WO2020027511A1

WO2020027511A1 - Method for generating syntax-based heat-map for compressed image

Info

Publication number: WO2020027511A1
Application number: PCT/KR2019/009372
Authority: WO
Inventors: 이현우; 정승훈; 이성진
Original assignee: 이노뎁 주식회사
Priority date: 2018-07-30
Filing date: 2019-07-29
Publication date: 2020-02-06
Also published as: KR102042397B1

Abstract

The present invention generally relates to a technology for effectively generating a heat-map from a compressed image such as H.264 AVC or H.265 HEVC. More specifically, the present invention relates to a technology that can generate a heat-map with a small number of operations, by extracting a region having some significant motion in an image, that is, a moving object region, by using a syntax (e.g., a motion vector, a coding type) obtained by parsing compressed image data and accumulating a trajectory of the moving object region, instead of generating a heat-map through complex image processing, as in the prior art, for a compressed image generated by, for example, a CCTV camera. According to the present invention, there is an advantage in that a heat-map can be effectively generated from a compressed CCTV image without complex processing such as decoding, downscale resizing, difference image acquisition, image analysis, or the like. In particular, it is possible to generate a heat-map by using about 1/10 of the operation quantity of the prior art, and thus there is an advantage in that the number of available analysis channels of an image analysis server can be increased by about 10 times or more.

Description

Syntax-based Heatmap Generation Method for Compressed Images

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention generally relates to techniques for efficiently generating heat maps from compressed images such as H.264 AVC and H.265 HEVC.

More specifically, the present invention provides a syntax (eg, a motion vector, for example) obtained by parsing compressed image data instead of generating a heat map through a complex image processing, for example, for a compressed image generated by a CCTV camera. The present invention relates to a technology that can generate a heat map with a small number of operations by extracting a region in which something meaningful movement exists in an image, that is, a moving object region, and accumulating a trajectory of the moving object region using a coding type.

There is a field that analyzes what patterns of behaviors of a large number of people have shown in a specific space and draws meaningful information through them. For example, by analyzing customers' movements and interests within the store, they can gain valuable data for sales and marketing decisions. This data collection method can collect customer interests directly through interviews, membership cards, salespeople, or indirectly through CCTV cameras, sensors, and smartphone apps.

As such, there is a heat-map as a way of visually representing people's movements and interests in a specific space. Heat maps combine heat (heat) and map (map) to represent information in a thermal distribution. Such a heat map may express people's movements or interests in a color step in a camera image. People's movements are accumulated for a certain unit of time and colors are displayed according to the accumulated degree. In general, the areas in which people's movements are accumulated are expressed in red, and the areas in which people's movements are accumulated are represented in blue, so that they are consistent with the feeling of temperature.

For example, heat maps from images taken from store CCTV cameras allow store managers to intuitively identify which products are of interest to customers and vice versa by using heat maps. have. Based on this information, it is possible to decide whether to change the arrangement of goods in the store, to change the price policy or to establish a sale event policy in consideration of the actual purchase rate. In addition, heat maps obtained from images taken by alleyway CCTV cameras can be used to identify the paths that people are moving along the alleys.

Hereinafter, a process of generating a heat map from a CCTV compressed image in the prior art will be described with reference to FIGS. 1 and 2.

Recently installed CCTV cameras adopt high resolution (e.g. Full HD) and high frame rate (e.g. 24 frames per second), so that H.264 AVC and H.265 HEVC take into account the burden of network bandwidth and storage space. High compression ratio complex image compression technology such as is being adopted. The CCTV camera device generates and provides a compressed image, and the device for reproducing the video decodes the compressed image in reverse according to the technical specifications. In order to determine the existence and movement of an object in a CCTV image to which image compression technology is applied, conventionally, a process of processing an image after decoding a compressed image and obtaining a reproduced image, that is, an original image that has been decompressed, is required.

