Analysis system, analysis method, program, and storage medium

Abstract

To provide an analysis system, an analysis method, a program, and a storage medium capable of analyzing work from the perspective of efficiency and safety.SOLUTION: In an analysis system 1, a detection unit 12 detects a worker from an image obtained by capturing the worker at a work site, and calculates a position of the worker. A first determination unit 13 refers to layout data related to a layout of a plurality of work areas in the work site and determines a movement path of the worker in the layout based on the calculated position. A second determination unit 14 determines a work intensity of the worker from biological data of the worker. An output unit 15 outputs an analysis result indicating the layout, the movement path between the plurality of work areas, a movement frequency of the movement path, and the work intensity in the movement path.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] FIELD An embodiment of the present invention relates to an analysis system, an analysis method, a program, and a storage medium. [Background technology]

[0002] In addition to efficiency, safety is also required for work. There is a demand for the development of technology that can analyze work from the standpoint of both efficiency and safety. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2018-10366 A Summary of the Invention [Problem to be solved by the invention]

[0004] An object of the present invention is to provide an analysis system, an analysis method, a program, and a storage medium that are capable of analyzing work from the standpoint of efficiency and safety. [Means for solving the problem]

[0005] The analysis system according to the embodiment includes a detection unit, a first determination unit, a second determination unit, and an output unit. The detection unit detects a worker from an image of the worker at a work site and calculates the position of the worker. The first determination unit refers to layout data related to a layout of a plurality of work areas at the work site and determines a movement path of the worker in the layout based on the calculated position. The second determination unit determines the work intensity of the worker from biometric data of the worker. The output unit outputs an analysis result indicating the layout, the movement path between the plurality of work areas, the movement frequency of the movement path, and the work intensity on the movement path. [Brief description of the drawings]

[0006] [Figure 1] FIG. 1 is a schematic diagram illustrating a configuration of an analysis system according to an embodiment. [Diagram 2] FIG. 2 is a schematic diagram showing layout data. [Diagram 3] FIG. 13 is a schematic diagram showing an example of output of an analysis result. [Figure 4] 4 is a flowchart showing the operation of the analysis system according to the embodiment. [Diagram 5] FIG. 1 is a schematic diagram illustrating a work site. [Figure 6] 1A is a schematic diagram illustrating map data, and FIG. 1B is a schematic diagram illustrating an image captured by an imaging device. [Figure 7] 1A is a schematic diagram showing a cut-out image and extracted skeletal data, and FIG. 1B is a schematic diagram showing a part of an image captured by an imaging device. [Figure 8] 11 is a table showing a processing result by a detection unit. [Figure 9] 11 is a table showing a processing result by a first determination unit. [Figure 10] 11 is a table showing a processing result by a first determination unit. [Figure 11] 13 is a table showing a processing result by a second determination unit. [Figure 12] 13 is a table showing data integrated by a second determination unit. [Figure 13] FIG. 13 is a schematic diagram showing an example of output of an analysis result. [Figure 14] FIG. 13 is a schematic diagram showing an example of output of an analysis result. [Figure 15] FIG. 13 is a schematic diagram showing an example of output of an analysis result. [Figure 16] FIG. 2 is a schematic diagram showing a hardware configuration. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In this specification and the drawings, elements similar to those already described are designated by the same reference numerals, and detailed description thereof will be omitted as appropriate.

[0008] FIG. 1 is a schematic diagram showing the configuration of an analysis system according to an embodiment. As shown in FIG. 1, the analysis system 1 according to the embodiment includes a processing device 10, an imaging device 20, a measuring device 21, a storage device 30, an input device 31, and an output device 32.

[0009] The processing device 10 analyzes the behavior and work intensity of a worker at a work site. Specifically, the work site includes a plurality of work areas. A worker works in one of the plurality of work areas. In addition, the worker may move between work areas between tasks. The processing device 10 analyzes the movement route between the plurality of work areas, the movement frequency of the movement route, the work intensity on the movement route, etc. Work intensity means the intensity of work performed by a worker. The higher the work intensity, the greater the burden on the worker and the more fatigued the worker becomes.

[0010] The imaging device 20 captures an image of a worker and acquires the image. The imaging device 20 is installed in each of a plurality of work areas and on a path between the plurality of work areas. The imaging device 20 is, for example, a camera. The imaging device 20 acquires a still image. The imaging device 20 may acquire a moving image, and a still image may be extracted from the moving image. The imaging device 20 stores the acquired data in the storage device 30.

