Apparatus and method for setting navigation destination

Abstract

The present application relates to an apparatus and method for setting a navigation destination, the apparatus comprising: an image capturing device configured to capture a predetermined image; a vision-based recognition device configured to recognize a figure in the predetermined image and determine a destination; a database configured to store map data; and a controller configured to control the image capturing device and the vision-based recognition device, wherein, when a user input for requesting recognition of a rough map is received, the controller recognizes a region of the rough map from the image captured by the image capturing device and captures a rough map image, controls the vision-based recognition device to recognize the destination and a nearby place of the destination from the rough map image, and searches for candidates of the destination from the database.

Description

TECHNICAL FIELD

[0001] The disclosure relates to a navigation destination setting apparatus, and more particularly, to an apparatus and method of setting a navigation destination for recognizing a destination from a rough map image and setting the navigation destination. BACKGROUND

[0002] Generally, a navigation apparatus establishes a large amount of map information and road information in the form of a searchable database (DB), includes a global positioning system (GPS) module to recognize a current position via communication with a satellite, and matches the recognized current position with the map information and road information established in the form of the DB to guide a driver through a path to a destination set by the driver in real time.

[0003] The navigation apparatus can receive information about a destination of a business name, a batch number, or a telephone number from a user, can search for the destination using a key input device or a touch screen, can search for a path to the found destination from a current position, can map-match the found path with map data, and then guide a route along the path.

[0004] However, for the navigation apparatus, it is inconvenient for a user to directly input information about a place name, a business name, an address, a telephone number, or a destination name one by one by using a key input device or a touch screen in order to search for a destination.

[0005] Therefore, there is a need to develop an apparatus for setting a destination of a navigation apparatus to recognize a destination from a rough map image and automatically set the destination of the navigation apparatus. SUMMARY

[0006] An object of the disclosure is to provide an apparatus and method of setting a navigation destination for recognizing a destination from a rough map image captured by an image captured and automatically setting the navigation destination based on the recognized destination, thereby providing a user with convenience.

[0007] Technical problems solved by the embodiments are not limited to the above-described technical problems, and other technical problems not described herein will become apparent to those skilled in the art from the following description.

[0008] To achieve these objects and other advantages and in accordance with the purpose of the present disclosure, as embodied and broadly described herein, an apparatus for setting a navigation destination includes an image capturing apparatus configured to capture a predetermined image, a vision-based recognition apparatus configured to recognize a figure in the predetermined image and determine a destination, a database configured to store map data, and a controller configured to control the image capturing apparatus and the vision-based recognition apparatus. When receiving a user input for requesting recognition of a rough map, the controller recognizes a region of the rough map from the image captured by the image capturing apparatus and captures a rough map image, controls the vision-based recognition apparatus to recognize the destination and a nearby place of the destination from the rough map image, searches for candidates of the destination from the database, searches for candidates of the nearby place from the database, and when the number of the candidates of the destination is plural, calculates distances between the candidates of the destination and the candidates of the nearby place, and selects a final candidate based on the calculated distances, and sets the final candidate as the navigation destination.

[0009] In another aspect of the present disclosure, a method of setting a navigation destination of an apparatus for setting a navigation destination, the apparatus including an image capturing apparatus and a controller configured to control the image capturing apparatus and a vision-based recognition apparatus, the method includes checking, by the controller, whether a user input for requesting recognition of a rough map is received, when the user input is received, activating, by the controller, the image capturing apparatus, capturing, by the image capturing apparatus, a predetermined image, recognizing, by the controller, a region of the rough map from the captured image and capturing a rough map image, recognizing, by the vision-based recognition apparatus, a destination and a nearby place of the destination from the rough map image, searching, by the controller, for candidates corresponding to the destination, checking, by the controller, whether the number of the candidates of the destination is plural, when the number of the candidates of the destination is plural, searching, by the controller, for candidates of the nearby place, calculating, by the controller, distances between the candidates of the destination and the candidates of the nearby place, selecting, by the controller, a final candidate based on the calculated distances, and setting, by the controller, the final candidate as the navigation destination.

