long as the required image quality can be obtained, it is not always necessary to strictly observe these relations and completely avoid the memory batting. May be configured so that the size of the small region is smaller than the maximum value that the motion vector can take, to allow a certain amount of memory batting, and to save the storage capacity of the memory.

In this embodiment, the small areas RA1 to RA
Although the size in the vertical direction (vertical direction) is defined in accordance with the division of B2 so as to be adjacent in the vertical direction, the size of each small area is the maximum value of the motion vector in the direction in which the small areas are adjacent. If the small area is adjacent in the horizontal direction, the size of the small area in the horizontal direction (lateral direction) may be larger than the maximum value of the motion vector.

Hereinafter, the operation of the motion compensation of the image processing apparatus of the present embodiment configured as described above will be described. As described above, when decoding image information conforming to MPEG, motion compensation is sequentially performed according to a motion vector in units of image blocks. That is, the decoder 3A shown in FIG.
First, an image block a belonging to the small area RA1 shown in FIG.
1, the motion compensation is started from the portion corresponding to the block b1, and in parallel with this, the decoder 3B makes the block b1 belonging to the small area RB1.
The motion compensation is started from the portion corresponding to.

Here, the positions of the image blocks a1 to a5 belonging to the image area RA and the positions of the image blocks b1 to b5 belonging to the image area RB have the same relative positions in the respective image areas. . Therefore, the image blocks a1 to a5 belonging to the image area RA and the image area R
The distance on the screen from the image blocks b1 to b5 belonging to B is twice as large as the vertical size of the small area, so that the maximum value does not exceed the vertical size of the small area. As will be described later, the motion vectors of the blocks a1 to a5 and the image blocks b1 to b5 do not refer to the same small area in the process of performing motion compensation in parallel for each piece of image information.

As described above, the correspondence between the image information stored in the storage units 5A and 5B and each image area of the screen is set, and the motion compensation is performed as follows. That is,
First, when motion compensation is performed on a portion corresponding to the image block a1 shown in FIG. 2, the motion vector of the image block a1 is contained within the small area RA1 and the decoder 3A
Directly accesses the memory 5A-1 to access the image block a.
The motion compensation is performed according to the motion vector of No. 1.

On the other hand, in parallel with the processing of the part corresponding to the image block a1, the motion compensation of the part corresponding to the image block b1 is performed. In this case, the maximum vertical range that the motion vector of the image block b1 can take is:
It extends over both the small areas RA2 and RB1. Therefore, in this case, the selection state of the selectors 4A-2 and 4B-1 is set to the decoder 3B, and the decoder 3B controls one of the memories 5A-2 or 5B-1 via the selector 4A-2 or 4B-1. Access and perform motion compensation.

Next, when motion compensation is performed on the portion corresponding to the block a2, the maximum range in the vertical direction that the motion vector of the image block a2 can take is still the small area RA1.
, The decoder 3A has the memory 5
A-1 is accessed to perform motion compensation.

On the other hand, in parallel with the processing of the part corresponding to the block a2, the motion compensation of the part corresponding to the block b2 is performed. In this case, the maximum range in the vertical direction that the motion vector of the image block b2 can take is the small area RB
It is in one. Therefore, in this case, the selector 4
The selected state of B-1 is maintained by the decoder 3B, and the decoder 3B accesses the memory 5B-1 via the selector 4B-1 to perform motion compensation. In this case, the memory 5A
-2 is not accessed by any of the decoders 3A and 3B, so that the selector 4A-2 may be in any selected state.

Next, when motion compensation is performed on a portion corresponding to the image block a3, the maximum range of the motion vector of the image block a3 which can be taken in the vertical direction is small areas RA1 and
A2. Therefore, in this case, the selection state of the selector 4A-2 is changed to the decoder 3A,
The decoder 3A accesses one of the memories 5A-1 and 5A-2 to perform motion compensation.

On the other hand, in parallel with the processing of the part corresponding to the image block a3, the motion compensation of the part corresponding to the image block b3 is performed. In this case, the maximum vertical range that the motion vector of this image block b3 can take is:
It extends over both the small regions RB1 and RB2. Therefore, in this case, the selected state of the selector 4B-1 is maintained by the decoder 3B, and the decoder 3B accesses either the memory 5B-1 or 5B-2 to perform motion compensation.