1 is a block diagram illustrating a general configuration of a video decoding apparatus according to the H.264 AVC Technical Specification. Referring to FIG. 1, a video decoding apparatus according to H.264 AVC includes a parser 11, an entropy decoder 12, an inverse converter 13, a motion vector operator 14, a predictor 15, and a deblocking filter ( 16) is configured to include. These hardware modules sequentially process the data of the compressed image to decompress the compressed image and restore the original image data. At this time, the parser 11 parses the motion vector and the coding type for the coding unit of the compressed image. Such a coding unit is generally an image block such as a macroblock or a subblock.

2 is a flowchart illustrating a process of generating a heat map from a compressed image in a conventional image analysis solution.

First, a compressed image is decoded according to a video standard such as H.264 AVC and H.265 HEVC to obtain a reproduced image (S10), and the frame images constituting the reproduced image are downscaled to a small image, for example, 320x240. (S20). The reason for this downscaling resizing process is to slightly reduce the processing burden in the subsequent process. Then, after obtaining differential images of the resized frame images, the moving objects existing in the compressed image are extracted through image analysis, and the coordinates of the moving objects are extracted (S30). Then, the heat map is generated by accumulating the trajectories of the moving objects through image analysis of a series of frame images over time (S40).

In the prior art, a moving object is extracted to generate a heat map. To extract a moving object from a high resolution compressed image, compressed image decoding, downscale resizing, and image analysis are performed. These are very complicated processes, and therefore, in a conventional video control system, the capacity that a single video analysis server can process simultaneously is quite limited. Currently, CCTV channels that can be covered by high-performance video analytics servers are typically up to 20 channels. Therefore, in order to generate heat maps for compressed images generated from CCTV cameras installed at various points, a plurality of image analysis servers were required, which caused an increase in cost and difficulty in securing physical space.

SUMMARY OF THE INVENTION An object of the present invention is to provide a technique for effectively generating heat maps from compressed images such as H.264 AVC and H.265 HEVC.

In particular, an object of the present invention is syntax (e.g., motion vector, coding) obtained by parsing compressed image data, rather than generating a heat map for a compressed image generated by a CCTV camera, for example, through complex image processing. It is to provide a technology that can generate a heat map with a small number of operations by extracting a region in which there is something meaningful movement in the image, that is, a moving object region and accumulating the trajectory of the moving object region.

The present invention is to achieve the above object, the syntax-based heat map generation method for a compressed image according to the present invention, parsing the bitstream of the compressed image to obtain a motion vector and coding type for the coding unit Stage 1; A second step of obtaining a motion vector cumulative value for a predetermined time for each of the plurality of image blocks constituting the compressed image; A third step of comparing a motion vector cumulative value with a first threshold value for a plurality of image blocks; A fourth step of marking an image block having a motion vector accumulation value exceeding a first threshold as a moving object region; And a fifth step of generating a heat map for the compressed image by accumulating a moving object region over a series of image frames of the compressed image.

In this case, the fifth step may include: identifying a plurality of moving object areas marked above in a series of image frames constituting the compressed image; Calculating a representative position with respect to the plurality of moving object regions; A fifth step of calculating hit data by accumulating the calculated plurality of representative positions; And a fifth step of generating a heat map for the compressed image based on the hit data.

In the fifth step, a unique ID is newly issued and assigned to a plurality of moving object areas identified above in a series of video frames constituting the compressed image, and assigned to the moving object areas identified as unassigned. A fifth step of revoking a unique ID for the moving object region disappearing from the image frame in an ID allocation state; A fifth step of deriving a movement trajectory for each unique ID by aligning the calculated representative positions by a unique ID reference; And a fifth step of reinforcing the hit data by accumulating the movement trajectories for each Unique ID.

In addition, the method of generating a heat map according to the present invention may include: a) identifying a plurality of adjacent image blocks (hereinafter, referred to as 'neighbor blocks') around a moving object area; B) comparing a motion vector value with a second preset threshold value for a plurality of neighboring blocks; C) additionally marking a neighboring block having a motion vector value exceeding a second threshold as a moving object region; D) additionally marking a neighboring block having a coding type of an intra picture among the plurality of neighboring blocks as a moving object region; The method may further include an e-step of performing interpolation on the plurality of moving object regions to additionally mark a predetermined number or less of unmarked image blocks surrounded by the moving object region as the moving object region.