[0010] In another aspect of the present disclosure, a computer-readable recording medium having recorded thereon a program for executing a method of setting a navigation destination of an apparatus for setting a navigation destination performs the program provided by the method of setting a navigation destination of the apparatus for setting a navigation destination.

[0011] In another aspect of the present disclosure, a vehicle includes an input device configured to receive a user input for requesting identification of a rough map, and a navigation destination setting device configured to set a destination identified from the rough map image as a navigation destination according to the user input. When the user input is received, the navigation destination setting device identifies a region of the rough map from the captured image and captures a rough map image, identifies the destination and a nearby place of the destination from the rough map image, searches for candidates of the destination from map data, searches for candidates of the nearby place from the map data, and calculates distances between the candidates of the destination and the candidates of the nearby place when the number of the candidates of the destination is plural, selects a final candidate based on the calculated distances, and sets the final candidate as the navigation destination. BRIEF DESCRIPTION OF DRAWINGS

[0012] BRIEF DESCRIPTION OF DRAWINGS

[0013] Figure 1 is a diagram for illustrating a vehicle including a navigation destination setting device according to one embodiment of the present disclosure;

[0014] Figure 2 is a block diagram for illustrating a configuration of a navigation destination setting device according to one embodiment of the present disclosure;

[0015] Figure 3 is a diagram for illustrating Figure 2 is a block diagram for illustrating a configuration of a vision-based recognition device;

[0016] Figure 4 is a diagram for illustrating a step of extracting a region containing location information from a rough map image;

[0017] Figure 5 is a diagram for illustrating a step of identifying a destination and a nearby place thereof from a region containing location information of a rough map image; and

[0018] Figures 6 to 8 is a flowchart for illustrating a method of setting a navigation destination according to one embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] The exemplary embodiments of the present disclosure are described in detail to make those skilled in the art easily implement the present disclosure with reference to the accompanying drawings. However, the present disclosure can be implemented in various different forms and is not limited to the embodiments. To clearly describe the present disclosure, parts irrelevant to the description are omitted in the accompanying drawings, and the same reference numerals in the specification denote the same elements.

[0020] Throughout the specification, unless explicitly defined otherwise, the terms "comprise", "comprising", and "including" will be understood to imply the inclusion of a stated step or object and the exclusion of any additional optional steps or objects that are not specifically recited. In addition, the terms "unit", "module", "device", and the like disclosed in the specification refer to elements for processing at least one function or operation, which can be implemented by hardware, software, or a combination thereof.

[0021] Hereinafter, a navigation destination setting apparatus according to an embodiment of the disclosure will be described with reference to the accompanying drawings. Figures 1 to 8 The detailed description is applicable to an apparatus and method of setting a destination of a navigation apparatus according to an embodiment of the disclosure.

[0022] Figure 1 A diagram for illustrating a vehicle including a navigation destination setting apparatus according to an embodiment of the disclosure is shown.

[0023] As shown, the vehicle 10 can include an input apparatus 100 for receiving a user input for requesting recognition of a rough map, and a navigation destination setting apparatus 200 for setting a destination recognized from a rough map image as a navigation destination according to the user input. Figure 1

[0024] Here, the input apparatus 100 can include a manipulation system for receiving a user command for requesting recognition of a rough map or a microphone for receiving a user's rough map recognition voice command, but the disclosure is not limited thereto.

[0025] When the user input is received, the navigation destination setting apparatus 200 can recognize a region of a rough map from an image captured to capture a rough map image, can recognize a destination and a nearby place thereof from the rough map image, can search for a candidate of the destination from map data, when there are a plurality of destination candidates, can calculate a distance between the candidate of the destination and a candidate of a nearby place of the destination by searching for the candidate of the nearby place of the destination, and can set a final candidate as a navigation destination by selecting the final candidate based on the calculated distance.

[0026] Here, when capturing the rough map image, when the navigation destination setting apparatus 200 receives a user input for requesting recognition of a rough map, the navigation destination setting apparatus 200 can activate a camera, can provide a guide frame for focusing on a rough map image from an image captured by the camera, and when a region of a rough map of the captured image is located within the guide frame, can capture the rough map image by recognizing the region of the rough map located within the guide frame.