[0011] The measuring device 21 acquires biometric data of the worker. For example, the biometric data is one or more selected from pulse rate, blood pressure, body movement, cardiac potential, sweat rate, body temperature, percutaneous arterial oxygen saturation (SpO2), and respiratory rate. The measuring device 21 is a wearable biosensor that measures the biometric data. A specific method for acquiring the biometric data is arbitrary. For example, the measuring device 21 includes one or more selected from an acceleration sensor, a light-emitting device and a light-receiving device, a temperature sensor, a voltmeter, a humidity sensor, and a proximity sensor. The measuring device 21 acquires measured values ​​as biometric data. The biometric data may be calculated from the measured values. For example, one or more selected from a pulse wave sensor, a blood pressure meter, a body movement sensor, a cardiac potential meter, a sweat sensor, a thermometer, a pulse oximeter, and a respirometer are used as the measuring device 21. The measuring device 21 stores the acquired biometric data in the storage device 30.

[0012] The processing device 10 performs analysis based on the image and biological data. The processing device 10 includes an acquisition unit 11, a detection unit 12, a first determination unit 13, a second determination unit 14, and an output unit 15, as shown in FIG.

[0013] The acquiring unit 11 acquires the images and biometric data from the storage device 30. The acquiring unit 11 may acquire the images and biometric data directly from the imaging device 20 and the measuring device .

[0014] The detection unit 12 detects a worker from an image in which the worker is captured. The detection unit 12 calculates the position of the detected worker. The detection unit 12 may further identify the detected worker.

[0015] The first determination unit 13 refers to the layout data, which relates to the layout of a plurality of work areas.

[0016] FIG. 2 is a schematic diagram showing layout data. The layout data includes an image showing the layout, the origin coordinates in the layout, the axis directions of the coordinate system, the coordinates of each work area, and the routes between each work area. In the layout data 100 shown in FIG. 2, an image 101 is prepared, and the origin coordinates (Ox, Oy) and the axis directions (X, Y) are set. The work site includes five work areas 111-115. For each work area, the coordinates (x1, y1), (x2, y2), (x3, y3), and (x4, y4) of the four corners are set. Between the work areas 111-115, routes 121-128 along which the worker may move are set. The first determination unit 13 determines whether the worker's movement route is one of a plurality of routes set in advance, based on the calculated position.

[0017] The second determination unit 14 determines the work intensity of the worker based on the biometric data. As an example, the biometric data is a pulse rate. The second determination unit 14 compares the pulse rate with a plurality of thresholds to determine the work intensity. The higher the pulse rate, the higher the work intensity is determined to be. The second determination unit 14 may calculate heart rate variability (RR interval) from the pulse rate or cardiac potential. The heart rate variability corresponds to a stress level. The second determination unit 14 compares the heart rate variability with a plurality of preset thresholds to determine the work intensity. The second determination unit 14 may compare the body temperature or the amount of sweat with a plurality of thresholds to determine the work intensity. The body temperature or the amount of sweat corresponds to the risk of heat stroke. The second determination unit 14 may compare the blood pressure with a plurality of thresholds to determine the work intensity.

[0018] The threshold for determining the work intensity may be set commonly for a plurality of workers, or may be set for each worker. Preferably, the threshold is set based on the age of the worker or the worker's normal biological data.

[0019] The second determination unit 14 may comprehensively determine the work intensity of the worker based on two or more pieces of biometric data. For example, the second determination unit 14 calculates a normalized score from each piece of biometric data. The second determination unit 14 compares a value obtained from the average, sum, weighted average, or weighted sum of those scores with multiple thresholds to determine the work intensity.

[0020] The output unit 15 generates an analysis result using the movement path determined by the first determination unit 13 and the work intensity determined by the second determination unit 14, and outputs the analysis result to the output device 32.

[0021] The input device 31 is used when a user inputs data to the processing device 10. The input device 31 includes at least one selected from a mouse, a keyboard, a microphone, and a touch pad. The acquisition unit 11 accepts the data input from the input device 31.

[0022] The output device 32 outputs data so that the user can recognize it. The output device 32 includes at least one selected from a monitor, a projector, a printer, and a speaker. A device having the functions of both the input device 31 and the output device 32, such as a touch panel, may be used.

[0023] The processing device 10 includes a processing circuit equipped with a central processing unit. The storage device 30 is a hard disk drive (HDD), a solid state drive (SSD), a network HDD (NAS), or the like. The processing device 10, the imaging device 20, the measuring device 21, the storage device 30, the input device 31, and the output device 32 are connected to each other by wireless communication or wired communication. The processing device 10, the storage device 30, the input device 31, and the output device 32 may be incorporated into one device.

[0024] FIG. 3 is a schematic diagram showing an example of output of the analysis results. The analysis result 150 indicates the movement route traveled by the worker, the movement frequency, and the work intensity on the movement route. For example, the analysis result 150 is output to a graphical user interface (GUI) displayed on the output device 32. In the example shown in FIG. 3, it is indicated that the displayed route is the movement route of the work vehicle. That is, among the routes 121 to 128 shown in FIG. 2, the routes 122 to 124 and 126 to 128 are the movement routes. The movement frequency is indicated by the thickness of the line of the movement route. The thicker the line, the higher the movement frequency. That is, a route with a thick line indicates that the work vehicle passes through it more frequently than a route with a thin line. The type of line indicates the work intensity. In this example, the work intensity based on the heart rate variability is indicated, and these work intensities correspond to stress levels. A dotted line indicates that the stress level on the movement route is low. A dashed line indicates that the stress level on the movement route is medium. A solid line indicates that the stress level on the movement route is high.

