JP3253595B2 - Moving image specific color detection apparatus and detection method - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an apparatus and a method for detecting a moving image specific color object.

[0002]

2. Description of the Related Art Hitherto, in most cases, a moving image monitoring system mainly detects an object or the like entering a screen. However, when the monitored image is, for example, an instrument panel of a plant, the change may be the color of the lamp. In such a case, the abnormality of the monitoring image can be detected by detecting the specific color.

In order to detect a specific color, it is generally necessary to check the color of each pixel. However, the process of examining the color for each pixel actually has a problem of requiring a large amount of calculation. For example, ITU-TH. 261, H .;
263, CIF format often used in ISO / IEC MPEG-4, etc.
The color space is converted for a total of 101376 pixels of eight pixels. For such a process with a large amount of calculation, it is necessary to prepare dedicated hardware, and there has been a great problem in terms of cost.

[0004]

As described above, according to the prior art, there is a problem that a large amount of calculation is required to detect a specific color at high speed.

SUMMARY OF THE INVENTION An object of the present invention is to provide a moving image specific color detecting device capable of detecting a specific color object at high speed and stably with high accuracy.

[0006]

A moving image specific color detecting device according to the present invention is a device for detecting a specific color in a moving image, the moving image decoding means for decoding encoded data obtained by compressing a moving image. And a specific color object detection means, wherein the specific color object detection means determines, for each block decoded by the moving image decoding means, whether an image in the block is in a still state or a moving state from a decoding result. Means for determining a specific color object from the result of static / movement determination for each block, and means for combining the determined area of the specific color object with a reproduced image signal created by the moving image decoding means and displaying the combined image.

The means for determining whether the image in the block is still or moving from the decoded result of each decoded block of the moving image specific color object detecting device is provided for each block decoded by the moving image decoding means. From the mode information, the motion vector information, the transform coefficient information, and the difference between the current reproduced image signal and the reproduced image one frame before, it is determined whether the block is in the stationary state or the moving state.

As described above, by combining the moving picture decoding apparatus with the detection of the specific color, the decoding can be performed simultaneously with the decoding, and the range of detecting the specific color can be greatly narrowed based on the result of the still / moving judgment for each block. , The specific color can be detected at high speed.

A moving image specific color detecting device according to the present invention is a device for detecting a specific color object in a moving image, wherein the moving image coding means for coding a moving image, the specific color object detecting means, a moving image Moving image decoding means for decoding the encoded data obtained by compressing the image, and the specific color object detecting means converts each block coded by the moving image coding means Means for determining whether the image is in a still state or a moving state; means for determining a specific color object from a result of the still / moving determination for each block; and the moving image encoding means, wherein the determination result of the specific color object is encoded data and Multiplexed and transmitted, the video decoding means decodes the encoded data,
Means for combining and displaying the reproduced image signal and the determination result of the specific color object.

The means for judging whether the image in the block is still or moving from the coding result of each decoded block of the moving image specific color object detecting device is a block coded by the moving image coding means. Whether the block is stationary or moving is determined based on the mode information, the motion vector information, the transform coefficient information, and the difference between the current input moving image signal and the locally decoded image one frame before.

Further, the moving image specific color object detecting apparatus includes:
The image processing apparatus further includes a moving image encoding unit that combines the determined area of the specific color object with a local image signal created by the moving image encoding unit and displays the combined image.

As described above, the combination of the moving picture coding apparatus and the detection of the specific color can be performed simultaneously with the coding, and the range of detecting the specific color can be greatly narrowed from the result of the still / moving judgment for each block. , The specific color can be detected at high speed.

The means for judging a specific color object from the still / moving judgment result for each block of the moving image specific color object detection device includes the step of recognizing the specific color object by a figure in which the image in the block includes the specific color detection block. judge.

Further, in the moving image specific color detecting method according to the present invention, a decoding step of decoding coded data obtained by compressing a moving image, and a decoding result decoded by the decoding means for each block in the block. A step of determining whether the image is a stationary state or a moving state; a step of determining a specific color object of the moving state block from the result of the static / moving determination for each block; Generating a reproduced image signal created by the decoding step. By such processing, the influence of the detection error can be suppressed, and the detection result can be displayed more clearly.