On the other hand, the computer program according to the present invention is stored in the medium in combination with hardware to execute the syntax-based heat map generation method for the compressed image as described above.

According to the present invention, there is an advantage in that a heat map can be efficiently generated from a CCTV compressed image without complex processing such as decoding, downscale resizing, difference image acquisition, image analysis, and the like. In particular, it is possible to generate a heat map with a calculation amount of about 1/10 of the prior art, which has the advantage of increasing the number of available analysis channels of the image analysis server by about 10 times or more.

1 is a block diagram showing a general configuration of a video decoding apparatus.

2 is a flowchart illustrating a process of generating a heat map from a compressed image in the prior art.

3 is a flowchart illustrating an entire process of a syntax based heatmap generation process for a compressed image according to the present invention.

4 is a flowchart illustrating an embodiment of a process of detecting effective motion from a compressed image in the present invention.

5 is a diagram illustrating an example of a result of applying an effective motion region detection process according to the present invention to a CCTV compressed image.

FIG. 6 is a flowchart illustrating an example of a process of detecting a boundary region for a moving object region in the present invention. FIG.

7 is a diagram illustrating an example of a result of applying a boundary area detection process according to the present invention to the CCTV image of FIG.

8 is a diagram illustrating an example of a result of arranging a moving object region through interpolation with respect to the CCTV image of FIG. 7.

9 is a flowchart illustrating an embodiment of a process of generating a heat map from a moving object region detected in a compressed image according to the present invention.

FIG. 10 is a diagram for one example in which a unique ID is assigned to a moving object area in the present invention; FIG.

11 is a view showing an example in which the center coordinates are set in the moving object area in the present invention.

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

3 is a flowchart illustrating an entire process of a syntax based heatmap generation process for a compressed image according to the present invention. In the heat map generation process according to the present invention, an image analysis server may be preferably performed in a system for handling compressed images, for example, a CCTV image control system or a CCTV image analysis system.

The present invention parses a bitstream of a compressed image without having to decode the compressed image, thereby syntax information of each image block, that is, a macro block and a sub block, preferably a motion vector. Quickly extract the moving object region using the and coding type information. The moving object region thus obtained does not accurately reflect the boundary of the moving object as shown in the image attached to the present specification, but exhibits a certain level of reliability even though the processing speed is high. Then, the present invention generates a heat map for the space by accumulating the information of the moving object region thus obtained.

Meanwhile, according to the present invention, the moving object region can be extracted and the heat map can be generated without decoding the compressed image. However, the apparatus or software to which the present invention is applied should not perform the operation of decoding the compressed image, but the scope of the present invention is not limited.

Hereinafter, a process of generating a heat map from a compressed image according to the present invention will be described with reference to FIG. 3.

Step S100: First, an effective motion that can be substantially recognized from the compressed image is detected from the compressed image based on the motion vector of the compressed image, and the image region in which the effective motion is detected is set as the moving object region.

To this end, the motion vector and coding type of a coding unit of a compressed image are parsed according to a video compression standard such as H.264 AVC and H.265 HEVC. In this case, the size of the coding unit is generally about 64x64 to 4x4 pixels and may be set to be flexible.

The motion vectors are accumulated for a predetermined time period (for example, 500 msec) for each image block, and it is checked whether the motion vector accumulation value exceeds the first predetermined threshold (for example, 20). If such an image block is found, it is considered that effective motion has been found in the image block and marked as a moving object area. Accordingly, even if the motion vector is generated, if the cumulative value for a predetermined time does not exceed the first threshold, the image change is assumed to be insignificant and ignored.