Next, when motion compensation is performed on a portion corresponding to the image block a4, the maximum range of the motion vector of the image block a4 which can be taken in the vertical direction falls within the small area RA2. Is maintained in the decoder 3A, and the decoder 3A accesses the memory 5A-2 via the selector 4A-2 to perform motion compensation.

On the other hand, in parallel with the processing of the part corresponding to the image block a4, the motion compensation of the part corresponding to the image block b4 is performed. In this case, the maximum vertical range that the motion vector of the image block b4 can take is:
Since it fits inside the small area RB2, the decoder 3B
Performs motion compensation by accessing the memory 5B-2. Note that, in this case, the memory 5B-1 includes the decoders 3A and 3A.
B is not accessed, so the selector 4B-1
May be in any selection state.

Finally, when motion compensation is performed on the portion corresponding to the image block a5, the maximum vertical range that the motion vector of the image block a5 can take extends over both the small areas RA2 and RB1. Therefore, in this case,
The selection state of the selector 4A-2 is maintained by the decoder 3A, and the selection state of the selector 4B-1 is changed to the decoder 3A.
Either the memory 5A-2 or 5B-1 is accessed via B-1 to perform motion compensation.

On the other hand, in parallel with the processing of the portion corresponding to the image block a5, the motion compensation of the portion corresponding to the image block b5 is performed. In this case, since the motion vector of the image block b5 falls within the small area RB2, the decoder 3B accesses the memory 5B-2 to perform motion compensation.

As described above, in the process of performing the motion compensation on the image blocks a1 to a5 and the image blocks b1 to b5 in parallel and performing the decoding process, the selector 4A-A5 is used in accordance with the image block to be decoded. 2 and 4B-1 are set, and there is no case where the decoders 3A and 3B simultaneously access the same memory. Also, for any image block on the screen, image blocks a1 to a
5 or any of b1 to b5, and the decoders 3A and 3B can store the memory storing the image information (reference information) necessary for the motion compensation according to the respective motion vectors without causing batting. Access in parallel.

Therefore, according to the image processing apparatus of the present embodiment, unlike the above-described conventional apparatus in which motion compensation is performed with reference to simply divided image information, the boundary between the image areas RA and RB is also different. By performing the motion compensation normally, it is possible to perform the motion compensation in parallel for the image information corresponding to each image region, and it is possible to construct the image information in which natural motion is reproduced.

The image processing apparatus of the present embodiment shown in FIG. 1 is configured to process image information in parallel in correspondence with image areas RA and RB obtained by dividing a screen into two. The number of divisions (the number of parallel processing stages) may be increased according to. For example, when trying to decode image information in parallel in association with an image area obtained by dividing a screen into three, as shown in FIG. 3, in the configuration of the apparatus shown in FIG.
Further, a buffer 2C, a decoder 3C, a selector 4C-
1. Each element of the storage unit 5C (the memories 5C-1 and 5C-2) may be added.

In this case, the slice detector 1 and the combiner 6 are configured so as to have expanded functions to cope with the newly added elements described above, and each of the storage units 5A to 5C The storage capacity is adjusted (decreased) in accordance with an increase in the number of screen divisions.

Further, in the case of the image processing apparatus of the present embodiment shown in FIGS. 1 and 3, the storage unit (for example, the storage unit 5)
A) with two memories (for example, memories 5A-1 and 5A-).
2), these two memories are used as the memory space of the storage unit 5A which can be accessed independently, but each of the memories (5A-1 to 5C-2) may be treated as an independent storage unit in the first place. In this case, the image information decoded by one decoder is divided and stored in two storage units.

In the case of such a configuration, for example, the decoder 3B (M-th decoding means) shown in FIG. 3 operates according to the position of the image block to be processed in the memory 5A-2 (2M-2 storage means). ) To memory 5C-1 (2M + 1)
, And motion compensation is performed by referring to the image information (reference information) stored in these memories.

Further, in the present embodiment, the storage section (for example, the storage section 5A) shown in FIGS. 1 and 3 is constituted by two memories to realize a plurality of memory spaces which can be accessed independently. It is sufficient that the device can be accessed independently for each small region of each image region. For example, the device can be configured using a device such as a dual port memory capable of simultaneously specifying a plurality of addresses.

Furthermore, in the present embodiment, for example, the number of memories that can be accessed by the decoder 3A is limited to a maximum of three (the memories 5A-1, 5A-
2, 5B-1), but each decoder may be configured to be able to access all memories.

