JP2005310052A - Device, method and program for detecting illegal dumping site - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a device, method, and program for detecting an illegal dumping site for locating and detecting a site where waste or the like is dumped. <P>SOLUTION: Luminance and geometry of a past satellite image and a present satellite image are corrected (a step S01, a step S02). Positions and luminance of the two satellite images are fitted (a step S03, a step S04). An identical area on the two satellite images is detected and is divided (a step S05). Difference of the luminance of each pixel on the two satellite images is taken to generate difference image data (a step S06), an area corresponding to a cloud on the two satellite images is set as an area out of a processing object (a step S07), and vegetation on each area on the two satellite images is obtained (a step S08). In regards to the area with small vegetation or reduced vegetation, a change in a spacial characteristic is obtained (a step S09, a step S10) to determine possibility of the illegal dumping site. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to an illegal dumping point detection device, method, and program for searching for an illegal dumping place of waste.

  The illegal dumping of waste causes serious environmental pollution, and it is important to detect the dumping site early in order to suppress this damage. Conventional methods of detecting illegal dumping places of waste depend on human resources such as notification of neighboring residents and patrols of observers, and thus require a lot of labor and are within the scope of searching for illegal dumping places. There is a limit. Moreover, the place where illegal dumping is usually performed is often a place where it is usually difficult to see. For these reasons, it is difficult to find illegal dumping places such as waste. For these reasons, a method for exhaustively searching a wide target range is required for effective discovery of illegal dumping locations.

  In addition, an illegal dumping monitoring system that captures and monitors images according to a conventional technique is to monitor a situation by installing a camera on the ground at a point requiring caution or where illegal dumping has already occurred. For this reason, it was difficult to use for the purpose of finding a new illegal dumping place.

  On the other hand, it is also considered to find a place where waste is dumped using an image taken from the sky by an artificial satellite or the like. The method of finding illegal dumping sites by visual observation based on images from artificial satellites, etc. requires a great deal of labor. Analyzing images of satellites, etc. for the purpose of assisting this, find illegal dumping sites. A method has also been proposed in recent years. However, the conventional technique has a problem that the search range is limited because only the forest area is targeted for illegal dumping spot discovery.

In addition, what is described in patent document 1, patent document 2, and patent document 3 is known as a prior art. The techniques of Patent Literature 1 and Patent Literature 2 are for monitoring illegal dumping of waste at a specific location, and are not effective for finding the above-mentioned new illegal dumping location. Further, the technique described in Patent Document 3 is a technique for assisting the cyclic monitoring of illegal dumping of wastes and the like, and is not effective for the purpose of finding the above-mentioned new illegal dumping point.
JP 2003-132443 A JP 2002-334386 A JP 2002-041633 A

  The present invention has been made in view of the above circumstances, and an object thereof is to provide an illegal dumping point detection device, method, and program capable of finding and detecting a place where waste or the like has been dumped. is there.

  SUMMARY OF THE INVENTION The present invention has been made to solve the above-described problems. The invention of claim 1 is directed to a region of the same quality for the first image data and the second image data obtained by photographing the same place from the sky at different dates and times. And a division processing unit that divides both image data in the same manner, a first area in the first image data, and the first area based on a processing result of the division processing unit. Vegetation determination means for obtaining vegetation in each region with the second region in the second image data at the same location, and whether the vegetation in the region between the first region and the second region is poor Or a statistic determination means for determining a change in spatial characteristics between the first area and the second area only when the statistic determination means has decreased, and a change in the spatial characteristics determined by the statistic determination means. Based on the above, the area where there is a high possibility that waste was illegally dumped A dumping position detecting device characterized by comprising a region determination unit that.

  The invention according to claim 2 is the illegal dumping location detection apparatus according to claim 1, wherein the first image data and the second image data are processed before the processing by the division processing means. The image processing apparatus further includes correction processing means for performing luminance correction, atmospheric correction, and geometric correction.

  The invention according to claim 3 is the illegal dumping location detecting device according to claim 2, wherein after the processing by the correction processing means, the first image data and the second image data The image processing apparatus further includes alignment means for aligning images.

  Invention of Claim 4 is an illegal dumping location detection apparatus of Claim 3, Comprising: After the process by the said alignment means, said 1st image data and said 2nd image data The image display apparatus further includes a brightness alignment unit that performs brightness adjustment of the image.