Step S200: Detects how far the boundary region is to the moving object region detected in S100 based on the motion vector and the coding type. If a motion vector occurs above a second threshold (for example, 0) or a coding type is an intra picture by inspecting a plurality of adjacent image blocks centered on the image block marked as a moving object area, the corresponding image block is also moved. Mark as an object area. Through this process, the corresponding image block is substantially in the form of forming a lump with the moving object region detected in S100.

If an effective motion is found and there is a certain amount of motion in the vicinity of the moving object area, it is marked as a moving object area because it is likely to be a mass with the previous moving object area. In addition, in the case of an intra picture, since a motion vector does not exist, determination based on a motion vector is impossible. Accordingly, the intra picture located adjacent to the image block already detected as the moving object region is estimated as a mass together with the previously extracted moving object region.

Step S300: The interpolation is applied to the moving object areas detected at S100 and S200 to clean up the fragmentation of the moving object area. In the above process, since it is determined whether the moving object area is the image block unit, even though it is actually a moving object (for example, a person), there is an image block that is not marked as the moving object area in the middle. The phenomenon of dividing into may occur. Accordingly, if there are one or a few unmarked image blocks surrounded by a plurality of image blocks marked with the moving object region, they additionally mark the moving object region. By doing so, it is possible to make the mobile object region divided into several into one. The influence of such interpolation is clearly seen when comparing FIG. 7 and FIG.

Step S400: The moving object region is quickly extracted from each frame image constituting the compressed image based on the syntax (motion vector, coding type) of the coding unit through the above process. In operation S400, a heat map of the corresponding image is generated by using the extracted result of the moving object region.

To this end, the present invention accumulates the extraction result of the moving object region over a series of image frames to estimate how frequently the moving object is found for each region in the image and thereby generates a heat map. In this case, the detection itself of the moving object region may be accumulated or the movement trajectories of the moving object region may be accumulated. A detailed process of generating a heat map from the extraction result of the moving object region will be described later in detail with reference to FIG. 9.

4 is a flowchart illustrating an example of a process of detecting effective motion from a compressed image in the present invention, and FIG. 5 is a diagram illustrating an example of a result of applying the effective motion region detection process according to the present invention to a CCTV compressed image. . The process of FIG. 4 corresponds to step S100 in FIG. 3.

Step S110: First, a coding unit of a compressed image is parsed to obtain a motion vector and a coding type. Referring to FIG. 1, a video decoding apparatus performs parsing (header parsing) and motion vector operations on a stream of compressed video according to a video compression standard such as H.264 AVC and H.265 HEVC. Through this process, the motion vector and coding type are parsed for the coding unit of the compressed image.

Step S120: Acquire a motion vector cumulative value for a preset time (for example, 500 ms) for each of the plurality of image blocks constituting the compressed image.

This step is presented with the intention to detect if there are effective movements that are practically recognizable from the compressed image, such as driving cars, running people, and fighting crowds. Shaky leaves, ghosts that appear momentarily, and shadows that change slightly due to light reflections, though they are moving, are virtually meaningless objects and should not be detected.

To this end, a motion vector cumulative value is obtained by accumulating a motion vector in units of one or more image blocks for a predetermined time period (for example, 500 msec). In this case, the image block is used as a concept including a macroblock and a subblock.

Steps S130 and S140: Comparing a motion vector cumulative value with respect to a plurality of image blocks with a preset first threshold value (eg, 20), and moving the image block having a motion vector cumulative value exceeding the first threshold value. Mark with

If an image block having a predetermined motion vector accumulation value is found as described above, it is considered that something significant movement, that is, effective movement, is found in the image block and is marked as a moving object region. For example, in a video surveillance system, a human run is to select and detect a movement that is worth the attention of the control personnel. On the contrary, even if a motion vector is generated, if the cumulative value for a predetermined time is small enough not to exceed the first threshold, the change in the image is assumed to be small and insignificant and is neglected in the detection step.