[0025] The movement route, movement frequency, and work intensity are displayed superimposed on the layout image 101. This allows the user to easily understand the movement route, movement frequency, and work intensity at the work site.

[0026] FIG. 4 is a flowchart showing the operation of the analysis system according to the embodiment. The imaging device 20 acquires an image (step S1). The measuring device 21 acquires biometric data of the worker (step S2). The detection unit 12 detects the worker from the image (step S3). The detection unit 12 calculates the position of the worker in the image (step S4). The first determination unit 13 refers to the layout data (step S5). The first determination unit 13 determines the movement path of the worker based on the position of the worker (step S6). The second determination unit 14 determines the work intensity of the worker from the biometric data (step S7). The output unit 15 causes the output device 32 to output the analysis results indicating the layout, movement path, movement frequency, and work intensity (step S8).

[0027] Advantages of the embodiment will be described. For efficient work, it is preferable that the distance of the route along which the workers move frequently is short. For example, by locating two work areas where the workers move frequently close to each other, the time required to move between the work areas can be reduced, thereby improving work efficiency.

[0028] On the other hand, from the viewpoint of work safety, it is preferable to consider the work intensity on the moving route. For example, even if the moving frequency of a long moving route is low, if heavy parts or work in progress are carried on the moving route, or if a transportation method that places a large burden on the worker is used on the moving route, there is room for improvement from the viewpoint of safety. In addition, if a worker becomes excessively tired, he or she may become ill, which may result in a decrease in work efficiency.

[0029] Regarding this issue, the analysis system 1 according to the embodiment determines the movement route of the worker and determines the work intensity of the worker from the biometric data of the worker. Then, as shown in FIG. 3, the analysis system 1 outputs an analysis result indicating the layout, the movement route between a plurality of work areas, the movement frequency of the movement route, and the work intensity on the movement route. By referring to the analysis result, the user can easily understand the movement route and the movement frequency as well as the work intensity on the movement route. For example, the user can design the layout based on the analysis result so that the work areas with high movement frequency are close to each other while preventing the movement route that places a heavy burden on the worker from being too long.

[0030] According to the embodiment, it is possible to analyze work from the viewpoints of efficiency and safety. The invention according to the embodiment is suitable for use in analyzing marshalling at work sites that involve frequent movement, work at construction sites, and the like. By applying the invention according to the embodiment to these types of work, it is possible to visualize disaster risks, set appropriate rest times, and prevent industrial accidents.

[0031] Hereinafter, each process performed by the processing device 10 will be described with reference to a specific example.

[0032] FIG. 5 is a schematic diagram illustrating a work site. 5, a plurality of imaging devices 20a to 20k are provided at a work site 110. At the work site 110, a plurality of workers 131 to 133 are working.

[0033] (Detection unit) The detection unit 12 refers to a first model for detecting a worker from an image. The first model is prepared in advance by a user and stored in the storage device 30. The first model includes a neural network. Preferably, the first model includes a Convolutional Neural Network (CNN). By using the CNN, the worker can be detected with high accuracy from each image. The first model is trained in advance so that the worker can be detected from the image. The detection unit 12 may detect the worker from each image using a Single Shot MultiBox Detector (SSD) or Regions with CNN (R-CNN).

[0034] The detection unit 12 inputs an image into the first model and detects a worker included in the image. The detection unit 12 cuts out a part of the image in which the worker is shown based on the detection result. For example, the part of the image is cut out into a rectangle. The detection unit 12 stores the image in which the worker is shown, cut out from each image, in the storage device 30. The detection unit 12 also stores the position in each image where the worker is cut out as a detection area in the storage device 30.

[0035] Fig. 6(a) is a schematic diagram illustrating map data, and Fig. 6(b) is a schematic diagram showing an image captured by an imaging device. The detection unit 12 refers to map data represented in a two-dimensional coordinate system that is stored in advance in the storage device 30. A plurality of reference points are set in advance in the map data. A plurality of reference points are also set in advance for an image acquired by the imaging device 20. For example, as shown in FIG. 6(a), a plurality of reference points Re1 to Re12 are set in the map data M within a range captured by the imaging device 20c. As shown in FIG. 6(b), a plurality of reference points St1 to St12 are set for an image IM captured by the imaging device 20c.

[0036] A plurality of base points in the image are set at positions corresponding to a plurality of reference points in the map data. The detection unit 12 converts the coordinate system of the image so that the plurality of base points coincide with the plurality of reference points, respectively. A perspective projection transformation matrix can be used for the conversion. In the example of FIG. 6(a) and FIG. 6(b), the coordinate system is converted so that the coordinates of the plurality of base points St1 to St12 coincide with the coordinates of the plurality of reference points Re1 to Re12. In the map data, a plurality of reference points may be set in common for a plurality of imaging devices 20, or a plurality of reference points may be set for each imaging device 20.