  Invention of Claim 5 is an illegal dumping location detection apparatus in any one of Claims 1-4, Comprising: From the processing result of the said division | segmentation process means, said 1st image data and said 1st The image processing apparatus further includes pre-processing means for setting a region corresponding to a cloud on the second image data as a non-processing target thereafter.

  According to the sixth aspect of the present invention, the first image data obtained by shooting the same place from the sky at different dates and the second image data are divided into regions of the same quality, and both image data are divided in the same manner. Based on the division result, each of the first area in the first image data and the second area in the second image data that is the same location as the first area Only when the vegetation is sought and the vegetation in the region between the first region and the second region is poor or has decreased, the spatial relationship between the first region and the second region An illegal dumping point detection method characterized in that a change in characteristics is obtained, and an area that is likely to be illegally dumped such as waste is detected based on the obtained change in spatial characteristics.

  According to the seventh aspect of the present invention, in the computer of the illegal dumping location detection device, the first image data obtained by photographing the same place from the sky at different dates and the second image data are in the same quality area and both. The image data in the same way, the first area in the first image data based on the result of the division, and the second image data in the same location as the first area Only when the processing for obtaining the vegetation of each region with the second region of the first region and the vegetation of the region with the first region and the second region is poor or reduced. A process for obtaining a change in spatial characteristics between the area and the second area, and a process for detecting an area likely to be illegally dumped such as waste based on the change in the obtained spatial characteristics; Is a program for executing

According to the invention of claim 1, claim 6, or claim 7, there is an effect that the user of the illegal dumping location detection device can find a location where illegal dumping of waste or the like may have been performed. .
According to the invention of claim 2, when using image data taken by an artificial satellite or the like, even if the image data is affected by correction by the atmosphere or the artificial satellite itself, There is an effect that it is possible to find a place where illegal dumping may have occurred.

According to the invention of claim 3, even when there is a positional deviation between the first image data and the second image data when using image data taken by an artificial satellite or the like, There is an effect that correction can be made to find a place where illegal dumping of waste or the like may have been performed.
According to the invention of claim 4, when using image data taken by an artificial satellite or the like, there is a difference in luminance caused by weather or the like between the first image data and the second image data. However, there is an effect that it is possible to find a place where illegal dumping of waste or the like may be performed by correcting this.

  According to the invention of claim 5, when image data taken by an artificial satellite or the like is used, this region is excluded even when the clouds are moved to the first image data and the second image data. Thus, there is an effect that it is possible to find a place where illegal dumping of waste or the like may be performed in an area that can be analyzed.

  FIG. 2 shows the configuration of the computer 100 in this embodiment. The computer 100 stores, in a storage area, image data C that is a current ground image captured by the artificial satellite and image data P that is an image obtained when the artificial satellite previously captured the same location as the image data C. Store. The image data C and the image data P are multispectral image data including a visible region, and an R (Red) band that is a visible red band and a visible green band that are included in reflection from the ground. Information on a (Green) band, a B (Blue) band that is a visible blue band, and an Ir (Infrared) band that is a near-infrared band is included.

  The control unit 101 is a control function of the computer 100, and details will be described later. The correction processing unit 102 corrects the image data C and the image data P so that they can be analyzed, and performs processing for obtaining processed image data C1 and processed image data P1. The division processing unit 103 identifies regions of the same quality such as forests and factories in the processed image data C1 and the processed image data P1, and performs region division.

  The difference generation unit 104 calculates a difference in luminance between the processed image data C1 and the processed image data P1, and generates difference image data. The preprocessing unit 105 performs a process of excluding a region such as a cloud in the processed image data C1 and the processed image data P1 from the processing target. The area determination unit 106 instructs the vegetation determination unit 107 to detect a change in vegetation between the processed image data C1 and the processed image data P1.

  The vegetation determination unit 107 refers to the vegetation determination table in the storage area shown in [Table 1] and relates to vegetation changes in the region of the processed image data C1 and vegetation based on the vegetation in the region of the processed image data P1. Make a decision.

  The vegetation determination result in [Table 1] represents a case classification of a determination result of a change in vegetation according to the presence or absence of vegetation between the region of the processed image data C1 and the region of the processed image data P1. In this case, there are three cases, Case 1 to Case 3. Case 1 is a case where vegetation is lost from the area, and illegal dumping may occur in the area. Case 2 is a case where there is no vegetation in the area, and there is a possibility that illegal dumping has occurred. Case 3 is an area where vegetation in the area is maintained or vegetation is richer, and the possibility of illegal dumping is low.

