Information processor

Abstract

To appropriately search for travel routes based on the monotony of the surrounding landscape.SOLUTION: An information processor according to the present application comprises an acquisition unit that acquires the monotonicity of the surrounding landscape at a given point or along a given section, and a search unit that searches for travel routes based on the monotonicity of the given point or section included in the travel routes of a moving body.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to an information processing apparatus.

Background Art

[0002] Generally, when driving for a long time on a road with monotonous scenery such as a highway, a phenomenon of falling into a hypnotic state such as drowsiness is known as highway hypnosis. Also, on a road with no change in scenery or with poor scenery change, or a road having streetlights installed regularly at equal intervals, drowsiness may be induced.

[0003] As an invention for detecting such a monotonous road, for example, a technique is known in which feature judgment processing is performed to classify scenery, and the monotony degree is obtained based on the count of the number of scenery changes (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the conventional technology, for example, in the case of the invention described in Patent Document 1, since feature judgment processing is performed to classify scenery and the monotony degree is obtained based on the count of the number of scenery changes, even if the scenery is complex like "urban landscape", if the time change or position change is small, the monotony degree will be determined to be low. Therefore, even if there are many signs and billboards in a straight single-lane road, it may be determined to be monotonous. For this reason, with the conventional technology, it is not possible to detect a tendency of monotony from the captured image, and it is not possible to appropriately search for a driving route based on the monotony degree of the surrounding scenery.

[0006] As an example of the problem to be solved by the present invention, appropriately searching for a driving route based on the monotony of the surrounding scenery can be cited.

Means for Solving the Problem

[0007] The information processing apparatus according to claim 1 is characterized by including: an acquisition unit that acquires the monotony of the scenery around a point or a section; and a search unit that searches for the driving route based on the monotony of the point or the section included in the driving route of the moving body.

[0008] Further, the information processing method according to claim 7 is an information processing method executed by an information processing apparatus, and is characterized by including: an acquisition step of acquiring the monotony of the scenery around a point or a section; and a search step of searching for the driving route based on the monotony of the point or the section included in the driving route of the moving body.

[0009] Further, the information processing program according to claim 8 is an information processing program for causing a computer to execute: an acquisition step of acquiring the monotony of the scenery around a point or a section; and a search step of searching for the driving route based on the monotony of the point or the section included in the driving route of the moving body.

[0010] Further, the storage medium according to claim 9 is characterized by storing an information processing program for causing a computer to execute: an acquisition step of acquiring the monotony of the scenery around a point or a section; and a search step of searching for the driving route based on the monotony of the point or the section included in the driving route of the moving body.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Embodiments for Carrying Out the Invention

[0012] Hereinafter, embodiments for carrying out the present invention (hereinafter referred to as embodiments) will be described with reference to the drawings. Note that the present invention is not limited by the embodiments described below. Further, in the description of the drawings, the same parts are denoted by the same reference numerals.

[0013] (Embodiment 1) 〔Schematic Configuration of Information Processing System〕 FIG. 1 is a block diagram showing the configuration of the information processing system 1 according to Embodiment 1. The information processing system 1 is a system that searches for a driving route based on the monotony of a point or section included in the driving route of the vehicle VE (FIG. 1), which is a moving object, and presents the searched driving route to the passengers. Here, the passengers may be either the driver or the passengers.

[0014] As shown in FIG. 1, this information processing system 1 includes an in-vehicle terminal 2 and an information processing device 3. The in-vehicle terminal 2 and the information processing device 3 communicate with each other via a network NE (FIG. 1), which is a wireless communication network. In the following description of the embodiments, the case where the user (passenger) uses an automobile as a means of transportation will be described as an example, but it is not limited thereto. For example, the means of transportation may be a bicycle, a motorcycle, or the like.

[0015] Note that, as an example in FIG. 1, the in-vehicle terminal 2 that communicates with the information processing device 3 is shown as one unit, but it may be a plurality of units respectively mounted on a plurality of vehicles. Also, in order to execute services for a plurality of passengers riding in one vehicle respectively, a plurality of in-vehicle terminals 2 may be mounted on one vehicle.

[0016] The in-vehicle terminal 2 is, for example, a stationary navigation device or a drive recorder installed in the vehicle VE. Note that the in-vehicle terminal 2 is not limited to a navigation device or a drive recorder, and a portable terminal such as a smartphone used by the passenger PA of the vehicle VE may be adopted.