[0037] The detection unit 12 calculates the position of the worker in the image based on the part of the worker that is in contact with the floor surface. For example, the detection unit 12 uses the center position of the bottom side of the detection area as the position of the worker in the image. The position of the worker in the common coordinate system is calculated by the above-mentioned coordinate system conversion.

[0038] The detection unit 12 may identify the worker. A second model for identifying the worker from the image is stored in advance in the storage device 30. The second model includes, for example, a neural network. Preferably, the second model includes a CNN. By using the CNN, the worker can be identified with high accuracy. The second model is trained in advance so as to be able to identify the worker. Alternatively, the detection unit 12 may extract Histograms of Oriented Gradients (HOG) features from the image and input the HOG features to a support vector machine (SVM) to identify the worker.

[0039] The detection unit 12 extracts the area in which the worker is detected from the image acquired by the imaging device 20, and inputs the extracted image to the second model. The detection unit 12 identifies the worker corresponding to the class with the highest reliability as the worker appearing in the image. The detection unit 12 stores the identification result of the worker together with the reliability in the storage device 30.

[0040] The worker may wear a marker to facilitate identification by the detection unit 12. The second model may identify the worker by identifying the marker. For example, when the worker is wearing a bib, the second model may identify the color of the bib or the characters printed on it. The detection unit 12 stores the marker identification result in the storage device 30 as the worker identification result.

[0041] Part of the ranges captured by two or more imaging devices 20 may overlap. When the same worker is captured in multiple images at the same time, the detection unit 12 calculates the position of the worker in each image and converts each position into a position in a common coordinate system. "The same time" includes not only cases where two or more times are completely the same, but also cases where the difference between two or more times is small. For example, if the difference between two or more times is within 5 seconds, those times can be considered to be substantially the same. For example, the detection unit 12 calculates the midpoint between each position in the common coordinate system as the position of the worker.

[0042] When the detection unit 12 calculates the position of the worker in the image, the detection unit 12 may calculate the accuracy. The detection unit 12 calculates the position of the worker using the accuracy for each position. For example, a higher accuracy indicates a higher accuracy of the position. The accuracy is preferably calculated using at least one of the following five values.

[0043] The first is the reliability of the person identification result. The higher the reliability, the more accurate the person identification result is. In other words, it indicates that the person is more clearly captured in the image. The higher the reliability, the higher the accuracy is calculated.

[0044] The second is the size of the worker in the image. In other words, this is the size of the detection area. The closer the worker is to the image capture device 20, the larger the worker appears. The larger the worker appears, the more accurate the position will be. Therefore, the larger the size, the higher the calculated accuracy.

[0045] The third is the distance between the center of the image and the worker. For example, the detection unit 12 calculates the distance between the center of the image and the center of the detection area. The shorter the distance, the lower the possibility that the worker is cut off from the image. The smaller the proportion of the worker that is cut off, the higher the accuracy of the position. Therefore, the shorter the distance, the higher the calculated accuracy.

[0046] Fig. 7(a) is a schematic diagram showing a cut-out image and extracted skeletal data, and Fig. 7(b) is a schematic diagram showing a part of an image captured by an imaging device. The fourth is a value indicating the posture of the person. The detection unit 12 extracts skeletal data of the person from the cut-out image. For example, as shown in FIG. 7(a), a plurality of joints Jo are extracted as skeletal data from the cut-out image IM1. The detection unit 12 calculates the width W1 of both shoulders. The detection unit 12 calculates the ratio R1 of the width W1 to the height H1 of the cut-out image. For example, the ratio R2 of the shoulder width W2 to the height H2 when each person faces forward is stored in the storage device 30 in advance. The detection unit 12 uses the ratio R3 of the ratio R1 to the ratio R2 as a value indicating the posture of the person. The larger the ratio R3, the more the person faces forward or backward in the image. The more the person faces forward or backward, the higher the possibility that both hands and both feet of the person are captured, and the higher the accuracy of the detection of the worker. Therefore, the larger the ratio R3, the higher the calculated accuracy.

[0047] The fifth is the degree of exposure of the worker in the image. For example, as shown in FIG. 7(b), a part of the worker is hidden in the image. In this case, a detection area DR1 is detected as an area in which the worker is photographed. The detection unit 12 extracts the position of the skeleton of the person photographed in the detection area DR1 and estimates the position of the hidden skeleton.

[0048] For example, a model for estimating the position of a person's skeleton based on an image and also estimating the relationship between each joint is stored in advance in the storage device 30. OpenPose can be used as the model. The detection unit 12 estimates the position of the person's skeleton including hidden skeletons using the model. The detection unit 12 corrects the detection area based on the estimation result. The corrected detection area DR2 is an area where a person is estimated to be included if there is no obstruction.