[0027] For example, the camera can be an indoor camera mounted inside a vehicle, but the disclosure is not limited thereto. ​

[0028] Then, when the destination and the vicinity of the destination are identified, the navigation destination setting apparatus 200 can extract a region including location information by identifying text and graphics from the rough map image, can identify a marker location and text around the marker location in the region including the location information, and can identify the destination and the vicinity of the destination based on the marker location and the text around the marker location.

[0029] For example, when the destination is identified, the navigation destination setting apparatus 200 can identify the destination by comparing the marker locations based on at least one of shapes, sizes, or colors of the marker locations.

[0030] Here, the navigation destination setting apparatus 200 can identify text corresponding to a marker location that is most different among the marker locations as a comparison result of the marker locations.

[0031] In another example, when the destination is identified, the navigation destination setting apparatus 200 can also identify the destination by comparing the vicinity texts based on at least one of sizes or fonts of the texts around the marker locations.

[0032] Here, the navigation destination setting apparatus 200 can also identify a vicinity text that is most different among the vicinity texts as a comparison result of the vicinity texts.

[0033] In another example, when the destination is identified, the navigation destination setting apparatus 200 can compare the marker locations based on shapes, sizes, and / or colors of the marker locations, can compare the vicinity texts of the marker locations based on sizes and / or fonts of the vicinity texts to assign points to respective marker locations, and can identify the destination based on the assigned points.

[0034] Here, in assigning the points, the navigation destination setting apparatus 200 can assign higher points to more distinguishable marker locations among the marker locations, and can assign lower points to less distinguishable marker locations among the marker locations.

[0035] The navigation destination setting apparatus 200 can identify text corresponding to a marker location to which the highest point is assigned or a vicinity text to which the highest point is assigned as the destination.

[0036] Then, in calculating the distance, the navigation destination setting apparatus 200 can check whether the number of found destination candidates is plural, when the number of found destination candidates is plural, can search for a candidate corresponding to the vicinity location from the map data, and can calculate the distance between the destination candidate and the vicinity location candidate.

[0037] Here, the navigation destination setting apparatus 200 can set the candidate of the destination as the navigation destination when the number of found destination candidates is one.

[0038] In selecting the final candidate, the navigation destination setting apparatus 200 can select the candidate of the destination located at the shortest distance from the nearby place based on the calculated distance as the final candidate.

[0039] As such, according to the disclosure, the destination can be recognized from the rough map image captured by the collected image, and the navigation destination can be automatically set based on the recognized destination, thereby providing convenience for the user.

[0040] The disclosure can provide an interface for inputting an image to a navigation apparatus based on a computer vision technique, thereby improving user convenience and accuracy and reliability of searching for a destination.

[0041] According to the disclosure, an indoor camera can be used as an interface with a vehicle, and thus installation costs can be reduced without additional costs.

[0042] Figure 2 A block diagram for explaining a configuration of a navigation destination setting apparatus according to one embodiment of the disclosure.

[0043] As Figure 2 shown, the navigation destination setting apparatus 200 can include an image collection apparatus 210 for collecting a predetermined image, a vision-based recognition apparatus 220 for recognizing a landmark place and its nearby text from a rough map image to determine a destination, a database 230 for storing map data, and a controller 240 for controlling the image collection apparatus 210 and the vision-based recognition apparatus 220.

[0044] Here, the image collection apparatus 210 can be an indoor camera installed inside a vehicle, but the disclosure is not limited thereto.

[0045] In this case, the image collection apparatus 210 can be activated to collect an image according to a control signal of the controller 240.

[0046] The vision-based recognition apparatus 220 can recognize text and graphics from a rough map image to extract a region including location information, can recognize a landmark place and nearby text of the landmark place in the region including location information, and can determine a destination and its nearby place based on the landmark place and the nearby text of the landmark place.