[0015]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS (First Embodiment) A first embodiment of the present invention will be described below with reference to the drawings.

FIG. 1 is a block diagram showing a configuration of a moving image specific color object detecting apparatus according to an embodiment of the present invention.

The moving image specific color object detecting apparatus shown in FIG. 1 is composed of two parts, a moving image decoding unit 110 and a specific color object detecting unit 116.

In the moving picture decoding unit 110, first,
Coded data received from a transmission path or a storage system is once stored in an input buffer 101, separated by a demultiplexing unit 102 on a frame-by-frame basis based on syntax, and output to a variable-length decoding unit 103. The variable length decoding unit 103 decodes a variable length code of information of each syntax.

In the variable length decoding section 103, if the mode of the macroblock is INTRA, the mode changeover switch 109 is selected to be off, and the quantized DCT coefficient information decoded by the variable length decoding section 103 is inverted. Quantization unit 104
, And the IDCT unit 105 performs an inverse discrete cosine transform process to generate a reproduced image signal. The reproduced image signal is stored in the frame memory 107 as a reference image, and is input to the specific color object synthesis display unit 115 in the specific color object detection unit 116.

If the macroblock mode is INTER or NOT_CODED in the variable length decoding unit 103, the mode changeover switch 109 is turned off, and the quantized DCT coefficient information decoded by the variable length decoding unit 103 is , Is inversely quantized by the inverse quantization unit 104 and the IDCT unit 1
05, performs an inverse discrete cosine transform process, and based on the motion vector information decoded by the variable length decoding unit 103, performs motion compensation on the reference image in the motion compensation unit 108,
The addition is performed by the adder 106 to generate a reproduced image signal. The reproduced image signal is stored in the frame memory 107 as a reference image, and is input to the specific color object synthesis display unit 115 in the specific color object detection unit 116.

On the other hand, in the specific color object detecting section 116, as shown in the flow chart of FIG. 2, the macro block static / moving judgment (S101) and the specific color object judgment (S10) are performed for each frame.
2) The three processes of the specific color object combination display (S103) are performed by the macroblock still / movement determination unit 111, the specific color object determination unit 112, and the specific color object combination display unit 115, respectively.

The macroblock static / motion determining unit 111 includes the mode information, the motion vector information, the DCT coefficient information decoded by the variable length decoding unit 103 and the reproduced image signal for the INTRA macroblock obtained by the subtractor 112 and 1 Sum of absolute difference (SAD) with frame memory before frame
Then, a still / moving decision is made for each macroblock in the frame.

FIG. 3 is a flowchart showing a macroblock static / movement determination (S10).
It is a specific flowchart of 1). Here, i and j represent the vertical and horizontal macroblock addresses in the frame, respectively, and V_NMB and H_NMB represent the number of vertical and horizontal macroblocks in the frame. The two-dimensional array M [i] [j] is an array for storing information as to whether each macroblock is a moving macroblock.
E indicates a moving macroblock, and FALSE indicates a still macroblock.

First, the mode information MODE from the variable length decoding unit 103 is determined for each macroblock. (S2
03) If MODE is INTRA, calculate the sum of absolute differences (SAD) between the reproduced image signal of the macroblock and the frame memory one frame before, and compare it with the threshold value T0. (S204) If it is larger than the threshold value T0, the macro block is determined to be a moving macro block, and M
TRUE is substituted for [i] [j]. (S206) If MODE is INTER, the variable length decoding unit 1
03 from the motion vector information and DCT coefficient information from
Sum of absolute values of motion vectors of the macro block Σ | MV
And the sum of absolute values of DCT coefficients Σ | COF |
A comparison is made with the respective threshold values T1 and T2. (S205)
If the sum of the absolute value of the motion vector and the sum of the absolute values of the DCT coefficients are equal to or larger than the threshold, the macroblock is determined to be a moving macroblock, and TRUE is substituted for M [i] [j]. (S206) The specific color object determination unit 113 determines a specific color object based on the static / movement determination information for each macroblock of the macroblock static / movement determination unit 112. FIG. 4 is a specific flowchart. As shown in FIG. 4, the processing content is a specific color detection process (S
301) and the specific color object inclusion processing (S302). In the specific color detection processing (S301), in order to prevent the small macro-objects in the background image from being erroneously detected as moving macro-blocks due to the fluctuation of the small object or noise at the time of image capturing, a moving macro-block in which all eight surrounding macro blocks are still Has been removed. Specific color object inclusion processing (S3
In step 02), a process of detecting the smallest rectangle that includes a region where an adjacent moving macroblock exists is performed based on the result of the still / moving determination after removing noise. Through this processing, a rectangle that includes the specific color object can be found.