  The area determination unit 106 instructs the statistic determination unit 108 as necessary to check a spatial feature difference between the area in the processed image data C1 and the area of the processed image data P1. The statistic determination unit 108 detects the uniformity or randomness in the area by checking the difference in the spatial characteristics of the area, and thus it is possible that illegal dumping of waste or the like has been performed in the area It is possible to detect whether or not there is sex. The statistic determination unit 108 refers to the spatial feature determination table in the storage area shown in [Table 2] in checking the spatial feature difference.

  In the spatial feature determination table of [Table 2], the vegetation determination result is the vegetation determination result of [Table 1]. The difference statistic changes in [Table 2] are classified according to D, which is the degree to which the spatial characteristics have changed between the processed image data C1 and the processed image data P1 for a certain region. It is. T1 and T2 are predetermined threshold values. In [Table 2], regions are classified into four types, Case A to Case D, according to the size of changes in spatial characteristics and the combination of Case 1 and Case 2 in [Table 1].

  Of these four cases, Case A to Case D, Case A is a case in which the vegetation in the corresponding region is reduced and the change in spatial characteristics is large, and there is a possibility that illegal dumping of waste or the like is performed There is a case. Case B is a case where the vegetation of the area is reduced and the change in spatial characteristics is small, and the area changes from forest to field, or becomes an illegal dumping place of waste etc. before and after harvesting of the field. This is a low possibility.

  Case C is a case where the vegetation in the region has been low for a long time, and the change in spatial characteristics is large, and it may be an illegal dumping place for waste and the like. Case D is a case where the vegetation in the area has been low for a long time, and the change in the spatial characteristics is small, and the possibility that the area is an illegal dumping place such as waste is low.

Next, the flow of processing in the present embodiment will be described with reference to FIG. Now, the user of the computer 100 inputs designation of the image data C and the image data P to the operation unit of the computer 100, and instructs the computer 100 to display a place where the illegal dumping may be performed.
The control unit 101 of the computer 100 receives an instruction from the user via the operation unit of the computer 100, designates the image data C and the image data P to the correction processing unit 102, and puts these image data into a state that can be analyzed. Require to do.

  The correction processing unit 102 receives an instruction from the control unit 101 and performs image correction processing corresponding to step S01 in FIG. In this process, the correction processing unit 102 first reads the image data C from the storage area, and returns the correction because the image data C sent from the artificial satellite has been corrected so that it can be easily seen by humans. As a result, the image data C becomes an original image captured by the sensor of the artificial satellite.

Next, the correction processing unit 102 removes the attenuation of luminance and the like due to radiation from the atmosphere existing between the sensor of the artificial satellite that captured the image data C and the object to be imaged. Perform atmospheric correction. Further, the correction processing unit 102 performs correction of the distortion of the lens of the artificial satellite sensor on the image data C and geometric correction that is correction of the distortion of the image due to the position and orientation of the artificial satellite. The correction processing unit 102 writes the image data C in the storage area after performing such correction.
The correction processing unit 102 performs the same processing as that in step S01 in FIG. 1 on the image data P (step S02 in FIG. 1).

  Next, the correction processing unit 102 performs alignment processing corresponding to step S03 in FIG. In this process, since the image data P and the image data C are taken on different days, the positions of the two images may be slightly different due to slight changes in the position and attitude of the artificial satellite. This is to correct this. In this processing, the correction processing unit 102 reads the image data P and the image data C that have been corrected earlier from the storage area, and moves the predetermined building or the like included in the image data P and the image data C. The positional deviation between the two image data is corrected based on the missing feature.

Further, the correction processing unit 102 performs luminance matching processing corresponding to step S04 in FIG. This process is for correcting the image data P and the image data C, which are taken on different days, so that the brightness of the two images may differ depending on the weather or the like. is there. In this process, the correction processing unit 102 is based on features that do not vary depending on the shooting time, such as a predetermined building included in the image data P and the image data C that have been subjected to the alignment process. A difference in luminance between the two image data is detected and corrected.
The correction processing unit 102 writes the image data C and the image data P in which consistency between the position and the luminance is ensured into the storage area as the processed image data C1 and the processed image data P1, and controls “pre-processing completed”. Output to the unit 101.

  The control unit 101 receives “preprocessing completed” from the correction processing unit 102 and instructs the division processing unit 103 to divide the area between the image data P and the image data C corresponding to step S05 in FIG. The division processing unit 103 receives an instruction from the control unit 101 and reads the processed image data C1 and the processed image data P1 from the storage area.