[0017] 〔Configuration of Information Processing Device〕 FIG. 2 is a block diagram showing the configuration of the information processing device 3. The information processing device 3 is, for example, a server device. As shown in FIG. 3, this information processing device 3 includes a communication unit 31, a control unit 32, and a storage unit 33.

[0018] The communication unit 31 transmits and receives information to and from the in-vehicle terminal 2 via the network NE under the control of the control unit 32.

[0019] The storage unit 33 stores various programs (information processing programs according to the present embodiment) executed by the control unit 32, as well as data and the like necessary when the control unit 32 performs processing. As shown in FIG. 3, this storage unit 33 includes a map information DB 33a.

[0020] The map information DB 33a stores a map (monotony map) indicating the monotony of a location or section generated by a map generation unit 32a described later. For example, as illustrated in FIG. 3, the map information DB 33a stores a monotony map indicating the monotony of the surrounding scenery for each location or section. Note that the map information DB 33a is not limited to storing the monotony map generated by the map generation unit 32a, and the storage unit 33 may store a pre-generated monotony map. Further, instead of the monotony map, the map information DB 33 may store a table in which a location or section and its monotony are associated.

[0021] The control unit 32 is realized by executing various programs (including information processing programs according to the present embodiment) stored in the storage unit 33 by a controller such as a CPU or MPU, and controls the operation of the entire information processing apparatus 3. Note that the control unit 32 is not limited to a CPU or MPU, and may be configured by an integrated circuit such as an ASIC or FPGA. As shown in FIG. 2, this control unit 32 includes a map generation unit 32a, an acquisition unit 32b, and a search unit 32c. Note that the map generation process may be performed by another device in advance, and another device may have the map generation unit 32a.

[0022] The map generation unit 32a generates a map indicating the monotony of a location or section using an image captured from the outside by the vehicle VE and the position information of the vehicle VE. For example, based on the image captured from the outside by the vehicle VE, the map generation unit 32a estimates visual saliency distribution information obtained by estimating the level of visual saliency in the image, calculates the monotony of the location or section indicated by the position information corresponding to the visual saliency distribution information based on the visual saliency distribution information, and generates a map based on the monotony.

[0023] Hereinafter, with reference to FIGS. 4 to 9, the process in which the map generation unit 32a estimates visual saliency distribution information will be described. FIG. 4(a) is a diagram illustrating an image input to the map generation unit 32a, and FIG. 4(b) is a diagram illustrating an image showing the visual saliency distribution estimated for FIG. 4(a). The map generation unit 32a estimates the visual saliency of each part in the image. Visual saliency means, for example, the ease of being noticeable or the ease of attracting the line of sight. Specifically, visual saliency is indicated by a probability or the like. Here, the magnitude of the probability corresponds to, for example, the magnitude of the probability that the line of sight of a person who has seen the image will be directed to that position.

[0024] FIGS. 4(a) and 4(b) are in corresponding positions to each other. And in FIG. 4(a), the higher the visual saliency, the higher the luminance is displayed in FIG. 4(b). An image showing the visual saliency distribution like FIG. 4(b) is an example of the visual saliency distribution. In the example of this figure, the visual saliency is visualized with a luminance value of 256 gradations. Examples of the visual saliency distribution will be described in detail later.

[0025] FIG. 5 is a flowchart illustrating the operation of the map generation unit 32a according to the present embodiment. The flowchart shown in FIG. 5 is a part of an information processing method executed by a computer, and includes an input step S110, a non-linear mapping step S120, and an output step S130. In the input step S110, for example, the map generation unit 32a receives an image (moving image) captured by a camera or the like of the in-vehicle terminal 2 and position information (point data) of the vehicle VE output from a GPS (Global Positioning System) receiver or the like, and associates the image with the point data. Note that the input moving image is output as image data decomposed in time series such as for each frame. Although a still image may be input as the image input to the map generation unit 32a, it is preferable to input it as a group of still images along a time series.

[0026] Then, the image is converted into intermediate data that can be subjected to mapping processing. In the non-linear mapping step S120, the intermediate data is converted into mapping data. In the output step S130, visual saliency estimation information (visual saliency distribution information) indicating a saliency distribution is generated based on the mapping data. Here, the non-linear mapping step S120 includes a feature extraction step S121 that extracts features from the intermediate data, and an upsampling step S122 that upsamples the data generated in the feature extraction step S121.