[0049] The detection unit 12 calculates the ratio of the area of ​​the detection area DR1 to the area of ​​the corrected detection area DR2 as the degree of exposure. The higher the degree of exposure, the more of the worker is shown. The higher the degree of exposure, the higher the accuracy of detecting the worker. Therefore, the higher the degree of exposure, the higher the calculated accuracy.

[0050] The detection unit 12 calculates the accuracy using at least one of the five values ​​described above. Preferably, the detection unit 12 calculates the accuracy using all of the five values. For example, the detection unit 12 uses the average of the five values ​​as the accuracy. Alternatively, a weight may be set in advance for each of the five values, taking into account the priority of these values. The detection unit 12 may multiply each value by the weight, and use the sum of the multiplied values ​​as the accuracy. The detection unit 12 calculates the accuracy for each position.

[0051] The detection unit 12 calculates an integrated position using multiple positions and the accuracy for each position. For example, the detection unit 12 uses the accuracy as a weight. The detection unit 12 normalizes the multiple accuracy and multiplies each position by the accuracy. The detection unit 12 calculates the sum of the products as the integrated position. By using the accuracy, the position of the worker can be calculated with higher accuracy.

[0052] FIG. 8 is a table showing the processing results by the detection unit. The table 200 shown in FIG. 8 includes a data ID 201, a device ID 202, a time 203, an identification result 204, an accuracy 205, an x ​​coordinate in the camera coordinate system 206, a y coordinate in the camera coordinate system 207, an x ​​coordinate in the common coordinate system 208, a y coordinate in the common coordinate system 209, and a working area 210.

[0053] The data ID 201 is a unique character string assigned to data obtained from processing one image. The device ID 202 is a unique character string assigned to each imaging device 20. The time 203 indicates the time when the image was captured. The identification result 204 indicates the identification result of the worker detected from the image. For example, an ID or name for identifying the worker is recorded as the identification result. The accuracy 205 is the accuracy for the coordinates. The x coordinate 206 and the y coordinate 207 are the positions of the worker in the X direction and the Y direction, respectively, in the image. The x coordinate 208 and the y coordinate 209 are obtained by converting the x coordinate 206 and the y coordinate 207 into a common coordinate system, respectively. The work area 210 indicates the work area where the worker is present, and is derived by comparing the x coordinate 208 and the y coordinate 209 with the layout data. "Outside the area" indicates that the worker is not in any work area and is moving along a route. As described above, two or more positions calculated for the x coordinate 208 and the y coordinate 209 from two or more images acquired at the same time are appropriately integrated.

[0054] The first determination unit 13 determines the movement route of the worker from the processing result by the detection unit 12. First, the first determination unit 13 divides the processing result by worker and rearranges the divided data in chronological order. The first determination unit 13 refers to the work area of ​​the immediately preceding data for the data at each time. If the work area of ​​the immediately preceding data is "outside the area", the work area in which the worker was last located is set as the immediately preceding work area. If the current work area in the data at each time has not changed from the immediately preceding work area, the first determination unit 13 determines that the worker has not moved from the immediately preceding work area. If the current work area in the data at each time has changed from the immediately preceding work area, the first determination unit 13 determines that the worker has moved from the immediately preceding work area to the current work area. The first determination unit 13 determines the presence or absence of movement and the movement route for each worker.

[0055] FIG. 9 and FIG. 10(a) to FIG. 10(c) are tables showing the processing results by the first determination unit. 9 shows the extraction result of data related to worker X. The table 220 includes a data ID 221, a time 222, an identification result 223, a work area 224, a previous work area 225, and a movement route 226.

[0056] FIG. 9 shows the extraction results from data in which the positions of workers calculated from images at the same time have been integrated. Data ID 221 is a unique character string assigned to each piece of data after position integration. Time 222 indicates the time corresponding to the integrated position. Identification result 223, like identification result 204, indicates the identification result of the worker detected from the image. Work area 224 indicates the work area corresponding to the integrated position. Previous work area 225 indicates the previous work area at each time. Movement route 226 indicates the presence or absence of movement and the route.

[0057] The first determination unit 13 generates FromTo charts 230-232, for example, as shown in Figs. 10(a)-10(c), from the determination result of the movement route. In the FromTo charts 230-232, rows indicate source work areas. Columns indicate destination work areas. Cell values ​​indicate the number of movements (movement frequency) on that route. The FromTo charts 230 and 231 show the movement routes and movement frequencies of workers X and Y, respectively. The FromTo chart 232 shows the movement routes and movement frequencies of all workers.

[0058] FIG. 11 is a table showing the processing results by the second determination unit. The table 240 shown in FIG. 11 includes a data ID 241 , a time 242 , a worker 243 , first biometric data 244 , a score 245 , second biometric data 246 , a score 247 , and an activity intensity 248 .