  Then, the division processing unit 103 divides the R band, G band, B band, and Ir band of pixels having the same coordinates on the processed image data C1 and the processed image data P1 into a total of eight bands. Pay attention to divide each pixel into regions. For each pixel on the processed image data C1, the division processing unit 103 takes a difference from the luminance of adjacent pixels or the average luminance of the region, and when the luminance difference of each of the eight bands falls within the predetermined threshold value, An area is generated by integrating the pixels of 1 into one area. The division processing unit 103 performs this area division on all the pixels on the processed image data C1, and based on the result, which area the pixels of the processed image data C1 and the processed image data P1 are included in. The area information to be expressed is generated and written into the storage area, and the completion of the area division is notified to the control unit 101 (step S05 in FIG. 1). By this processing, it becomes possible to distinguish the forest, farmland, etc. on the processed image data C1 and the processed image data P1 as different areas.

Upon receiving the notification from the division processing unit 103, the control unit 101 instructs the difference generation unit 104 to create difference image data that is data to be used in subsequent processing.
The difference generation unit 104 receives an instruction from the control unit 101 and reads the processed image data C1 and the processed image data P1 from the storage area. Then, the difference generation unit 104 sets “difference image = | for the R band, the G band, the B band, and the Ir band of pixels having the same coordinates on the processed image data C1 and the processed image data P1. The absolute value of each difference is calculated as represented by the equation “image (current) −image (past) |”, this calculation is performed for all pixels, and new image data is generated based on the calculation result. This new image data is written into the storage area as difference image data (step S06 in FIG. 1). Then, the difference generation unit 104 notifies the control unit 101 of the completion of generation of the difference image data.

The control unit 101 receives the notification from the difference generation unit 104, and subsequently excludes the area corresponding to the cloud above the processed image data C1 and the processed image data P1 from the target of subsequent processing. Detection is instructed to the preprocessing unit 105.
In response to an instruction from the control unit 101, the preprocessing unit 105 reads out the processed image data C1, the processed image data P1, and the region information from the storage region. Then, the preprocessing unit 105 checks the luminance of all the bands of the R band, the G band, and the B band of each pixel included in each region on the processed image data C1, and exceeds the predetermined threshold value. Check if it is high. Then, if the pre-processing unit 105 finds that a predetermined ratio of pixels included in a certain area on the processed image data C1 corresponds to this check, the area is a cloud, and It is determined that the information is not subject to processing, and information related to the region in the region information is set as not subject to processing. Further, the preprocessing unit 105 checks the luminance of all the above-described bands, and confirms whether or not it is lower than a predetermined threshold. Then, if the pre-processing unit 105 finds that a predetermined percentage of pixels included in a certain area on the processed image data C1 falls under this check, the area is a water area or a shadow. Therefore, it is determined that the information is not subject to subsequent processing, and information related to the region in the region information is set as a processing subject.
Further, the preprocessing unit 105 performs the same check on the processed image data P1. Thereafter, the preprocessing unit 105 writes the area information into the storage area (step S07 in FIG. 1). Then, the preprocessing unit 105 notifies the control unit 101 of completion of the preprocessing.

  The control unit 101 receives the notification from the pre-processing unit 105, and the areas in the processed image data C1 and the processed image data P1 may be illegal dumping points based on the data obtained by the processing so far. Check if it exists. For this purpose, the control unit 101 requests the region determination unit 106 to check each region of the processed image data C1 and the processed image data P1.

  The area determination unit 106 accepts a request from the control unit 101. First, in step S08 of FIG. 1, the presence / absence or some degree of vegetation in each area in the processed image data C1 and the processed image data P1, or the degree of activity Check out. For this reason, the area determination unit 106 reads the processed image data C1, the processed image data P1, and the area information from the storage area. Then, the area AC on the processed image data C1 and the area AP located on the processed image data P1 at the same location as the area AC are specified, and the vegetation determination unit 107 is requested to check for vegetation.

  The vegetation determination unit 107 receives a request from the region determination unit 106 and calculates an NDVI (Normalized Difference Vegetation Index) of each pixel in the region AC. This NDVI is obtained by a calculation formula of (Ir band-R band) / (Ir band + R band) based on the Ir band and R band of the pixel. Then, the vegetation determining unit 107 calculates the NDVI average of all the pixels in the area AC to obtain the NDVI of the area AC. When NDVI of area | region AC is high, it turns out that the vegetation of area | region AC is rich. Furthermore, the vegetation determination unit 107 compares the NDVI in the area AC with a predetermined threshold value T_NDVI, and determines that “vegetation is present” for the area AC if NDVI ≧ T_NDVI in the area AC. Conversely, the vegetation determination unit 107 determines that there is no vegetation for the region AC when NDVI <T_NDVI of the region AC.