[0027] In the input step S110, the map generation unit 32a acquires an image and converts it into intermediate data. The map generation unit 32a acquires image data from the in-vehicle terminal 2 of the vehicle VE. The image may be, for example, an image captured in the traveling direction of the vehicle. That is, it is an image continuously captured of the outside from the in-vehicle terminal 2. This image may be a so-called panoramic image or an image including directions other than the traveling direction such as 180° or 360° in the horizontal direction, such as an image obtained using a plurality of cameras. Further, the input image is not limited to an image captured by a camera, and may be an image read from a recording medium such as a hard disk drive or a memory card.

[0028] After acquiring the image, the map generation unit 32a converts the acquired image into intermediate data. The intermediate data is not particularly limited as long as it is data that the map generation unit 32a can receive, but is, for example, a high-dimensional tensor. Further, the intermediate data is, for example, data obtained by normalizing the luminance of the acquired image, or data obtained by converting each pixel of the acquired image into the slope of the luminance. In the input step S110, the map generation unit 32a may further perform noise removal or resolution conversion of the image.

[0029] In the non-linear mapping step S120, the map generation unit 32a converts the intermediate data into mapping data. Here, the mapping data is, for example, a high-dimensional tensor. The mapping process applied to the intermediate data is preferably a mapping process that can be controlled by, for example, parameters, and is a process by a function, a functional, or a neural network.

[0030] FIG. 6 is a diagram illustrating in detail the processing of the non-linear mapping step, and FIG. 6 is a diagram illustrating the configuration of the intermediate layer 323. The map generation unit 32a includes a non-linear mapping unit 320 that converts intermediate data into mapping data. The non-linear mapping unit 320 includes a feature extraction unit 321 that extracts features from the intermediate data, and an upsampling unit 322 that performs upsampling of the data generated by the feature extraction unit 321. The feature extraction step S121 is performed in the feature extraction unit 321, and the upsampling step S122 is performed in the upsampling unit 322. Also, in the example of this figure, at least one of the feature extraction unit 321 and the upsampling unit 322 is configured to include a neural network including a plurality of intermediate layers 323. In the neural network, a plurality of intermediate layers 323 are combined.

[0031] In particular, the neural network is preferably a convolutional neural network. Specifically, each of the plurality of intermediate layers 323 includes one or two or more convolutional layers 324. And in the convolutional layer 324, convolution of the input data is performed by a plurality of filters 325, and activation processing is performed on the outputs of the plurality of filters 325.

[0032] In the example of FIG. 6, the feature extraction unit 321 is configured to include a neural network including a plurality of intermediate layers 323, and includes a first pooling unit 326 between the plurality of intermediate layers 323. Also, the upsampling unit 322 is configured to include a neural network including a plurality of intermediate layers 323, and includes an unpooling unit 328 between the plurality of intermediate layers 323. Further, the feature extraction unit 321 and the upsampling unit 322 are connected to each other via a second pooling unit 327 that performs overlapping pooling.

[0033] In the example of this figure, each intermediate layer 323 is composed of two or more convolutional layers 324. However, at least a part of the intermediate layers 323 may be composed of only one convolutional layer 324. Adjacent intermediate layers 323 are separated by any one of the first pooling unit 326, the second pooling unit 327, and the unpooling unit 328. Here, when two or more convolutional layers 324 are included in the intermediate layer 323, it is preferable that the number of filters 325 in these convolutional layers 324 is equal to each other.

[0034] In this figure, the intermediate layer 323 marked as "A×B" is composed of B convolutional layers 324, and each convolutional layer 324 means including A convolutional filters for each channel. Such an intermediate layer 323 is also referred to as an "A×B intermediate layer" hereinafter. For example, the 64×2 intermediate layer 323 is composed of two convolutional layers 324, and each convolutional layer 324 means including 64 convolutional filters for each channel.

[0035] In the example of this figure, the feature extraction unit 321 includes a 64×2 intermediate layer 323, a 128×2 intermediate layer 323, a 256×3 intermediate layer 323, and a 512×3 intermediate layer 323 in this order. Also, the upsampling unit 322 includes a 512×3 intermediate layer 323, a 256×3 intermediate layer 323, a 128×2 intermediate layer 323, and a 64×2 intermediate layer 323 in this order. Also, the second pooling unit 327 connects two 512×3 intermediate layers 323 to each other. Note that the number of intermediate layers 323 constituting the non-linear mapping unit 320 is not particularly limited, and can be determined according to, for example, the number of pixels of the image data.