FIG. 5 shows the specific processing contents of the specific color detection processing. As in FIG. 3, i and j represent the addresses of the vertical and horizontal macroblocks in the frame, respectively, and V_NMB and H_NMB represent the numbers of the vertical and horizontal macroblocks in the frame. The two-dimensional array M [i] [j] here is an array for storing information as to whether or not each macroblock is a specific color macroblock.
E indicates a specific color macroblock.

First, the result of static / dynamic determination for each macroblock will be examined. (S403) The two-dimensional array M [i] [j] is already
The static / movement determination result is stored by the macroblock static / movement determination process (S101). TRUE indicates a moving macroblock, and FALSE indicates a stationary macroblock. If the value of the two-dimensional array M [i] [j] is FAL
SE, that is, if the macroblock is a still macroblock, the macroblock does nothing and goes to the next macroblock.
If the value of the two-dimensional array M [i] [j] is TURE, that is, if it is a moving macroblock, it is checked whether the pixel value of the macroblock is within the range of the color space specified by the specific color specifying unit. I do. (S405) If
If not, it is determined that there is no specific color in the moving macroblock, that is, the newly rewritten macroblock, and is rewritten to FALSE. (S406) The specific color specification unit 114 specifies the range of the color space of the color to be detected. If the color is known in advance, Y
It can be specified directly on the CbCr color space. Here, D1 to D6 are threshold values.

(Equation 1) As another method of specifying a specific color, there is a method in which a user sets a color range in an RGB color space, and the range is converted into YCbCr using Expression (2) and determined.

(Equation 2) As another method of specifying a specific color, there is also a method of converting the YCbCr color space being coded into an RGB space using Expression (3), and detecting the RGB space in Expression (4). .

(Equation 3)

(Equation 4) As described above, if a range that can be distinguished in an appropriate color space can be designated, it can be executed by any method.

FIGS. 6 to 8 show the specific color object inclusion processing (S1).
02). Here, n is a counter indicating the number of specific color objects, S1 to S4 are parameters indicating a search range of a rectangle including the specific color object, and S1 and S2 are the starting points of the vertical address. This is the end point, and S3 and S4 are the start point and end point of the address in the horizontal direction.

In the flowchart of FIG. 6, initialization is performed so that the entire frame is designated as a search range. (S501) Next, a function Rectangular for searching for the smallest rectangle including the specific color object in the specified search range is called. (S502) The flowcharts of FIGS. 7 and 8 show the function Rectangular.
The content of the process of (S502) is shown. Function Rect
angular receives as input a search range S1 to S4, n indicating the number of specific color objects, and a two-dimensional array M storing static / movement determination results of each macroblock, and stores a rectangular address of the search results. The dimensional arrays B1 to B4 and n indicating the number of specific color objects are output.

Here, the one-dimensional array HV is a work array for creating a histogram of the number of moving macroblocks in the vertical direction, and the one-dimensional array HH creates a histogram of the number of moving macroblocks in the horizontal direction. It is a work arrangement to perform. The variable VFLAG becomes TRUE when the value of the histogram in the horizontal direction is not 0, and the value VFLAG becomes 0.
The flag HFLAG is set to TRUE when the value of the vertical histogram is not 0, and is set to FALSE when the value is 0.
This flag is changed to be LSE.