(Regarding the Second Embodiment) Next, FIG.
An image processing apparatus according to the second embodiment of the present invention will be described with reference to FIG. The image processing apparatus according to the first embodiment divides image information and performs parallel processing in association with an image area that is a physical area on a screen. Focuses on attributes (data structure) such as luminance and color difference, and performs parallel processing by dividing image information.

Generally, color image information includes luminance and color difference,
Alternatively, the image data is decomposed into components such as RGB (Red-Green-Blue) and subjected to encoding / decoding processing. The image processing apparatus according to the present embodiment is configured by paying attention to this point, and performs different decoding processes of the color image information on the luminance component (luminance information) and the color difference component (color difference information). And motion compensation for the luminance component and the color difference component is performed in parallel.

That is, the image processing apparatus of this embodiment shown in FIG. 4 receives a bit stream of color image information,
A luminance decoder 30 and a chrominance decoder 31 for respectively decoding the luminance component and the chrominance component of the color image information, and a luminance for storing the luminance component and the chrominance component of the image information decoded by the luminance decoder 30 and the chrominance decoder 31, respectively. Memory 50 and a color difference memory 51.

In the case of the device of the present embodiment having the above-described structure, the luminance decoder 30 and the color difference decoder 31
A bit stream of color image information is input, and a luminance component and a chrominance component of the color image information are decoded and stored in a luminance memory 50 and a chrominance memory 51, respectively.

Here, when performing motion compensation, the luminance decoder 30 and the chrominance decoder 31 are connected to the luminance memory 50.
And the color difference memory 51 is accessed according to the motion vector to read out the image information of the required image block, and the luminance component and the color difference component of the image information motion-compensated using this image information are connected to the subsequent stage. It is given to a D / A converter (not shown).

As described above, in the apparatus according to the present embodiment, the color image information is divided into the luminance component and the color difference component and is processed in parallel, so that the processing is performed so that the load on one decoder is not excessive. The amount of data is reduced. In the present embodiment, the apparatus is configured to decode color image information including a luminance component and a chrominance component. However, as described above, the apparatus is configured to decode RGB color image information. , The color image information is divided into R (Red), G (Green), and B (Blue) components, and the image information is motion-compensated in parallel for each color component and decoded. What is necessary is just to appropriately select a division criterion according to the type of image information to be processed.

(Regarding the Third Embodiment) Next, FIG.
The image processing device according to the third embodiment of the present invention will be described with reference to FIG. As described above, the image processing apparatus according to the second embodiment is configured to divide image information into a luminance component and a chrominance component and perform parallel processing. However, the image processing apparatus according to the present embodiment illustrated in FIG. In the process of processing the luminance component and the chrominance component in parallel, the image region obtained by dividing the screen is obtained by combining the device of the first embodiment and the device of the second embodiment. And the processing of the luminance component or the color difference component is further parallelized.

By the way, the number of screen divisions for processing the luminance component and the number of screen divisions for processing the chrominance component need not always be the same. That is, in MPEG or the like, the chrominance component is thinned out with respect to the luminance component of the image information to reduce the number of pixels of the image. Does not require much processing power.

The apparatus of this embodiment pays attention to this point,
The number of decoders responsible for processing of the luminance component and the chrominance component is adjusted according to the data amount, and two decoders are allocated to the decoding process of the luminance component having a large data amount. In addition to parallel processing, one decoder is allocated for decoding a color difference component having a relatively small amount of data, so that the decoder is efficiently allocated in accordance with the data structure of image information. is there.

That is, the image processing apparatus shown in FIG. 5 uses the apparatus of the first embodiment shown in FIG. 1 as a processing system for a luminance component, and further performs processing for a color difference component. And a color difference component processing system including a color difference decoder 31 and a color difference memory 51 shown in FIG.

However, the slice detector 1 constituting the apparatus shown in FIG. 5 divides the bit stream of the compressed image data into a luminance component and a chrominance component, and, for the luminance component, moves the screen vertically. It is configured to be further divided into two in association with each image region obtained by dividing into two so as to be adjacent.

The decoders 3A and 3B and the decoder 31 shown in FIG. 3 are configured to decode the luminance component and the color difference component of the image information input from the slice detector 1, respectively, and among them, the decoders 3A and 3B Decodes each of the luminance components further divided into two in association with the image area. Further, the combiner 6 is configured to combine the luminance component and the chrominance component of the image information decoded by the luminance decoders 3A and 3B and the chrominance decoder 3C into the image information of one screen.