  Similarly, the vegetation determination unit 107 obtains the NDVI of the area AP, and also determines “with vegetation” or “without vegetation” for the area AP. Then, the vegetation determination table is read from the storage area, and the determination results of Case 1 to Case 3 are obtained according to the vegetation determination table. The vegetation determination unit 107 outputs the vegetation determination result to the region determination unit 106.

The region determination unit 106 receives the output of the vegetation determination unit 107 and determines subsequent processing corresponding to Case 1 to Case 3 which are the vegetation determination results by the vegetation determination unit 107.
When the vegetation determination result by the vegetation determination unit 107 is Case 3, the region determination unit 106 determines that the region AC has abundant vegetation and is not an illegal dumping place for waste or the like, and selects another region. Then, the process of step S08 in FIG. 1 is performed again to check the area.

  When the determination result of vegetation by the vegetation determination unit 107 is Case 2, the region determination unit 106 determines that the region AC and the region AP have poor vegetation, and thus may be an illegal dumping place such as waste. A further check is performed by a process corresponding to step S09 in FIG. For this purpose, in step S09 of FIG. 1, the area determination unit 106 designates the area AC and the area AP, and the statistic determination unit 108 determines the magnitude of the change in the spatial characteristics of the image data in the area. Request a check.

  The statistic determination unit 108 receives a request from the region determination unit 106, and the statistic determination unit 108 attempts to detect the magnitude of the change in the spatial characteristics between the region AC and the region AP. The statistic determination unit 108 reads the difference image data and the area information from the storage area, and identifies an area AD that is an area in the difference image data corresponding to the area AC. Then, the statistic determination unit 108 obtains each entropy (Entropy) and angular second moment (Angle Second Moment) for the region AC, the region AP, and the region AD. Entropy and angular second moment are differential statistics, and the entropy is high when the spatial features in the region are messy, and the angular second moment is obtained when the spatial features in the region are uniform. High value.

  Further, the statistic determination unit 108 obtains D representing the change in the difference statistic according to the calculation formula [Equation 1]. Then, the statistic determination unit 108 reads the spatial feature determination table from the storage area, and obtains the determination result of the change of the spatial feature in the area based on the obtained D. In step S09 in FIG. 1, only T2 is a comparison target. T1 is used in step S10 of FIG. From [Table 2], the statistic determination unit 108 outputs “CaseC” to the region determination unit 106 when D obtained previously is equal to or larger than T2. When D is smaller than T2, the statistic determination unit 108 outputs “Case D” to the region determination unit 106 from [Table 2].

  The region determination unit 106 receives an output from the statistic determination unit 108, and when it is “CaseC”, that is, it is determined that a change in spatial characteristics is detected in a region where vegetation is poor, Therefore, it is determined that there is a possibility that illegal dumping of waste or the like has occurred in this area. Then, the area determination unit 106 reads the area information from the storage area and sets “detection” to the data corresponding to the area AC.

  Further, when the output from the statistic determination unit 108 is “CaseD”, the region determination unit 106 determines that it has detected that the change in the spatial feature is small in the region where the vegetation is poor. Since there is no possibility that illegal dumping of waste or the like has occurred in the area, it is determined that there is no need to be particularly wary of the area, and another area is selected and the process of step S08 in FIG. 1 is performed again. Check the area.

  In addition, when the vegetation determination result by the vegetation determination unit 107 is Case 1, the region determination unit 106 has vegetation in the region AP, but vegetation in the region AC is scarce, and thus is an illegal dumping place for waste and the like. It is determined that there is a possibility, and further check is performed by the process corresponding to step S10 in FIG. The process in step S10 in FIG. 1 is the same as the process in step S09. However, the threshold value in [Table 2] is T1.

  The region determination unit 106 receives the output from the statistic determination unit 108, and when this is “Case A”, that is, it is determined that it has detected that the change in the spatial characteristics is large in the region where vegetation is poor. Therefore, it is determined that there is a possibility that illegal dumping of waste or the like has occurred in the area. Then, the area determination unit 106 reads the area information from the storage area and sets “detection” to the data corresponding to the area AC.