First, the range of S1 to S2, which is the search range of the work array HV for creating a histogram of the number of moving macroblocks in the vertical direction, is initialized with a value of 0. (S60
1) In the next double loop of LOOP1 and LOOP2, a histogram of the number of moving macroblocks in the vertical direction in the search range is created. That is, the values of the static / movement determination result M [i] [j] for each macroblock are compared (S604), and
URE, that is, if it is a moving macroblock, HV [i]
Is incremented by 1 (S605), and in the case of FALSE, an operation is performed in which nothing is performed.

Next, a non-zero continuous portion is searched from the histogram in the vertical direction. First, the flag V
Set FLAG to FALSE. (S608) Next, in the order of the search range S1 to S2, the histogram HV
Is not 0 and VFLAG is FALSE. (S610) The condition that satisfies this condition is the start point of a continuous portion where the histogram is not zero.
Therefore, since it is a candidate for the starting point in the vertical direction of the rectangle being searched, the address i is stored in the one-dimensional array B1 [n], and VFLAG is set to TURE. (S611) Next, it is checked whether the histogram HV is 0 or VFLAG is TURE at the end point of the search range.
(S612) The condition corresponding to this condition is the end point of a continuous portion where the histogram is not zero. Therefore,
If the histogram HV is 0, the address i-1 is stored in the one-dimensional array B2 [n] (S614). The address i is stored in the one-dimensional array B2 [n]. (S615) Then, the VFLAG is reset to FA again.
Set to LSE. (S611) FIG. 8 is a continuation of the flowchart of FIG. This time, the range of S3 to S4, which is the search range of the working array HV for creating a histogram of the number of moving macroblocks in the horizontal direction, is initialized with a value of 0. (S617) Next LOOP4 and LOO
In the double loop of P5, a histogram of the number of moving macroblocks in the horizontal direction in the search range is created. That is, the value of the static / movement determination result M [i] [j] for each macroblock is compared (S604), and if the value is TURE, that is, if the value is a moving macroblock, HH [i] is incremented by one (S60).
5) In the case of FALSE, an operation of doing nothing is performed.

Next, a continuous portion other than 0 is searched from the horizontal histogram. First, the flag H
Set FLAG to FALSE. (S624) Next, in the order of the search ranges S3 to S4, the histogram HH
Is not 0 and HFLAG is FALSE. (S626) The condition that satisfies this condition is the start point of a continuous portion where the histogram is not zero.
Therefore, since it becomes a candidate of the horizontal start point of the rectangle being searched, the address j is stored in the one-dimensional array B3 [n], and HFLAG is set to TURE. (S627) Next, it is checked whether the histogram HH is 0 or HFLAG is TURE at the end point of the search range.
(S628) The condition that satisfies this condition is the end point of a continuous portion where the histogram is not zero. Therefore,
If the histogram HH is 0, the address j-1 is stored in the one-dimensional array B4 [n] (S630). The address j is stored in the one-dimensional array B4 [n]. (S631) Then, HFLAG is restored to FA again.
Set to LSE. (S632) Here, the search using one vertical and horizontal histogram has been completed, but the search results B1 [n] to B4
It is checked whether [n] matches the search ranges S1 to S4 (S633). If they match, there is no more search range, so it can be determined that the smallest rectangle has been found. (S634) Then, n representing the number of specific color objects
Is increased by 1 (S635), and the process proceeds to the search for the next specific color object. If the search results B1 [n] to B4 [n] do not match the search ranges S1 to S4, there are still a plurality of specific color objects in the search result range.
[N] to B4 [n] are transferred to S1 to S4 (S63
7) Call the function Rectangular again.
(S637) FIG. 9 is an example of the determination result of the specific color object determination unit 113. Here, two specific color objects were determined. As shown in the figure, the result of each determination is that, in this example, the origin of the address of the macro book is at the upper left of the frame, and B1
The specific color object is determined in an arrangement such as [0] to B4 [0] and B1 [1] to B4 [1].