The apparatus according to the present embodiment configured as described above divides image information into a luminance component and a chrominance component to perform motion compensation decoding in parallel, and the luminance component is stored in each image area of the screen. The decoding process is parallelized by further dividing the image data in association with each other, and the distribution of the decoders is optimized according to the data structure of the image information.

In the present embodiment, two decoders are allocated to the processing of the luminance component and one decoder is allocated to the chrominance components. The distribution is not limited, and the distribution may be appropriately determined according to the data amount of each component and the processing capability of the decoder alone. Similarly, when the image information is of the RGB type, the distribution of the decoders may be determined according to the data amount of each color component.

In the above description of the first and third embodiments, the screen dividing direction for the parallel processing is the vertical direction. However, the screen dividing direction is not limited to this. Left or right) or a two-dimensional direction may be used, and further, these division directions may be appropriately combined, and the division direction may be appropriately determined as needed.

[0076]

As is apparent from the above description, according to the present invention, the following effects can be obtained. That is, claims 1 and 2 and dependent claims 10 and 11
According to the image processing apparatus according to the present invention, when performing motion compensation in parallel with reference to image information corresponding to a plurality of image regions obtained by dividing the screen, the image information of a certain image region Since a plurality of decoding means (decoders) are configured to be able to refer to, even when a motion vector refers to reference information (image information) of another image area, the motion vector can be referenced by referring to necessary reference information. Compensation can be performed in parallel, and even near the boundary of each image region, image motion can be decoded into natural image information. Moreover, since image information is processed in parallel, large-scale image information can be motion-compensated and decoded at high speed without increasing the performance of the decoding means alone.

According to the image processing apparatus of the present invention, the image information is divided into a luminance component and a chrominance component, and the motion compensation is performed in parallel. Decoder) Large-scale image information composed of a luminance component and a color difference component can be motion-compensated at high speed and decoded without increasing the performance of a single unit.

Further, according to the image processing apparatus of the present invention, since the image information is divided into each color component such as RGB and the motion compensation is performed in parallel, the decoding means (decoder) ) RG without increasing the performance of a single unit
Large-scale image information composed of color components such as B can be decoded with high-speed motion compensation.

Further, according to the image processing apparatus according to the fifth and seventh aspects and the tenth and eleventh aspects of the present invention, the effects obtained by the image processing apparatus according to the third aspect of the invention can be obtained. In addition to the above, the effect obtained by the image processing apparatus according to the first aspect of the present invention can also be obtained, and large-scale image information including luminance and chrominance components is further motion-compensated and decoded at higher speed. be able to.

Further, according to the image processing apparatus according to the sixth and eighth aspects of the present invention, in addition to the effects obtained by the image processing apparatus according to the fourth aspect of the present invention, the first aspect of the present invention is characterized in that:
Thus, it is possible to obtain the effect obtained by the image processing apparatus according to the present invention, and to decode large-scale image information composed of color components such as RGB with further high-speed motion compensation.

Further, according to the image processing apparatus of the ninth aspect of the present invention, the decoding means is appropriately distributed in accordance with the data structure of the image information, so that the invention of the fifth or seventh aspect is provided. In addition to the effects obtained by the image processing apparatus according to the above, parallel processing can be efficiently performed with less decoding means.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a configuration of an image processing apparatus according to a first embodiment.

FIG. 2 is an explanatory diagram for explaining an operation of motion compensation of the image processing apparatus according to the first embodiment.

FIG. 3 is a block diagram illustrating a configuration in a case where the number of screen divisions is extended to three in the image processing apparatus according to the first embodiment.

FIG. 4 is a block diagram illustrating a configuration of an image processing apparatus according to a second embodiment.

FIG. 5 is a block diagram illustrating a configuration in a case where an image processing apparatus according to a second embodiment divides a screen into two with respect to a luminance component and performs parallel processing.

FIG. 6 is a block diagram showing a conventional image processing apparatus conforming to MPEG2.

FIG. 7 is an explanatory diagram for explaining an operation of a conventional image processing device that performs parallel motion compensation processing.