[0059] The data ID 241 is a unique character string assigned to the biometric data and the work intensity judgment result obtained at each time. The time 242 indicates the time when the biometric data was obtained. The worker 243 indicates the worker to whom the measuring device 21 is attached. The first biometric data 244 and the second biometric data 246 indicate the biometric data obtained by the measuring device 21. The first biometric data 244 and the second biometric data 246 may be obtained by one measuring device 21 or may be obtained by separate measuring devices 21. The scores 245 and 247 indicate evaluations of the first biometric data 244 and the second biometric data 246, respectively, from the viewpoint of work intensity. The work intensity 248 indicates the work intensity judged based on the scores 245 and 247. The score 245, the score 247, and the work intensity 248 are calculated by the second judgment unit 14.

[0060] FIG. 12 is a table showing the data integrated by the second determination unit. The second determination unit 14 integrates the data of table 220 by the first determination unit 13 with the data of table 240. Specifically, the second determination unit 14 searches for data in which the time and the worker (identification result) match between tables 220 and 240, and integrates the data. The integrated table 250 obtained by the integration includes a data ID 251, a time 252, a worker 243, a work area 224, a previous work area 225, a movement path 226, a first biometric data 244, a score 245, a second biometric data 246, a score 247, and an activity intensity 248, as shown in FIG.

[0061] The output unit 15 generates an analysis result based on the FromTo chart generated by the first judgment unit 13 and the integrated table by the second judgment unit 14. The movement route between the multiple work areas in the analysis result and the movement frequency of the movement route are shown in the FromTo chart. The work intensity on the movement route is determined from the integrated table by the second judgment unit 14. For example, for data determined to be "outside the area" between the work area of ​​the movement source and the work area of ​​the movement destination, a time average of the score based on the biometric data is calculated. The calculated average value is compared with multiple thresholds to determine the work intensity on the movement route. The output unit 15 outputs the generated analysis result as shown in FIG. 3.

[0062] 13(a), 13(b), 14(a), 14(b), and 15 are schematic diagrams showing examples of output of analysis results. When an analysis is performed on multiple workers, the analysis results may include an overall analysis result and an individual analysis result. The output unit 15 is capable of switching between displaying the overall analysis result and displaying the individual analysis result. The overall analysis result indicates multiple movement paths, movement frequencies of each of the movement paths, and multiple work intensities for multiple workers. The individual analysis result indicates one or more of the multiple movement paths, movement frequencies of one or more of the multiple movement paths, and one or more work intensities for one of the multiple workers.

[0063] For example, the processing device 10 accepts a selection of a worker to be analyzed from a user in a GUI that displays an analysis result 150. As shown in FIG. 13(a), the analysis result 150 includes a pull-down menu 160. The user operates the input device 31 to move a pointer P. Clicking an icon 161 displays a list of workers. The user can move the pointer P to select a worker to be analyzed. When a worker is selected, the output unit 15 extracts data related to the selected worker in the FromTo chart and the integrated table. Based on the extracted data, the output unit 15 outputs an analysis result indicating the movement route, movement frequency, and work intensity on the movement route for only the selected worker, as shown in FIG. 13(b), for example.

[0064] By displaying the overall analysis results and the individual analysis results, the user can evaluate the layout from both the perspective of the overall work and the perspective of each individual worker. For example, the user can check whether the layout is appropriate for the overall work, and also check whether a heavy load is being placed on a specific worker.

[0065] The processing device 10 may accept a selection of a travel route from a user in a GUI that displays the analysis result 150. For example, as shown in FIG. 14(a), the user places a pointer P on one of the travel routes and clicks it. When a travel route is selected, an image 170 obtained by an imaging device 20 that includes the route in its imaging range is displayed as shown in FIG. 14(b). If the selected route is imaged by multiple imaging devices 20, a pull-down menu 171 is displayed. When an icon 172 is clicked, a list of the imaging devices 20 is displayed. The user can move the pointer P to select one of the imaging devices 20. When one of the imaging devices 20 is selected, the output unit 15 displays the image obtained by the selected imaging device 20.

[0066] 14(b), the imaging device 20 acquires a video, and the video captured along the selected route is displayed. In this case, a bar 173 and a slider 174 may be displayed. The user can specify a part of the video to be displayed by moving the slider 174.

[0067] The second determination unit 14 may process the biometric data so as to determine only the effect of the movement route on the work intensity. For example, as shown in FIG. 12, the measurement device 21 acquires biometric data of the worker while working in the work area and while moving. The second determination unit 14 calculates the difference between the biometric data while moving and the biometric data while working. This calculates the change in the biometric data due to the movement itself. The second determination unit 14 determines the work intensity due to the movement route based on the difference. For example, the second determination unit 14 determines the stress level due to the movement by comparing the change in heart rate variability due to the movement with multiple preset thresholds. The second determination unit 14 may determine the risk of heat stroke due to the movement from the change in body temperature or the amount of sweating due to the movement.