The specific color object synthesizing display unit 115 creates an image in which the area of the specific color object determined by the specific color object determination unit 113 and the reproduced moving image signal are synthesized. FIG. 10 is a specific flowchart. Here, n indicates the number of specific color objects in the frame obtained by the specific color object determination unit 113. As the processing flow, B1 [i] for each specific color object
Since B4 [i] represents a rectangular macroblock of a specific color object, a rectangular white line surrounding the macroblock is drawn and combined with the reproduced image. (S602) FIG. 11 is an example of an image created by the specific color object synthesis display unit. (Second Embodiment) FIGS. 12 and 13 show a second embodiment of the present invention.
It is a block diagram which shows the structure of the moving image specific color object detection apparatus of embodiment. In this embodiment, the specific color object detection unit is combined with a moving image encoding unit.

In FIG. 12, an input moving image signal is divided into macro blocks by a blocking circuit 201. An input video signal divided into macro blocks is input to a subtractor 20.
2, and a difference from the predicted image signal is calculated to generate a predicted residual signal. One of the prediction residual signal and one of the input video signals from the blocking circuit 201 is
The signal is selected by a mode selection switch 203 and is subjected to a discrete cosine transform by a DCT (discrete cosine transform) circuit 204. The DCT coefficient data obtained by the DCT circuit 204 is
The quantization is performed by the quantization circuit 205. The signal quantized by the quantizer 205 is branched into two, and one of the signals is subjected to variable-length encoding by a variable-length encoding circuit 215.

On the other hand, the other of the signals quantized and bifurcated by the quantization circuit 205 is supplied to the inverse quantization circuit 206 and the IDC.
After the inverse discrete cosine transform (T) circuit 207 sequentially receives the inverse processing of the processing of the quantization circuit 205 and the DCT circuit 204, the adder 208 adds the predicted image signal input via the switch 211. As a result, a locally decoded signal is generated. This local decoded signal is stored in the frame memory 209 and input to the motion compensation circuit 210. The motion compensation circuit 210 generates a predicted image signal and sends necessary information to the mode selection circuit 203.

The mode selection circuit 212 selects a macroblock for performing inter-frame coding and a macroblock for performing intra-frame coding based on the prediction information P from the motion compensation circuit 210 in macroblock units. When performing intra-frame coding (intra coding),
The mode selection switch information M is A, and the switch information S is A. When performing inter-frame coding (inter coding), the mode selection switch information M is set to B, and the switch information S is set to B. The mode selection switch 203 changes the switch based on the mode selection switch information P, and the switch 216 changes the switch based on the switch information S.

The modes include an intra mode (INTRA), an inter mode (INTER), and a non-coding mode (NOT_CODED), which are associated with each macroblock, and the INTRA macroblock is subjected to intra-frame coding. Image area, INTER macroblock is an image area to be inter-coded, NOT
The macroblock of _CODED is an image area that does not require encoding.

On the other hand, in the specific color object detecting section 222, first, the mode information, motion vector information, and DCT coefficient information input to the variable length coding section 214 are input to the macroblock static / motion determining section, and the determination result is obtained. Is input to the specific color object determination unit 220. The result determined by the specific color object determination unit 220 is input to the specific color object synthesis display unit and to the multiplexing unit 215 of the video encoding unit 218. The specific color object synthesizing unit 221 generates an image in which the local decoded signal generated by the moving image encoding unit and the specific color object are synthesized, and outputs the image as a local reproduction signal. Note that the macroblock still / movement determination unit 219 and the specific color object determination unit 22
0, the specific processing content of the specific color object synthesis display unit 221 is the same as the processing in FIGS. 2 to 11 in the first embodiment.

In the encoding control circuit 214, the encoding section 21
The encoding unit 217 is controlled based on the encoding information of No. 8 and the buffer amount of the output buffer 216. Variable length coding circuit 21
The encoded data encoded in the specific color object determination unit 2
Multiplexing circuit 2 together with the specific color object determination result from
The data is multiplexed at 16 and the transmission rate is smoothed at the output buffer 217 and sent to the transmission system or storage system as encoded data.