[0036] Note that this figure is an example of the configuration of the non-linear mapping unit 320 included in the map generation unit 32a, and the non-linear mapping unit 320 may have other configurations. For example, a 64×1 intermediate layer 323 may be included instead of the 64×2 intermediate layer 323. By reducing the number of convolutional layers 324 included in the intermediate layer 323, the calculation cost may be further reduced. Also, for example, a 32×2 intermediate layer 323 may be included instead of the 64×2 intermediate layer 323. By reducing the number of channels in the intermediate layer 323, the calculation cost may be further reduced. Furthermore, both the number of convolutional layers 324 and the number of channels in the intermediate layer 323 may be reduced.

[0037] Here, in the plurality of intermediate layers 323 included in the feature extraction unit 321, it is preferable that the number of filters 325 increases every time passing through the first pooling unit 326. Specifically, the first intermediate layer 323a and the second intermediate layer 323b are continuous with each other via the first pooling unit 326, and the second intermediate layer 323b is located after the first intermediate layer 323a. The first intermediate layer 323a is composed of convolutional layers 324 where the number of filters 325 for each channel is N1, and the second intermediate layer 323b is composed of convolutional layers 324 where the number of filters 325 for each channel is N2. At this time, it is preferable that N2 > N1 holds. More preferably, N2 = N1 × 2 holds.

[0038] Also, in the plurality of intermediate layers 323 included in the upsampling unit 322, it is preferable that the number of filters 325 decreases every time passing through the unpooling unit 328. Specifically, the third intermediate layer 323c and the fourth intermediate layer 323d are continuous with each other via the unpooling unit 328, and the fourth intermediate layer 323d is located after the third intermediate layer 323c. The third intermediate layer 323c is composed of convolutional layers 324 where the number of filters 325 for each channel is N3, and the fourth intermediate layer 323d is composed of convolutional layers 324 where the number of filters 325 for each channel is N4. At this time, it is preferable that N4 < N3 holds. More preferably, N3 = N4 × 2 holds.

[0039] In the feature extraction unit 321, image features having a plurality of levels of abstraction, such as gradients and shapes, are extracted from the intermediate data as channels of the intermediate layer 323. FIG. 7 illustrates the configuration of the intermediate layer 323. With reference to this figure, the processing in the intermediate layer 323 will be described. In the example of this figure, the intermediate layer 323 is composed of a first convolutional layer 324a and a second convolutional layer 324b, and each convolutional layer 324 includes 64 filters 325. In the first convolutional layer 324a, convolution processing using the filter 325 is performed on each channel of the data input to the intermediate layer 323. For example, when the image input to the map generation unit 32a is an RGB image, processing is performed on each of the three channels h 0 i (i = 1..3). Also, in the example of this figure, the filter 325 is a 3×3 filter of 64 types, that is, a total of 64×3 types of filters. As a result of the convolution processing, for each channel i, 64 results h 0 i,j (i = 1..3, j = 1..64) are obtained.

[0040] Next, activation processing is performed on the outputs of the plurality of filters 325 in the activation unit 329. Specifically, activation processing is performed on the sum of the corresponding elements for the corresponding results j of all channels. By this activation processing, the results h of 64 channels 1 i (i = 1..64), that is, the output of the first convolutional layer 324a, is obtained as an image feature. The activation processing is not particularly limited, but a process using at least one of a hyperbolic function, a sigmoid function, and a rectified linear function is preferable.

[0041] Furthermore, the output data of the first convolutional layer 324a is used as the input data of the second convolutional layer 324b, and the same processing as that of the first convolutional layer 324a is performed in the second convolutional layer 324b to obtain 64-channel results h 2 i(i = 1..64), that is, the output of the second convolutional layer 324b is obtained as image features. The output of the second convolutional layer 324b becomes the output data of this 64×2 intermediate layer 323.