[0047] The vision-based recognition device 220 can identify a graphic, text, etc. from an image obtained by completely scanning an invitation card, etc. and a rough map image, as appropriate, and can calculate a horizontal range and a vertical range of a region for grouping all of the identified graphics, and can also divide the entire scanned image into a region of a rough map including location information and other regions based on the calculated horizontal range and vertical range.

[0048] Here, when identifying a graphic from a rough map image, the vision-based recognition device 220 can identify a graphic indicating road information, destination information, and nearby building information from the rough map image.

[0049] In extracting a region including location information from a rough map image, in identifying a graphic, the vision-based recognition device 220 can calculate a horizontal range and a vertical range of a region for grouping all of the identified graphics, and can extract a region including location information from the rough map image based on the calculated horizontal range and vertical range.

[0050] In identifying a marker location and nearby text of a marker location, the vision-based recognition device 220 can identify a marker location by analyzing a graphic in a region including location information based on a pre-learned graphic object, and can identify nearby text located near the identified marker location.

[0051] Here, in identifying nearby text, the vision-based recognition device 220 can identify nearby text located on the right and left sides and on the upper and lower sides of a marker location.

[0052] In determining a destination, the vision-based recognition device 220 can determine a destination by comparing marker locations based on at least one of a shape, a size, or a color of the marker locations.

[0053] Here, in determining a destination, the vision-based recognition device 220 can determine text corresponding to a marker location most different from the marker locations as a destination as a comparison result of the marker locations.

[0054] For example, in determining a destination, the vision-based recognition device 220 can check whether there is a marker location having a different shape by comparing shapes of a plurality of marker locations, and when there is a marker location having a different shape, can determine text corresponding to the marker location having a different shape as a destination.

[0055] Here, when checking whether there is a marker place having a different shape, the vision-based recognition device 220 can check whether there is a marker place having a different size or color, when there is no marker place having a different shape, and can determine the destination based on a marker place having neither a different size nor a different color.

[0056] In another example, in determining the destination, the vision-based recognition device 220 can check whether there is a marker place having a different size by comparing sizes of a plurality of marker places, and when there is a marker place having a different size, can determine text corresponding to the marker place having a different size as the destination.

[0057] Here, when checking whether there is a marker place having a different size, the vision-based recognition device 220 can check whether there is a marker place having a different shape or color, when there is no marker place having a different size, and can determine the destination based on a marker place having neither a different shape nor a different color.

[0058] In another example, in determining the destination, the vision-based recognition device 220 can check whether there is a marker place having a different color by comparing colors of a plurality of marker places, and when there is a marker place having a different color, can determine text corresponding to the marker place having a different color as the destination.

[0059] Here, when checking whether there is a marker place having a different color, the vision-based recognition device 220 can check whether there is a marker place having a different shape or size, when there is no marker place having a different color, and can determine the destination based on a marker place having neither a different shape nor a different size.

[0060] Depending on the situation, in determining the destination, the vision-based recognition device 220 can also determine the destination by comparing nearby texts based on at least one of a size or a font of the nearby texts of the marker place.

[0061] Here, in determining the destination, the vision-based recognition device 220 can determine, as a comparison result of the nearby texts, a most different nearby text among the nearby texts as the destination.

[0062] For example, in determining the destination, the vision-based recognition device 220 can check whether there is a nearby text having a different size by comparing sizes of a plurality of nearby texts, and when there is a nearby text having a different size, can determine the nearby text having a different size as the destination.

[0063] Here, in checking whether there is nearby text having a different font, the vision-based recognition device 220 can check whether there is nearby text having a different size when there is no nearby text having a different size, and can determine the destination based on the nearby text having a different size.

[0064] In another example, in determining the destination, the vision-based recognition device 220 can check whether there is nearby text having a different font by comparing fonts of a plurality of nearby texts, and when there is nearby text having a different font, can determine the nearby text having a different font as the destination.

[0065] Here, in checking whether there is nearby text having a different font, the vision-based recognition device 220 can check whether there is nearby text having a different size when there is no nearby text having a different font, and can determine the destination based on the nearby text having a different size.