FIG. 5 is an example illustrating a result of detecting an effective motion region from a CCTV compressed image through the process of FIG. 4. In FIG. 5, an image block having a motion vector accumulation value equal to or greater than a first threshold value is marked as a moving object area and displayed as a bold line area. Referring to FIG. 5, the sidewalk block, the road, and the shadowed part are not displayed as the moving object area, while the walking people or the driving car are displayed as the moving object area.

FIG. 6 is a flowchart illustrating an example of a process of detecting a boundary region of a moving object region in the present invention, and FIG. 7 is a boundary region of FIG. 5 with respect to the CCTV image of FIG. Figure 1 shows an example of the results of further applying the detection process. The process of FIG. 6 corresponds to step S200 in FIG. 3.

Referring to FIG. 5, it can be found that the moving object is not properly marked and only a portion of the moving object is marked. In other words, if you look at a person walking or driving a car, you will find that not all of the objects are marked, but only some blocks. In addition, it is also found that a plurality of moving object areas are marked for one moving object. This means that the criterion of the moving object region adopted in S100 was very useful for filtering out the general region but was quite strict. Therefore, it is necessary to detect the boundary of the moving object by looking around the moving object area.

Step S210: First, a plurality of adjacent image blocks are identified based on the image blocks marked as moving object areas by the previous S100. In the present specification, these are referred to as 'neighborhood blocks'. These neighboring blocks are portions that are not marked as the moving object region by S100, and the process of FIG. 6 examines them further to determine whether any of these neighboring blocks may be included in the boundary of the moving object region.

Steps S220 and S230: compare a motion vector value with respect to a plurality of neighboring blocks with a second preset threshold (eg, 0), and mark the neighboring block having a motion vector value exceeding the second threshold as a moving object region. do. If the movement is located adjacent to the area of the moving object where effective motion that is practically meaningful is found and a certain amount of movement is found for itself, the image block is likely to be a block with the area of the adjacent moving object due to the characteristics of the photographed image. . Therefore, such neighboring blocks are also marked as moving object regions.

Step S240: Also, the coding type is an intra picture among the plurality of neighboring blocks as a moving object region. In the case of an intra picture, since a motion vector does not exist, it is fundamentally impossible to determine whether a motion exists in a corresponding neighboring block based on the motion vector. In this case, it is safer for the intra picture located adjacent to the image block already detected as the moving object region to maintain the settings of the previously extracted moving object region.

FIG. 7 is a diagram illustrating a result of applying a boundary region detection process to a CCTV compressed image. In the above process, a plurality of image blocks marked as a moving object region are displayed as an area of a bold line. Referring to FIG. 7, the moving object area indicated by the bold line area was further extended near the moving object area indicated by the bold line area in FIG. 5 to cover the entire moving object when compared with the image captured by CCTV. You can find that it is enough.

FIG. 8 is a diagram illustrating an example of a result of arranging a moving object region through interpolation according to the present invention for a CCTV image image to which the boundary region detection process illustrated in FIG. 7 is applied.

Step S300 is a process of arranging the division of the moving object area by applying interpolation to the moving object areas detected in the previous steps S100 and S200. Referring to FIG. 7, an unmarked image block is found between the moving object regions indicated by the bold lines. If there is an unmarked image block in the middle, it can be regarded as if they are a plurality of individual moving objects. If the moving object region is fragmented as described above, the result of step S400 may be inaccurate, and the number of moving object regions may increase, thereby complicating the process of step S400.

Accordingly, in the present invention, if there is one or a few unmarked image blocks surrounded by a plurality of image blocks marked as the moving object region, this is marked as the moving object region, which is called interpolation. Referring to FIG. 8, in contrast to FIG. 7, all of the non-marked image blocks existing between the moving object regions are marked as moving object regions. By doing this, all the moving areas are bundled together and treated as a moving object.

Comparing FIG. 5 and FIG. 8, it can be found that the moving object region properly reflects the actual image situation through the boundary region detection process and the interpolation process. In FIG. 5, if it is judged as a lump marked with a bold line, it will be treated as if a lot of very small objects move in the image screen, which does not correspond to reality. On the other hand, if it is determined as a block marked with a bold line in Fig. 8 will be treated as having a few moving objects having a certain volume, similarly reflects the actual scene.