[0042] Here, the structure of the filter 325 is not particularly limited, but it is preferably a 3×3 two-dimensional filter. Also, the coefficients of each filter 325 can be set independently. In this embodiment, the coefficients of each filter 325 are held in the storage unit 33, and the non-linear mapping unit 320 can read it out and use it for processing. Here, the coefficients of the plurality of filters 325 may be determined based on correction information generated and corrected using machine learning. For example, the correction information includes the coefficients of the plurality of filters 325 as a plurality of correction parameters. The non-linear mapping unit 320 can further use this correction information to convert the intermediate data into mapped data.

[0043] FIG. 8(a) and FIG. 8(b) are diagrams showing examples of the convolution process performed by the filter 325. In both FIG. 8(a) and FIG. 8(b), examples of 3×3 convolution are shown. The example in FIG. 8(a) is a convolution process using the nearest neighbor elements. The example in FIG. 8(b) is a convolution process using neighboring elements with a distance of two or more. Note that a convolution process using neighboring elements with a distance of three or more is also possible. The filter 325 preferably performs a convolution process using neighboring elements with a distance of two or more. This is because more extensive features can be extracted and the estimation accuracy of visual saliency can be further improved.

[0044] The operation of the 64×2 intermediate layer 323 has been described above. The operations of other intermediate layers 323 (such as the 128×2 intermediate layer 323, the 256×3 intermediate layer 323, and the 512×3 intermediate layer 323) are the same as the operation of the 64×2 intermediate layer 323, except for the number of convolutional layers 324 and the number of channels. Also, the operation of the intermediate layer 323 in the feature extraction unit 321 and the operation of the intermediate layer 323 in the upsampling unit 322 are the same as above.

[0045] FIG. 9(a) is a diagram for explaining the processing of the first pooling unit 326, FIG. 9(b) is a diagram for explaining the processing of the second pooling unit 327, and FIG. 9(c) is a diagram for explaining the processing of the unpooling unit 328.

[0046] In the feature extraction unit 321, the data output from the intermediate layer 323 is input to the next intermediate layer 323 after being subjected to pooling processing for each channel in the first pooling unit 326. In the first pooling unit 326, for example, non-overlapping pooling processing is performed. FIG. 9(a) shows the process of associating four 2×2 elements 30 included in each channel with one element 30. In the first pooling unit 326, such association is performed for all elements 30. Here, the four 2×2 elements 30 are selected so as not to overlap with each other. In this example, the number of elements in each channel is reduced to one-fourth. Note that as long as the number of elements is reduced in the first pooling unit 326, the number of elements 30 before and after the association is not particularly limited.

[0047] The data output from the feature extraction unit 321 is input to the upsampling unit 322 via the second pooling unit 327. In the second pooling unit 327, overlapping pooling is performed on the output data from the feature extraction unit 321. FIG. 9(b) shows the process of associating four 2×2 elements 30 with one element 30 while overlapping some of the elements 30. That is, in the repeated association, some of the four 2×2 elements 30 in a certain association are also included in the four 2×2 elements 30 in the next association. In the second pooling unit 327 as shown in this figure, the number of elements is not reduced. Note that the number of elements 30 before and after the association in the second pooling unit 327 is not particularly limited.

[0048] The method of each process performed in the first pooling unit 326 and the second pooling unit 327 is not particularly limited. For example, there may be a correspondence (max pooling) in which the maximum value of four elements 30 is set to one element 30, or a correspondence (average pooling) in which the average value of four elements 30 is set to one element 30.

[0049] The data output from the second pooling unit 327 is input to the intermediate layer 323 in the upsampling unit 322. Then, the output data from the intermediate layer 323 of the upsampling unit 322 is input to the next intermediate layer 323 after being subjected to an unpooling process for each channel in the unpooling unit 328. FIG. 9(c) shows a process of expanding one element 30 into a plurality of elements 30. The method of expansion is not particularly limited, and for example, a method of replicating one element 30 into four 2×2 elements 30 can be cited as an example.

[0050] The output data of the last intermediate layer 323 of the upsampling unit 322 is output as mapping data, and in the output step S130, the map generation unit 32a generates a visual saliency distribution by performing, for example, normalization, resolution conversion, etc. on the acquired data. The visual saliency distribution is, for example, an image (image data) in which the visual saliency is visualized as luminance values as illustrated in FIG. 4(b). Further, the visual saliency distribution may be, for example, an image colored according to the visual saliency like a heat map, or an image in which a visually salient region where the visual saliency is higher than a predetermined criterion is marked distinguishable from other positions. Furthermore, the visual saliency estimation information is not limited to map information shown as an image or the like, and may be a table or the like listing information indicating the visually salient regions.