[0066] In another example, in determining the destination, the vision-based recognition device 220 can compare the marked locations based on shapes, sizes, and colors of the marked locations, can compare the nearby texts based on sizes and fonts of the nearby texts of the marked locations, can assign points to the respective marked locations, can assign points to the respective nearby texts, and can determine the destination as the assigned points.

[0067] Here, in assigning the points, the vision-based recognition device 220 can assign a higher point to a more distinguishable marked location among the marked locations, and can assign a lower point to a less distinguishable marked location among the marked locations.

[0068] In determining the destination, the vision-based recognition device 220 can determine text corresponding to a marked location to which the highest point is assigned or nearby text to which the highest point is assigned as the destination.

[0069] When receiving a user input for requesting to recognize a rough map, the controller 240 can recognize a region of the rough map from an image captured by the image capturing device 210 to capture a rough map image, the vision-based recognition device 220 can recognize a destination and a nearby location thereof from the rough map image, can search for candidates of the destination from the database 230, when there are a plurality of destination candidates, can calculate distances between the destination candidates and candidates of nearby locations thereof by searching for the candidates of the nearby locations of the destination, and can set a final candidate as a navigation destination by selecting the final candidate based on the calculated distances.

[0070] Here, in receiving a user input, the controller 240 can receive a user input including a user command for requesting recognition of a rough map input through a manipulation system including, but not limited to, a touch screen, a touch pad, a keyboard, a key knob, or a joystick or a rough map recognition voice command input through a microphone.

[0071] In capturing a rough map image, when a user input for requesting recognition of a rough map is received, the controller 240 can control the image capturing device 210 to activate the image capturing device 210, when the image capturing device 210 captures an image, a guide frame can be provided for focusing on a rough map image, when a region of a rough map of the captured image is located in the guide frame, the region of the rough map located in the guide frame can be recognized to capture the region of the rough map, and the captured rough map image can be provided to the vision-based recognition device 220.

[0072] Then, in searching for candidates of a destination, the controller 240 can generate a list including a destination and a place near the destination based on the destination and the place near the destination recognized by the vision-based recognition device 220, and can search for candidates corresponding to the destination from the database 230.

[0073] Then, in calculating a distance, the controller 240 can check whether the number of found candidates of a destination is plural, when the number of found candidates of a destination is plural, can search for candidates corresponding to a place near the destination from the database 230, and can calculate a distance between the candidate of the destination and the candidate of the place near the destination.

[0074] In checking whether the number of found candidates of a destination is plural, the controller 240 can set the found candidate of a destination as a navigation destination when the number of found candidates of a destination is one.

[0075] In selecting a final candidate, the controller 240 can select a candidate of a destination located at a shortest distance from a candidate of a place near as a final candidate based on the calculated distance.

[0076] Figure 3 For illustration Figure 2 a block diagram of a configuration of a vision-based recognition device.

[0077] As Figure 3 illustrated, the vision-based recognition device 220 can include a text recognition device 222 for recognizing text from a rough map image, a graphic recognition device 224 for recognizing graphics from a rough map image, and a destination determiner 226 for recognizing a marked place and a text near the marked place based on the recognized text and graphics from a rough map image and determining a destination.

[0078] Here, the text recognition device 222 can recognize nearby text located right and left and above and below the marker location.

[0079] The graphic recognition device 224 can recognize graphics indicating road information, destination information, and nearby building information from the rough map image.

[0080] Then, the destination determiner 226 can determine a destination by comparing the marker locations based on at least one of shapes, sizes, or colors of the marker locations.

[0081] As appropriate, the destination determiner 226 can also determine a destination by comparing the nearby text based on at least one of sizes or fonts of the nearby text of the marker locations.

[0082] In another example, the destination determiner 226 can compare the marker locations based on shapes, sizes, and colors of the marker locations, can compare the nearby text of the marker locations based on sizes and fonts of the nearby text to assign points to respective marker locations, and can determine a destination based on the assigned points.

[0083] Figure 4 is a diagram for explaining a step of extracting a region containing location information from a rough map image. Figure 5 is a diagram for explaining a step of recognizing a destination and nearby locations thereof from a region containing location information of a rough map image.