  In addition, when the output from the statistic determination unit 108 is “CaseB”, the region determination unit 106 determines that it has detected that the change in the spatial feature is small in the region where the vegetation is poor. Therefore, the area is changed to a field or the like, and therefore there is no possibility that illegal dumping of waste or the like has occurred. Therefore, it is determined that there is no need to be particularly wary of the area, and another area is selected and again shown in FIG. In step S08, the area is checked.

  The area determination unit 106 performs the process of step S08 in FIG. 1 for all areas of the processed image data C1 and the processed image data P1, and step S09 or step S10 if necessary, and then the control unit 101. Notify completion of processing.

  The control unit 101 receives the notification from the region determination unit 106, reads the region information from the storage region, and the computer indicates that there is a possibility that illegal dumping of waste or the like has been performed on the region where “detection” is set. 100 is displayed on the display unit. The user of the computer 100 confirms the display on the display unit of the computer 100 and recognizes a portion where illegal dumping may be performed.

  As described above, the embodiments of the present invention have been described in detail with reference to the drawings, but the specific configuration is not limited to these embodiments, and includes design changes and the like within a scope not departing from the gist of the present invention. It is. For example, the purpose of this embodiment is to detect illegal dumping of waste, but in addition to this, vegetation changes occur due to the progress of natural destruction and desertification. It is.

  In the present embodiment, it can be used in combination with the conventional technology only for the forest area, and can also be used to detect improper storage of waste at intermediate treatment facilities and final disposal sites. Is possible.

It is a flowchart of the computer 100 in embodiment of this invention. It is a block diagram of computer 100 in an embodiment of the invention.

Explanation of symbols

100 ... Computer (Illegal dumping point detection device)
DESCRIPTION OF SYMBOLS 101 ... Control part 102 ... Correction process part 103 ... Division | segmentation process part 104 ... Difference production | generation part 105 ... Pre-processing part 106 ... Area determination part 107 ... Vegetation determination part 108 ... Statistics amount determination part

Claims (7)

Division processing means for dividing the first image data obtained by photographing the same place from the sky at different dates and the second image data into homogeneous regions, and dividing both image data in the same manner;
Each of the first area in the first image data and the second area in the second image data at the same location as the first area based on the processing result of the division processing means A vegetation judging means for obtaining vegetation in the area,
Only when the vegetation of the region between the first region and the second region is poor or decreased, changes in spatial characteristics between the first region and the second region are changed. Statistic determination means to be obtained;
An illegal dumping location detection device comprising: an area determination unit that detects an area where waste or the like is likely to be illegally dumped based on a change in spatial characteristics obtained by the statistic determination unit .   The image processing apparatus further includes correction processing means for performing luminance correction, atmospheric correction, and geometric correction of the first image data and the second image data before the processing by the division processing means. The illegal dumping location detection device according to claim 1.   3. The apparatus according to claim 2, further comprising an alignment unit configured to align an image of the first image data and the second image data after the processing by the correction processing unit. Illegal dumping spot detection device.   4. The apparatus according to claim 3, further comprising a luminance alignment unit configured to perform luminance adjustment of an image of the first image data and the second image data after the processing by the alignment unit. Illegal dumping spot detection device.   The image processing apparatus further includes preprocessing means for setting a region corresponding to a cloud on the first image data and the second image data from the processing result of the division processing means as a target for subsequent processing. The illegal dumping location detection device according to any one of claims 1 to 4, wherein The first image data taken from the sky at the same place at different dates and the second image data are divided into homogeneous regions, and both image data are divided in the same manner,
Based on the division result, vegetation of each region of the first region in the first image data and the second region in the second image data at the same location as the first region Seeking
Only when the vegetation of the region between the first region and the second region is poor or decreased, changes in spatial characteristics between the first region and the second region are changed. Seeking
An illegal dumping point detection method, comprising: detecting an area where there is a high possibility of illegal dumping of waste or the like based on the obtained spatial characteristic change. In the computer of the illegal dumping spot detection device,
A process of dividing the first image data obtained by photographing the same place from the sky at different dates and the second image data into homogeneous regions and dividing both image data in the same manner;
Based on the division result, vegetation of each region of the first region in the first image data and the second region in the second image data at the same location as the first region Processing for
Only when the vegetation of the region between the first region and the second region is poor or decreased, changes in spatial characteristics between the first region and the second region are changed. The required processing,
And a process for detecting a region that is highly likely to be illegally dumped, such as waste, based on the obtained change in spatial characteristics.

Images