[Explanation of symbols]

1 slice detector 2A, 2B, 2C buffer 3A, 3B, 3C decoder 4A-2, 4B-1, 4B-2, 4C-1 selector 5A-5C storage unit 5A-1, 5A-2, 5B-1, 5B −2, 5C-1,
5C-2 Memory 6 Combiner 30 Decoder for luminance 31 Decoder for color difference 50 Memory for luminance 51 Memory for color difference

Claims (11)

[Claims] 1. An image processing apparatus which divides a screen into a plurality of vertically adjacent image regions, and performs motion compensation on the image information of the screen in parallel with each of the image regions as a unit, and decodes the image information. An information dividing unit that divides the image information in association with the image area; a plurality of decoding units that decode each of the image information divided by the information dividing unit; and the image information that is decoded by the plurality of decoding units. A plurality of storage means for storing each of the plurality of, and information combining means for combining each of the image information decoded by the plurality of decoding means in association with the plurality of image regions, respectively, each of the plurality of storage means Has a plurality of memory spaces that can be accessed independently, stores image information decoded by the decoding unit in the plurality of memory spaces, and stores the plurality of memory spaces. When decoding the image information divided by the information dividing means, each of the signal means accesses any of the plurality of storage means in units of the memory space, and performs parallel processing on the image information of the plurality of image areas. An image processing apparatus, comprising: 2. A screen is divided into first to N-th (N is an integer of 2 or more) image areas which are vertically adjacent to each other, and image information of the screen is divided into the image areas as a unit. What is claimed is: 1. An image processing apparatus for performing motion compensation and decoding in parallel, wherein said information dividing means divides said image information into first to Nth image information in association with said first to Nth image areas. First to N-th decoding means for decoding the first to N-th image information into first to N-th decoding information, respectively; The first to N-th decoded information is divided into first to second N reference information in association with the first to N-th small image areas obtained by dividing the image into two so as to be adjacent in the direction. First to second N storage means for respectively storing Information combining means for combining the N-th decoded information in association with the first to N-th image areas, wherein the first to N-th decoding means comprises the first to N-th image information Are respectively decoded into the first to N-th decoding information, the M-th (M is an integer of 1 or more and N or less) decoding means of the first to N-th decoding means is used.
Wherein the motion compensation is performed in parallel on the first to N-th image information by accessing any one of the first storage means and referring to the second M-2 to the second M + 1 reference information. Processing equipment. 3. An image processing apparatus for performing motion compensation on image information and decoding the image information, comprising: an information division unit configured to divide the image information into luminance information and color difference information; First and second decoding means for decoding into chrominance decoding information, respectively, and first and second means for storing the luminance decoding information and the chrominance decoding information as luminance reference information and chrominance reference information, respectively.
Storage means, and information combining means for combining the luminance decoding information and the chrominance decoding information, wherein the first and second decoding means convert the luminance information and the chrominance information into the luminance decoding information and the In decoding the chrominance decoding information, respectively, the first and second storage units are accessed to refer to the luminance reference information and the chrominance reference information stored in the first and second storage units, respectively. The image processing apparatus according to claim 1, wherein motion compensation is performed on the luminance information and the color difference information in parallel. 4. An image processing apparatus that performs motion compensation on image information and decodes the image information, comprising: an information dividing unit that divides the image information into first to N-th color information based on a color component; First to Nth decoding means for decoding the Nth color information into first to Nth decoded information, respectively; and storing the first to Nth decoded information as first to Nth reference information, respectively. A first to an N-th storage unit; and an information combining unit that combines the first to the N-th decoded information. The first to the N-th decoding unit stores the first to the N-th color information. When decoding the first to N-th decoding information, respectively, the first to N-th storage units are accessed, and the first to N-th storage units stored in the first to N-th storage units are accessed. By referring to each reference information,
An image processing apparatus for performing motion compensation on the first to Nth color information in parallel. 5. An image processing apparatus which divides a screen into a plurality of image areas vertically adjacent to each other, and performs motion compensation on the image information of the screen in parallel by using the image area as a unit, and decodes the image information. First information dividing means for dividing information into luminance information and color difference information, and second information dividing the luminance information or color difference information divided by the first information dividing means in association with the plurality of image areas. Information dividing means; a plurality of decoding means for decoding the luminance information or the chrominance information divided by the first and second information dividing means; and storing the luminance information or the chrominance information decoded by the plurality of decoding means. A plurality of storage means; and information combining means for combining the luminance information or the color difference information decoded by the plurality of decoding means in association with the plurality of image areas, Each of the plurality of decoding units has a plurality of memory spaces that can be independently accessed, and stores the luminance information or the color difference information decoded by the plurality of decoding units in the plurality of memory spaces. When decoding the luminance information or the chrominance information divided by the first and second information dividing means, any one of the plurality of storage means is accessed by using the memory space as a unit, and the plurality of image areas are An image processing apparatus for performing motion compensation in parallel on the image information. 