[0084] As Figure 4 and Figure 5 indicated, the vision-based recognition device according to the present disclosure can recognize text and graphics from a rough map image 510, and can separate a text region 520 and a region including location information 530 from the rough map image 510 based on the recognized text and graphics, and can extract the region including location information 530.

[0085] Here, as Figure 4 indicated, the vision-based recognition device can recognize graphics from the rough map image 510, can calculate horizontal and vertical ranges of a region for grouping all of the recognized graphics, and can extract a region including location information from the rough map image based on the calculated horizontal and vertical ranges.

[0086] For example, as Figure 5 indicated, the rough map image 510 can include a text region 520, which is a region indicating information about traffic or weather, and a region including location information 530, which is a region for providing visual information of a destination using graphics and text.

[0087] Then, the vision-based recognition device can recognize the marker point 532 and the nearby text 534 of the marker point 532 in the region including the location information 530, and can determine the destination and the nearby point thereof based on the recognized marker point 532 and the recognized nearby text 534 of the marker point 532.

[0088] For example, the vision-based recognition device can recognize a dot, a frame, and a shape of a building as the marker point 532 in the region including the location information 530.

[0089] That is, the vision-based recognition device can pre-learn road information using a straight line, a rectangle, etc., and can recognize a graphic object other than text and the pre-learned road information in the region including the location information 530 as the marker point 532.

[0090] Then, the vision-based recognition device can recognize text located at the right and left sides and the upper and lower sides of the recognized marker point 532, and can determine the destination.

[0091] Figures 6 to 8 A flowchart for explaining a method of setting a navigation destination according to one embodiment of the disclosure.

[0092] As Figure 6 indicated, according to the disclosure, it can be checked whether a user input for requesting recognition of a rough map is received (S100).

[0093] According to the disclosure, when the user input is received, a camera can be activated (S200).

[0094] Then, according to the disclosure, a predetermined image can be captured from the camera (S300).

[0095] Then, according to the disclosure, a region of a rough map can be recognized from the captured image, and a rough map image can be captured (S400).

[0096] Here, according to the disclosure, as Figure 7 indicated, when the rough map image is captured, a guide frame can be provided for focusing on the rough map image from the captured image (S410), it can be checked whether the region of the rough map of the captured image is located in the guide frame (S420), and when the region of the rough map is located in the guide frame, the region of the rough map located in the guide frame can be recognized and the rough map image can be captured (S430).

[0097] According to the disclosure, a destination and a nearby point thereof can be recognized from the rough map image (S500).

[0098] Here, according to the disclosure, asFigure 8 As illustrated, in identifying the destination and the nearby place, text and graphics can be recognized from the rough map image (S510), a text region and a region including location information can be separated from the rough map image, and the region including location information can be extracted (S520), a landmark place and nearby text thereof can be recognized in the region including location information (S530), and the destination and the nearby place thereof can be determined based on the recognized landmark place and the recognized nearby text thereof (S540).

[0099] For example, according to the disclosure, in determining the destination, the destination can be determined by comparing the landmark places based on at least one of shapes, sizes, or colors of the landmark places.

[0100] In another example, according to the disclosure, in determining the destination, the destination can be determined by comparing the nearby text based on at least one of sizes and fonts of the nearby text of the landmark places.

[0101] In another example, according to the disclosure, in determining the destination, the landmark places can be compared based on shapes, sizes, and colors of the landmark places, points can be assigned to the respective landmark places, the nearby text of the landmark places can be compared based on sizes and fonts of the nearby text, points can be assigned to the respective nearby text, and the destination can be determined based on the assigned points.

[0102] Then, according to the disclosure, a candidate corresponding to the destination can be searched (S600).

[0103] Then, according to the disclosure, it can be checked whether the number of found destination candidates is plural (S700).

[0104] According to the disclosure, when the number of found destination candidates is plural, a candidate of a nearby place can be searched (S800).

[0105] Here, according to the disclosure, when the number of found destination candidates is one, the found destination candidate can be set as a navigation destination (S1100).