[0051] After generating the visual saliency distribution, the map generation unit 32a, for example, calculates various statistical quantities from the visual saliency distribution and calculates the monotonicity based on the statistical quantities. That is, the map generation unit 32a calculates the monotonicity of the image using the statistical quantities calculated based on the visual saliency distribution (visual saliency distribution information).

[0052] As a method for calculating the monotonicity, for example, the map generation unit 32a calculates the standard deviation of the luminance of each pixel in the image (e.g., FIG. 4(b)) constituting the visual saliency distribution. First, the average value of the luminance of each image in the image constituting the visual saliency distribution is calculated. If the image constituting the visual saliency distribution is H pixels × V pixels, and the luminance value at an arbitrary coordinate (k, m) is V VC(k,m) then the average value is calculated by the following equation (1).

[0053]

Equation

[0054] Then, the map generation unit 32a calculates the standard deviation of the luminance of each image in the image constituting the visual saliency distribution (i.e., the deviation of the luminance within the image) from the average value calculated by equation (1). The standard deviation SDEV is calculated by the following equation (2).

[0055]

Equation

[0056] Subsequently, the map generation unit 32a determines whether there are multiple output results for the calculated standard deviation. Here, it is determined whether the input image is a moving image, the visual saliency distribution is acquired in units of frames, and the standard deviations for a plurality of frames have been calculated.

[0057] If there are multiple output results, the map generation unit 32a calculates the eye movement amount. In this embodiment, the eye movement amount is obtained based on the coordinate distance of the maximum (highest) luminance value in the visual saliency distribution of each of the temporally preceding and succeeding frames. If the coordinate of the maximum luminance value in the previous frame is (x1, y1) and the coordinate of the maximum luminance value in the subsequent frame is (x2, y2), the eye movement amount VSA is calculated by the following equation (3).

[0058]

Equation

[0059] The monotonicity calculation unit 32a calculates the monotonicity based on the calculated standard deviation and the amount of gaze movement. When the output result is not plural (the input is a single image), the monotonicity calculation unit 32a calculates the monotonicity based on the standard deviation. For example, when the standard deviation is smaller than a predetermined value, it is determined that the deviation of the luminance of the visual saliency is large, that is, the monotonicity is judged. Alternatively, a numerical value (e.g., 0 to 1) indicating the monotonicity is output according to the value of the standard deviation. When the output result is plural (the input is a video), the monotonicity calculation unit 32a calculates the monotonicity based on the amount of gaze movement. For example, a threshold value is set for the amount of gaze movement, and the monotonicity is judged by comparing it with the threshold value. Alternatively, a numerical value (e.g., 0 to 1) indicating the monotonicity is output according to the value of the amount of gaze movement. That is, the monotonicity calculation unit 32a calculates such that the smaller the standard deviation or the amount of gaze movement is, the higher the monotonicity at that point or section becomes. Then, the monotonicity calculation unit 32a registers (adds) the monotonicity to the target point or section in the map data. The monotonicity calculation unit 32a stores the generated monotonicity map in the map information DB 33a. In the above description, the monotonic tendency was determined by the standard deviation, but it may be determined whether there is a monotonic tendency based on the average value of the luminance of the visual saliency distribution, that is, the result of the formula (1). In the case of the average value of the luminance, a threshold value may be set in the same manner as the standard deviation, and it may be determined whether there is a monotonic tendency by comparing it with the threshold value.

[0060] Returning to the description of FIG. 2, the acquisition unit 32b acquires the monotonicity of the scenery around the point or section. For example, the acquisition unit 32b acquires the monotonicity of the points or sections included on the driving route using the monotonicity map. That is, the acquisition unit 32b reads out the monotonicity map stored in the map information DB 33a, and for the points or sections included on the driving route from the starting point to the destination point, refers to the monotonicity map and acquires the monotonicity of the points or sections included on the driving route.

[0061] The search unit 32c searches for a travel route based on the monotony of points or sections included on the travel route of the moving body. For example, the search unit 32c determines whether the monotony acquired by the acquisition unit 32b satisfies a predetermined condition. When the predetermined condition is satisfied, the search unit 32c searches for a travel route so as to change the travel route including a point or section where the monotony is lower than a predetermined threshold to another route.