FIG. 13 is a block diagram on the decoding side with respect to the encoding side in FIG.

First, in the moving picture decoding unit 310,
First, encoded data received from a transmission path or a storage system is once stored in an input buffer 301, separated by a demultiplexing unit 302 on a frame-by-frame basis based on syntax, and output to a variable-length decoding unit 303. The variable length decoding unit 303 decodes a variable length code of information of each syntax.

If the macroblock mode is INTRA in the variable length decoding section 303, the mode changeover switch 309 is turned off, and the quantized DCT coefficient information decoded by the variable length decoding section 303 is inverted. Quantizer 304
The IDCT unit 305 performs an inverse discrete cosine transform to generate a reproduced image signal. The reproduced image signal is stored in the frame memory 307 as a reference image, and is input to the specific color object synthesis display unit 311 in the specific color object detection unit 115.

In the variable length decoding unit 303, if the mode of the macroblock is INTER or NOT_CODED, the mode changeover switch 309 is selected to be off, and the quantized DCT coefficient information decoded by the variable length decoding unit 303 is , And inversely quantized by the inverse quantization unit 304, and the IDCT unit 3
05, performs an inverse discrete cosine transform process, and based on the motion vector information decoded by the variable length decoding unit 303, performs motion compensation on the reference image in a motion compensation unit 308,
The addition is performed by the adder 306 to generate a reproduced image signal. The reproduced image signal is stored in the frame memory 307 as a reference image, while the specific color object composite display unit 31
1 is input.

On the other hand, the specific color object determination result separated by the multiplexing / demultiplexing unit is input to the specific color object synthesis display unit 311 and operates according to the flowchart of FIG.

As described above, in the embodiment, an example in which processing is performed in units of macroblocks has been described. However, it goes without saying that the same method can be applied to processing in a smaller unit or processing in a larger unit.

Although an example of a method using DCT has been described as a moving picture coding method, a similar method can be used in other transform methods such as Wavelet transform.

[0047]

As described above, according to the present invention,
It is possible to provide a moving image specific color detecting device and a moving image specific color detecting method capable of detecting a specific color object at high speed and stably with high accuracy.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a moving image specific color object detection device according to a first embodiment of the present invention.

FIG. 2 is a flowchart showing the operation of a specific color object detection unit of the present invention.

FIG. 3 is a flowchart showing the operation of a macroblock still / movement determination unit according to the present invention.

FIG. 4 is a flowchart showing the operation of the specific color object determination unit of the present invention.

FIG. 5 is a flowchart showing an operation of noise processing of the specific color object determination unit of the present invention.

FIG. 6 is a flowchart showing an operation of a specific color object inclusion process of the specific color object determination unit of the present invention.

FIG. 7 is a flowchart showing an operation of a specific color object inclusion process of the specific color object determination unit of the present invention.

FIG. 8 is a flowchart showing an operation of a specific color object inclusion process of the specific color object determination unit of the present invention.

FIG. 9 is a diagram illustrating an example of a determination result of a specific color object determination unit according to the present invention.

FIG. 10 is a flowchart showing the operation of the specific color object synthesis display unit of the present invention.

FIG. 11 is a diagram showing an example of a display result of the specific color object determination unit of the present invention.

FIG. 12 is a block diagram showing a configuration on an encoding side of a moving image specific color object detection device according to a second embodiment of the present invention.

FIG. 13 is a block diagram showing the configuration on the decoding side of the moving image specific color object detection device according to the second embodiment of the present invention.