FIG. 9 is a flowchart illustrating an example of a process of generating a heat map from a moving object region detected in a compressed image according to the present invention, and corresponds to step S400 of FIG. 3.

As described above, the present invention extracts a moving object region based on syntax information directly obtained from a compressed image. The process of acquiring and analyzing the difference image of the original image by decoding the compressed image of the prior art is unnecessary, and according to the inventor's test, the processing speed is improved by up to 20 times. However, this approach has the disadvantage of poor precision. There is a difference in concept in that it extracts the chunk of the image block that is assumed to contain the moving object, rather than extracting the moving object. In the present invention, the process of generating the heat map also reflects these structural features.

Hereinafter, an embodiment of a heat map generation process adopted in the present invention will be described in detail.

Steps S410 and S420: Identify a plurality of moving object regions from a series of image frames constituting the compressed image. For example, if the heat map is generated from the compressed image for 10 minutes taken at 24 frames per second, the image of 14,400 frames in total through the process of steps S100 to S300 of FIG. Identifies a number of moving object areas, such as those indicated by bold lines in 8.

Representative coordinates are then calculated for the plurality of moving object regions identified in this manner, each of which represents a position within the frame image. As the representative coordinates, as shown in FIG. 11, center coordinates (cx1, cy1; cx2, cy2; cx3, cy3) for a virtual optimal rectangle surrounding the moving object region may be used.

Step S430: Then, by accumulating a plurality of representative coordinates derived from a series of image frames in image block units, heat data reflecting the frequency of appearance of the moving object in the space is calculated. Although it is possible to generate a heat map using the heat data calculated in step S430, it is preferable to generate the heat map after reinforcing the heat data through the following steps S440 to S470. In addition, according to the exemplary embodiment, a heat map may be generated by excluding the heat data calculation process of step S430 and calculating the heat data through steps S440 to S470 from the beginning.

Steps S440 and S450: A unique ID is allocated to a plurality of moving object areas in a series of image frames constituting the compressed image to treat the moving object area as an 'object' rather than a region.

First, in order to treat the moving object area as one object (object), if a moving object area in which the identification information (ID) is not assigned in the previous frame is found in the current frame, a new unique ID is issued and assigned (S440). . That is, a new moving object is found in the image. 10 illustrates an example in which unique IDs are allocated to three moving object areas.

On the contrary, when the moving object region that has been assigned the Unique ID disappears while passing through a series of image frames, the unique ID allocated in step S440 is revoked for the moving object region (S450). In other words, the moving object previously found and tracked disappears from the image.

Through the new allocation and revoke processing of Unique ID, the moving object area is regarded as an object, and the moving trajectory of the object is tracked while moving over a series of frame images in the compressed image.

On the other hand, looks at the process made in the step (S440, S450) more. In steps S440 and S450, it should be possible to determine whether the chunks of the interconnected image blocks marked as moving object regions are the same before and after the series of image frames. This is because it is possible to determine whether the Unique ID has been previously assigned to the mobile object area currently being handled.

In the present invention, since only the image block is a moving object region without checking the original image image, it is not possible to confirm whether the chunks of the moving object region are actually the same in the front and back image frames. That is, since the contents of the image included in the image are not known, such a change cannot be identified, for example, when the cat is replaced by a dog between the front and rear frames at the same point. However, given that the time interval between frames is very short and that the observation object of the CCTV camera moves at a normal speed, this is unlikely to happen.

Accordingly, the present invention estimates that the ratio or number of image blocks overlapping between the chunks of the moving object region in the front and back frames is equal to or greater than a predetermined threshold. According to this approach, it is possible to determine whether a specific moving object area is moving, a new moving object area is new, or an existing moving object area disappears even if the contents of the original image are not known. This judgment is lower in accuracy than the prior art, but can greatly increase the data processing speed, which is advantageous in practical applications.