[0062] FIG. 10 is a diagram for explaining a process of re-searching a route according to the monotony of the searched travel route. For example, as illustrated in FIG. 10, the search unit 32c searches for a travel route from a departure point to a destination point in consideration of distance, arrival time, and the like. Then, the search unit 32c calculates, for example, the total value of monotony for each section of a predetermined distance (for example, 5 km) on the travel route that is the route search result. When the total value of monotony is equal to or greater than a predetermined threshold, the search unit 32c avoids the section from the travel route and re-searches for a travel route so as to pass through another route in a section where the total value of monotony is less than the predetermined threshold. After that, the search unit 32c notifies the in-vehicle terminal 2 of the vehicle VE of the route re-search result. To explain with a specific example, for example, when the outer ring road is a section with high monotony from the monotony map, the search unit 32c re-searches for a safety consideration route, avoids the outer ring road, and searches for a relatively safe alternative route that takes more time but has low monotony.

[0063] Note that the search unit 32c is not limited to the above for the search process of the travel route. For example, when the number of points or sections with a monotony equal to or greater than a predetermined threshold on the travel route that is the route search result is equal to or greater than a predetermined threshold, the travel route may be re-searched. Also, the search unit 32c may search for a travel route so that, for example, the total value of monotony for a predetermined distance does not become equal to or greater than a predetermined threshold and the arrival time is shortened. Further, the search unit 32c may search for a travel route so that, for example, the monotony of the travel route is minimized.

[0064] Further, while the vehicle VE is in motion, the search unit 32c may measure the driving time during which the vehicle has traveled a point or section where the monotony level is higher than a predetermined threshold value, and if the driving time exceeds the predetermined threshold value, the search unit 32c may search for a driving route. That is, while the vehicle VE is in motion, if the time during which the vehicle has traveled a point or section where the monotony level is higher than a predetermined threshold value is long, the search unit 32c searches for a driving route so as to change to another driving route. Thereby, the search unit 32c can reroute the driving route according to the monotony level even during driving. For example, when continuously driving a long distance on a monotonous road, the search unit 32c can search for a driving route with a low monotony level.

[0065] In addition, the search unit 32c measures the driving time during which the vehicle has traveled a point or section where the monotony level is higher than a predetermined threshold value, and if the driving time exceeds the predetermined threshold value, the search unit 32c controls to output an alert or music. Further, the search unit 32c may output an alert or music not only when the driving time exceeds the predetermined threshold value, but also when acquiring the biometric information of the driver and detecting drowsiness or the like. The music output here is notified to the in-vehicle terminal 2 so as to select and output, for example, stimulating up-tempo music. That is, in the information processing apparatus 3, since the driver's arousal level generally decreases when driving on a monotonous road for a certain period of time, an alert or music is output before that.

[0066] In this way, since the information processing apparatus 3 searches for a driving route that avoids a route with a high monotony level, it is possible to present a driving route considering safety to the user. For this reason, the information processing apparatus 3 can appropriately search for a driving route based on the monotony level of the surrounding scenery, and can avoid a route with a high monotony level to promote the safe driving of the driver.

[0067] [Information Processing Method] Next, an example of a map generation processing method executed by the information processing apparatus 3 (control unit 32) will be described. FIG. 11 is a flowchart showing the map generation processing method.

[0068] First, the map generation unit 32a acquires location data (step S210). The location data may be acquired from a GPS receiver or the like as described above.

[0069] Next, the map generation unit 32a acquires a driving video (image data) (step S220). In this step, the image data input to the input means 2 is decomposed into a time series such as image frames and associated with the location data acquired in step S210. Also, image processing such as noise removal and geometric transformation may be performed in this step. Note that steps S210 and S220 may be in reverse order.

[0070] Next, the map generation unit 32a extracts a visual saliency distribution (step S230). The visual saliency distribution outputs, in the map generation unit 32a, a visual saliency distribution as shown in FIG. 4(b) in a time series by the method described above.

[0071] Next, the map generation unit 32a calculates the standard deviation or the line-of-sight movement amount by the method described above, and calculates the monotonicity based on the standard deviation or the line-of-sight movement amount (step S240). Then, the map generation unit 32a registers (adds) the monotonicity to the target location or section in the map data (map S250). Note that the map generation unit 32a is not limited to the method of registering the monotonicity to all the target locations or sections in the map data to generate a monotonicity map. For example, as illustrated in FIG. 12, the monotonicity map may be generated by registering the monotonicity only to the locations or sections where the monotonicity is equal to or greater than a predetermined threshold. FIG. 12 is a diagram showing another example of the monotonicity map.