[Explanation of symbols]

 Reference Signs List 101 input buffer 102 demultiplexing unit 103 variable length decoding unit 104 inverse quantization unit 105 IDCT unit 106 adder 107 frame memory 108 motion compensation unit 109 mode switching switch 110 moving image decoding Conversion unit 111 macroblock static / motion determination unit 112 subtractor 113 specific color object determination unit 114 specific color designation unit 115 specific color object synthesis display unit 116 specific color object detection unit 201 blocking circuit 202 subtraction Unit 203: Mode selection switch 204 ... DCT circuit 205 ... Quantization circuit 206 ... Inverse quantization circuit 207 ... IDCT circuit 208 ... Adder 209 ... Frame memory 210 ... Motion compensation circuit 211 ... Switch 212 ... Mode selection circuit 213 ... Encoding Control circuit 214 ... Variable length coding circuit 215 ... Multiplexing circuit 216 ... Output buffer 217: Encoding unit 218: Moving image encoding unit 219: Macroblock still / moving determining unit 220: Specific color object determining unit 221: Specific color specifying unit 222: Specific color object combining display unit 223: Specific color object detecting unit 301 input buffer 302 demultiplexing unit 303 variable length decoding unit 304 inverse quantization unit 305 IDCT unit 306 adder 307 frame memory 308 motion compensation unit 309 mode switching switch 310 moving image decoding Conversion unit 311: specific color object synthesis display unit

────────────────────────────────────────────────── ─── Continuation of front page (72) Yoshifumi Nakamura, Inventor 1 Toshiba-cho, Fuchu-shi, Tokyo Toshiba Corporation Fuchu Plant (58) Fields investigated (Int. Cl. ⁷ , DB name) H04N 11/00- 11/22 H04N 9/44-9/78

Claims (7)

(57) [Claims] 1. An apparatus for detecting a specific color in a moving image, comprising: moving image decoding means for decoding encoded data obtained by compressing the moving image; and a specific color object detecting means, wherein the specific color object detecting means is provided. Means for determining, for each block decoded by the moving image decoding means, whether an image in the block is in a still state or a moving state based on a decoding result; A moving image identification unit comprising: a unit for judging an object; and a unit for combining and displaying an image indicating an area determined to be a specific color object with a reproduced image signal created by the moving image decoding unit. Color detection device. 2. The moving image specific color object detecting device according to claim 1, wherein the means for determining whether the image in the block is still or moving from the decoding result for each decoded block is a moving image decoding unit. Determining whether a block is in a stationary state or a moving state from the decoded mode information for each block, motion vector information, transform coefficient information, and the difference between the current reproduced image signal and the reproduced image one frame before. A moving image specific color detection device characterized by the above-mentioned. 3. A device for detecting a specific color object in a moving image, a moving image encoding means for encoding and compressing the moving image, a specific color object detecting means, and decoding the encoded data obtained by compressing the moving image. The specific color object detecting means determines, for each block coded by the moving image coding means, whether the image in the block is in a still state or a moving state from the coding result. Means for determining a specific color object of a moving block from the still / moving determination result for each block; and the moving image encoding means multiplexes the determination result of the specific color object with encoded data and transmits the multiplexed result. Wherein the moving image decoding means decodes the encoded data, and synthesizes and displays a reproduced image signal and an image indicating an area determined to be a specific color object. Color detection device. 4. The moving image specific color object detecting device according to claim 3, wherein for each of the encoded blocks, the means for determining whether an image in the block is in a still state or a moving state from an encoding result.
Based on the mode information for each block, motion vector information, transform coefficient information, and the difference between the current input moving image signal and the locally decoded image one frame before, whether the block is in a stationary state, is determined by the moving image encoding means. A moving image specific color detecting device for determining whether the moving image is in a moving state. 5. The moving image specific color object detecting device according to claim 3, wherein the determined area of the specific color object is synthesized and displayed with a moving image encoding unit and a local image signal generated by the moving image encoding unit. A moving image specific color detecting device comprising: 6. A moving image specific color object detecting device according to claim 3, wherein the means for determining the specific color object from the result of the still / moving determination for each block includes a block in which the image in the block is in a moving state. A moving image specific color detection device, wherein a specific color object is determined based on a figure to be processed. 7. A decoding step of decoding the compressed coded data a moving image, the image determining whether stationary state or moving state of the block for each block from the decoding result decoded by the decoding step When, determining a particular color object block of the dynamic state from the movement determination result for each block, reproduced image signal created an image showing a region of a specific color object as determined by the moving image decoding step and synthesis step of generating a new reproduced image signal
Moving image specified color detection method characterized by having a flop.