[0068] If the above-mentioned difference is not used, the movement after a heavy load task may be determined to be heavy work load for the worker even if the load of the movement itself is light. For example, if the fatigue caused by the movement itself is sufficiently small and the safety during the movement is high, the distance of the movement route does not necessarily need to be shortened. By determining only the work load of the movement using the above-mentioned difference, it is possible to obtain analysis results that are more useful for layout design.

[0069] The output unit 15 may further include the work intensity of the worker in each work area in the analysis result. For example, in the analysis result 151 shown in Fig. 15, marks 181-185 are displayed in each of the multiple work areas 111-115. The size (diameter) of each mark indicates the time spent in that work area. The color of the mark (density of dots) indicates the intensity of work in that work area. In the example of Fig. 15, a lower dot density indicates a lower intensity of work.

[0070] The second determination unit 14 may process the biometric data so as to determine only the effect on the work intensity due to the entire work. For example, the measurement device 21 acquires biometric data of the worker before and after the start of work. The biometric data before the start of work may be input by the user. The second determination unit 14 calculates the difference between the biometric data obtained after the start of work and the biometric data before the start of work. This calculates the change in the biometric data due to the work itself. The second determination unit 14 determines the work intensity during work and movement after the start of work based on the difference. This makes it possible to determine only the work intensity due to the work.

[0071] The second determination unit 14 may process the biometric data so as to determine only the effect of each individual task on the task intensity. For example, the second determination unit 14 calculates the difference between the biometric data at the start of task in one task area and the biometric data at the end of task in that task area. The second determination unit 14 regards the time immediately after a movement as the start of task, and the time immediately before the next movement as the end of task. This allows the change in the biometric data due to each individual task to be calculated. The second determination unit 14 determines the task intensity of each individual task based on the difference.

[0072] The output unit 15 may calculate a score indicating the evaluation of the layout based on the movement route, the movement frequency, and the biometric data. For example, the output unit 15 time-integrates the scores of the biometric data for each movement route. The output unit 15 calculates the evaluation of the layout by comparing the obtained score with a plurality of preset thresholds. An evaluation value indicating the evaluation of the layout may be calculated. For example, the time integral value of the score is output as the evaluation value. Alternatively, the calculated time integral value may be standardized using evaluation values ​​related to past layouts. The standardized value is output as the evaluation value.

[0073] FIG. 16 is a schematic diagram showing a hardware configuration. The processing device 10 includes, for example, the hardware configuration shown in Fig. 14. A computer 90 shown in Fig. 14 includes a CPU 91, a ROM 92, a RAM 93, a storage device 94, an input interface 95, an output interface 96, and a communication interface 97.

[0074] The ROM 92 stores a program for controlling the operation of the computer. The ROM 92 stores programs necessary for the computer to realize each of the above-mentioned processes. The RAM 93 functions as a storage area in which the programs stored in the ROM 92 are expanded.

[0075] The CPU 91 includes a processing circuit. The CPU 91 uses a RAM 93 as a working memory and executes a program stored in at least one of a ROM 92 and a storage device 94. During execution of the program, the CPU 91 controls each component via a system bus 98 and executes various processes.

[0076] The storage device 94 stores data necessary for executing the programs and data obtained by executing the programs.

[0077] The input interface (I / F) 95 connects the computer 90 and the input device 95a. The input I / F 95 is, for example, a serial bus interface such as USB. The CPU 91 can read various data from the input device 95a via the input I / F 95.

[0078] The output interface (I / F) 96 connects the computer 90 and the output device 96a. The output I / F 96 is, for example, a video output interface such as a Digital Visual Interface (DVI) or a High-Definition Multimedia Interface (HDMI (registered trademark)). The CPU 91 transmits data to the output device 96a via the output I / F 96 and can cause the output device 96a to display an image.

[0079] A communication interface (I / F) 97 connects the computer 90 to a server 97a external to the computer 90. The communication I / F 97 is, for example, a network card such as a LAN card. The CPU 91 can read various data from the server 97a via the communication I / F 97. The camera 99 photographs an item and stores the image in the server 97a.

[0080] The storage device 94 includes one or more selected from a hard disk drive (HDD) and a solid state drive (SSD). The input device 95a includes one or more selected from a mouse, a keyboard, a microphone (audio input), and a touch pad. The output device 96a includes one or more selected from a monitor and a projector. A device having the functions of both the input device 95a and the output device 96a, such as a touch panel, may be used.

[0081] The storage device 94 may function as the storage device 30. The input device 95a may function as the input device 31. The output device 96a may function as the output device 32. The camera 99 may function as the imaging device 20.

[0082] The various data processing operations described above may be recorded as a program that can be executed by a computer on a magnetic disk (such as a flexible disk or a hard disk), an optical disk (such as a CD-ROM, CD-R, CD-RW, DVD-ROM, DVD±R, DVD±RW), a semiconductor memory, or other non-transitory computer-readable storage medium.