Step S460: Arrange a plurality of representative coordinates calculated in step S420 for a plurality of moving object areas based on a unique ID, thereby obtaining a sequence of representative coordinates in which each unique ID appears in a series of image frames. Can be. This corresponds to a movement trajectory indicating how each moving object represented by a unique ID has moved in a series of image frames.

Step S470: Then, the hit data is reinforced by accumulating the movement trajectories for the unique IDs in image block units, for example. Since the hit data calculated in step S430 reflects the frequency of appearance of the moving object region, the processing speed is high but the characteristics of the movement trajectories of the objects are not reflected. The hit data obtained in step S470 is relatively slow in processing speed, but has an advantage of reflecting moving lines of objects in a corresponding space.

Step S480: A heat map image is generated for the compressed image based on the hit data calculated in the above process.

Meanwhile, the present invention may be embodied in the form of computer readable codes on a computer readable nonvolatile recording medium. Such nonvolatile recording media include various types of storage devices, such as hard disks, SSDs, CD-ROMs, NAS, magnetic tapes, web disks, and cloud disks. Forms that are implemented and executed may also be implemented. In addition, the present invention may be implemented in the form of a computer program stored in a medium in combination with hardware to execute a specific procedure.

Claims

Parsing the bitstream of the compressed image to obtain a motion vector and a coding type for the coding unit;

A second step of obtaining a motion vector cumulative value for a predetermined time for each of the plurality of image blocks constituting the compressed image;

A third step of comparing the motion vector cumulative value with a first threshold value for the plurality of image blocks;

A fourth step of marking an image block having a motion vector accumulation value exceeding the first threshold as a moving object region;

Generating a heat map for the compressed image by accumulating the moving object region over a series of image frames of the compressed image;

A syntax-based heat map generation method for a compressed image including a.
The method according to claim 1,

The fifth step,

A fifth step of identifying the plurality of marked moving object regions in a series of image frames constituting a compressed image;

Calculating a representative position with respect to the plurality of moving object regions;

A fifth step of calculating hit data by accumulating the plurality of representative positions calculated;

A fifth step of generating a heat map for the compressed image based on the hit data;

Syntax-based heat map generation method for a compressed image, characterized in that comprises a.
The method according to claim 2,

The fifth step,

Performed between step 5c and step 5d,

In a series of video frames constituting a compressed image, a unique ID is newly issued and assigned to a plurality of mobile object areas identified by an ID unassigned state, and the image frames are assigned a unique ID state. A fifth step of revoking a unique ID for the moving object region disappearing in step 5e;

A fifth step of arranging the calculated representative positions based on the unique ID to derive a movement trajectory for each unique ID;

A fifth step of reinforcing the hit data by accumulating the movement trajectories for each Unique ID;

A syntax based heatmap generation method for a compressed image, characterized in that it further comprises.
The method according to claim 1,

Performed between the fourth and fifth steps,

A step of identifying a plurality of adjacent image blocks (hereinafter, referred to as 'neighbor block') around the moving object area;

B) comparing a motion vector value obtained in the first step with respect to the plurality of neighboring blocks with a second preset threshold value;

C) additionally marking, as a moving object region, a neighboring block having a motion vector value exceeding the second threshold value as a result of the comparison in the b of the plurality of neighboring blocks;

A syntax based heatmap generation method for a compressed image, characterized in that it further comprises.
The method according to claim 4,

Carried out after the step c,

D) additionally marking a neighboring block having a coding type of an intra picture among the plurality of neighboring blocks as a moving object region;

A syntax based heatmap generation method for a compressed image, characterized in that it further comprises.
The method according to claim 5,

Carried out after the d step,

Performing an interpolation operation on the plurality of moving object regions to additionally mark up to a predetermined number of non-marked image blocks surrounded by the moving object region as a moving object region;

Syntax-based heat map generation method for a compressed image, characterized in that further comprises.
A computer program stored in a medium in combination with hardware to execute a syntax-based heat map generation method for a compressed image according to any one of claims 1 to 6.