[0072] Next, an example of a search method executed by the information processing apparatus 3 (control unit 32) will be described. FIG. 13 is a flowchart showing the search method.

[0073] First, the search unit 32c searches for a driving route from the departure point to the destination point in consideration of factors such as distance and arrival time (step S310). Then, the search unit 32c determines whether the monotony of the points or sections included on the driving route satisfies a predetermined condition (step S320). As a result, if the monotony of the points or sections included on the driving route does not satisfy the predetermined condition (negative in step S320), the search unit 32c ends the process as it is.

[0074] On the other hand, if the monotony of the points or sections included on the driving route satisfies the predetermined condition (positive in step S320), the search unit 32c avoids the section from the driving route and re-searches for the driving route so that another route passes through a section where the total value of the monotony is less than a predetermined threshold (step S330).

[0075] For example, the search unit 32c calculates the total value of the monotony for each section of a predetermined distance (e.g., 5 km) on the driving route which is the route search result. If the total value of the monotony is equal to or greater than the predetermined threshold, the search unit 32c avoids the section from the driving route and re-searches for the driving route so that another route passes through a section where the total value of the monotony is less than the predetermined threshold. After that, the search unit 32c notifies the in-vehicle terminal 2 of the vehicle VE of the route re-search result.

[0076] According to the first embodiment described above, the following effects can be obtained. The information processing apparatus 3 according to the first embodiment acquires the monotony of the scenery around the point or section, and searches for the driving route based on the monotony of the points or sections included on the driving route of the moving body. Therefore, according to the information processing apparatus 3, it is possible to appropriately search for the driving route based on the monotony of the surrounding scenery.

[0077] Further, the information processing device 3 determines whether or not the monotony of a point or section included in the driving route satisfies a predetermined condition, and when the predetermined condition is satisfied, searches for a driving route including a point or section where the monotony is higher than a predetermined threshold value and changes it to another route. Thereby, the information processing device 3 can re-search for a driving route considering safety for the user even if the driving route is searched considering, for example, distance, arrival time, etc., and is a driving route with high monotony.

[0078] Further, while the vehicle VE is in motion, the information processing device 3 searches for a driving route so as to change to another driving route when the time taken to drive through a point or section where the monotony is higher than a predetermined threshold value is long. Thereby, since the information processing device 3 can re-route the driving route according to the monotony even during driving, for example, when continuously driving on a monotonous road for a long distance, it is possible to re-search for a driving route with low monotony.

[0079] Further, the information processing device 3 measures the driving time taken to drive through a point or section where the monotony is higher than a predetermined threshold value, and when the driving time exceeds a predetermined threshold value, outputs an alert or music. Thereby, the information processing device 3 can, for example, wake up drowsiness and alert the driver by outputting an alert or music when driving on a monotonous road continues and the driver feels drowsy.

[0080] (Other Embodiments) So far, the embodiments for carrying out the present invention have been described. However, the present invention should not be limited only by the above-described embodiments. In the above-described embodiments, all the configurations of the information processing apparatus 3 may be provided in the in-vehicle terminal 2. In this case, the in-vehicle terminal 2 corresponds to the information processing apparatus according to the present embodiment. Also, some of the functions of the control unit 32 in the information processing apparatus 3 may be provided in the in-vehicle terminal 2. In this case, the entire information processing system 1 corresponds to the information processing apparatus according to the present embodiment. Further, not limited to in-vehicle devices, portable terminals or mobile terminals that can be used inside the vehicle may also be used. Also, in the cost calculation in the route search of conventional navigation, the above-described monotonicity may be added to the calculation. In that case, the cost weight for monotonicity may be adjusted so that non-monotonic roads can be preferentially traveled.

Explanation of Reference Numerals

[0081] 3 Information processing apparatus 32a Map generation unit 32b Acquisition unit 32c Search unit

Claims

【Claim 1】 An acquisition unit that acquires the monotony degree of the scenery around a location or section; A search unit that searches for the travel route based on the monotony degree of the location or section included on the travel route of the mobile body An information processing apparatus characterized by comprising the above.

Images