[0083] For example, information recorded on a recording medium can be read by a computer (or an embedded system). The recording medium may have any recording format (storage format). For example, the computer reads a program from the recording medium and causes a CPU to execute instructions described in the program based on the program. The computer may acquire (or read) the program via a network.

[0084] According to the embodiment described above, an analysis system and an analysis method capable of analyzing an operation from the viewpoints of efficiency and safety are provided. Moreover, the same effect can be obtained by causing a computer to execute the above-mentioned analysis method.

[0085] Although some embodiments of the present invention have been illustrated above, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, modifications, etc. can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention, and are included in the scope of the invention and its equivalents described in the claims. In addition, the above-mentioned embodiments can be implemented in combination with each other. [Explanation of symbols]

[0086] 1: analysis system, 10: processing device, 11: acquisition unit, 12: detection unit, 13: first judgment unit, 14: second judgment unit, 15: output unit, 20, 20a to 20k: imaging device, 21: measurement device, 30: storage device, 31: input device, 32: output device, 90: computer, 91: CPU, 92: ROM, 93: RAM, 94: storage device, 95: input interface, 95a: input device, 96: output interface, 96a: output device, 97: communication interface, 97a: server, 98: system bus, 99: camera, 100: layout data, 101: image, 110: work site, 111 to 115: work area, 121 to 128: route, 131 to 133: worker, 150, 151: analysis results, 160: pull-down menu, 161: icon, 170: image, 171: pull-down menu, 172: icon, 174: slider, 181 to 185: mark, IM, IM1: image, M: map data

Claims

1. A detection unit that detects a worker at a work site from an image of the worker and calculates a position of the worker; a first determination unit that refers to layout data relating to a layout of a plurality of work areas in the work site and determines a movement path of the worker in the layout based on the calculated position; a second determination unit that determines a work intensity of the worker from biometric data of the worker; an output unit that outputs an analysis result indicating the layout, the movement path between the plurality of work areas, a movement frequency of the movement path, and the work intensity on the movement path; An analysis system comprising:

2. The analysis system according to claim 1 , wherein the layout data includes an image showing the layout, origin coordinates, axial directions, coordinates of each of the plurality of work areas, and paths between the plurality of work areas.

3. The analysis system according to claim 1 , further comprising an acquisition unit configured to acquire the images obtained by imaging the plurality of work areas and paths between the plurality of work areas.

4. the detection unit calculates a position of the worker in each of the plurality of images and converts the respective positions into positions in a common coordinate system in the layout; 4. The analysis system according to claim 1, wherein the first determination unit determines the movement path by using the position in the common coordinate system.

5. The analysis system of claim 4, wherein when the same worker appears in two or more images taken at the same time, the detection unit calculates a position accuracy for each of the two or more images and combines the two or more positions into one using the two or more probabilities.

6. The detection unit calculates positions of the plurality of workers from the plurality of images and identifies each of the plurality of workers; The first determination unit determines the movement path of each of the plurality of workers, 6. The analysis system according to claim 1, wherein the second determination unit determines the work intensity of each of the plurality of workers from the plurality of biological data of the plurality of workers.

7. The results of the analysis are as follows: an overall analysis result indicating a plurality of the movement paths, the movement frequencies, and a plurality of the work intensities for the plurality of workers; an individual analysis result indicating one or more of the plurality of movement paths, the movement frequency in the one or more of the plurality of movement paths, and one or more of the plurality of work intensities for one of the plurality of workers; The analytical system of claim 6 .

8. The analysis system according to claim 1 , wherein the output unit calculates an evaluation of the layout based on the movement route, the movement frequency, and the biological data.

9. The analysis system according to any one of claims 1 to 8, wherein the second determination unit calculates the work intensity on the movement path using a difference between the biometric data obtained during movement between the plurality of work areas and the biometric data obtained elsewhere.

10. On the computer, Detecting a worker at a work site from an image showing the worker; Calculating the position of the worker in the image; Referencing layout data relating to the layout of a plurality of work areas in the work site; determining a movement path of the worker in the layout based on the calculated position; determining a work intensity of the worker from biometric data of the worker; outputting an analysis result indicating the layout, the movement path between the plurality of work areas, a movement frequency of the movement path, and the work intensity on the movement path; Analysis method.

11. On the computer, Detecting a worker at a work site from an image showing the worker; Calculating the position of the worker in the image; Referencing layout data relating to the layout of a plurality of work areas in the work site; determining a movement path of the worker in the layout based on the calculated position; determining a work intensity of the worker from biometric data of the worker; outputting an analysis result indicating the layout, the movement path between the plurality of work areas, a movement frequency of the movement path, and the work intensity on the movement path; program.

12. A storage medium storing the program according to claim 11.

Images