6. An image processing apparatus which divides a screen into a plurality of vertically adjacent image areas, and performs motion compensation on the image information of the screen in parallel with each of the image areas as a unit, and decodes the image information. First information dividing means for dividing information based on color components, second information dividing means for dividing the image information divided by the first information dividing means in association with the plurality of image areas, A plurality of decoding units for decoding the image information divided by the first and second information division units; a plurality of storage units for storing the image information decoded by the plurality of decoding units; and the plurality of decoding units And information combining means for combining the image information decoded according to the plurality of image areas in association with each other, wherein each of the plurality of storage means has a plurality of memory spaces which can be independently accessed, and The image information decoded by the plurality of decoding units is divided and stored in the plurality of memory spaces, and each of the plurality of decoding units decodes the image information divided by the first and second information dividing units. An image processing apparatus configured to access one of the plurality of storage units using the memory space as a unit and perform motion compensation in parallel on image information of the plurality of image areas. 7. The screen is divided into first to Nth (N is an integer of 2 or more) N image areas vertically adjacent to each other, and image information of the screen is divided into the image areas as a unit. An image processing apparatus that performs motion compensation and decoding in parallel, comprising: a first information division unit configured to divide the image information into luminance information and chrominance information, and corresponding to the first to Nth image areas. A second information dividing unit that divides the luminance information or the color difference information divided by the first information dividing unit into first to N-th image information; First to N-th decoding means for decoding the first to N-th decoding information, respectively; and a first to N-th image area obtained by dividing each of the first to N-th image areas into two so as to be adjacent in the vertical direction. Corresponding to the 1st to 2nd Nth small image areas First to second N storage means for dividing the first to N-th decoded information into first to second N reference information and storing the divided first and second N pieces of reference information, respectively; And information combining means for combining the first to Nth image information in association with the first to Nth image information, wherein the first to Nth decoding means combine the first to Nth image information with the first to Nth image information. At the time of decoding, the M-th (M is an integer of 1 or more and N or less) decoding means of the first to N-th decoding means is used.
The first to the N-th image information are subjected to motion compensation in parallel by accessing any one of the first storage means and referring to the (2M-2) th to (2M + 1) th reference information. Image processing device. 8. A screen is divided into first to Nth (N is an integer of 2 or more) N image areas which are vertically adjacent to each other, and image information of the screen is divided into the image areas as a unit. An image processing apparatus that performs motion compensation in parallel and decodes the image information, wherein a first information dividing unit that divides the image information based on a color component; The image information divided by the first information dividing means
A second information dividing unit that divides the first to Nth image information into first to Nth decoded information, and a second information dividing unit that divides the first to Nth image information into first to Nth decoded information. The first to Nth image areas are respectively associated with the first to Nth small image areas obtained by dividing each of the first to Nth image areas into two so as to be adjacent in the vertical direction. First to second N storage means for dividing the decoded information into first to second N reference information and storing the divided information, respectively; and the first to Nth image areas for storing the first to Nth decoded information. And an information combining unit that combines the first to Nth image information into the first to Nth decoded information, respectively, when decoding the first to Nth image information. M-th (M is an integer from 1 to N) of the first to N-th decoding means Decoding means from 2M-2 to 2M +
The motion compensation is performed in parallel on each of the first to Nth image information by accessing any one of the first storage means and referring to the second M-2 to the second M + 1 reference information. Image processing device. 9. The method according to claim 5, wherein the number of divisions of the screen when decoding the luminance information is larger than the number of divisions of the screen when decoding the chrominance information. Image processing device. 10. The decoding method according to claim 1, wherein the screen is divided into image areas adjacent in the horizontal direction instead of the vertical direction and decoded. An image processing apparatus according to the item. 11. The decoding method according to claim 1, wherein the screen is divided into image areas adjacent in the two-dimensional direction instead of the vertical direction and decoded. 2. The image processing device according to claim 1.