[0106] Then, according to the disclosure, a distance between the candidate of the destination and the candidate of the nearby place can be calculated (S900).

[0107] Then, according to the disclosure, a final candidate can be selected based on the calculated distance (S1000).

[0108] Here, according to the disclosure, the candidate of the destination located at a shortest distance from the candidate of the nearby place can be selected as the final candidate based on the calculated distance.

[0109] According to the present disclosure, a final candidate can be set as a navigation destination (S1100).

[0110] As such, according to the present disclosure, a destination can be recognized from a rough map image captured by an acquired image, and a navigation destination can be automatically set based on the recognized destination, thereby providing a user with convenience.

[0111] The present disclosure can provide an interface for inputting an image to a navigation device using a computer vision technique, thereby improving user convenience and accuracy and reliability of searching for a destination.

[0112] According to the present disclosure, an indoor camera can be used as an interface with a vehicle, and thus installation costs can be reduced without additional costs.

[0113] According to the present disclosure, a computer-readable recording medium having recorded thereon a program for executing a method of setting a navigation destination of an apparatus for setting a navigation destination according to one embodiment of the present disclosure can perform the steps provided by the method of setting a navigation destination of an apparatus for setting a navigation destination according to one embodiment of the present disclosure when a controller and / or components thereof and a vision-based recognition apparatus execute the recorded program. The controller and / or components thereof and the vision-based recognition apparatus and / or components thereof can each or together be implemented as a computer, a processor, or a microprocessor. When the controller and / or components thereof and the vision-based recognition apparatus read and execute the recorded program, the controller and / or components thereof and the vision-based recognition apparatus can be configured to perform the method of setting a navigation destination of an apparatus for setting a navigation destination.

[0114] The aforementioned present disclosure can also be implemented as computer-readable code stored on a computer-readable recording medium. The computer-readable recording medium is any data storage device that can store data which can be subsequently read by a computer. Examples of the computer-readable recording medium include a hard disk drive (HDD), a solid state drive (SSD), a silicon disk drive (SDD), read-only memory (ROM), random access memory (RAM), CD-ROMs, magnetic tapes, floppy disks, optical data storage devices, and the like.

[0115] The apparatus and method of setting a navigation destination configured as described above in relation to at least one embodiment of the present disclosure can recognize a destination from a rough map image captured by an acquired image, and can automatically set a navigation destination based on the recognized destination, thereby providing a user with convenience.

[0116] The present disclosure can provide an interface for inputting an image to a navigation device using a computer vision technique, thereby improving user convenience and accuracy and reliability of searching for a destination.

[0117] According to the present disclosure, the indoor camera can be used as an interface with the vehicle, so the installation cost can be reduced without additional cost.

[0118] Those skilled in the art will recognize that the effects which can be achieved by the present disclosure are not limited to what has been particularly described hereinabove and some of the other advantages of the present disclosure will become apparent to those skilled in the art from the detailed description and drawings.

[0119] It will be apparent to those skilled in the art that various modifications and variations can be made in the present disclosure without departing from the spirit or scope of the embodiments. Thus, it is intended that the present disclosure cover the modifications and variations of the embodiments provided for by the scope of the appended claims and their equivalents.

Claims

1. A device for setting a navigation destination, comprising: an image capturing device configured to capture a predetermined image; a vision-based recognition device configured to recognize a figure in the predetermined image and determine a destination; a database configured to store map data; and a controller configured to control the image capturing device and the vision-based recognition device, wherein, when a user input for requesting recognition of a rough map is received, the controller recognizes a region of the rough map from an image captured by the image capturing device and captures a rough map image, controls the vision-based recognition device to recognize the destination and a nearby place of the destination from the rough map image, searches for candidates of the destination from the database, searches for candidates of the nearby place from the database, and, when the number of the candidates of the destination is plural, calculates distances between the candidates of the destination and the candidates of the nearby place, and selects a final candidate based on the calculated distances, and sets the final candidate as the navigation destination; wherein, in calculating the distances, the controller checks whether the number of found candidates of the destination is plural, when the number of found candidates of the destination is plural, searches for candidates corresponding to the nearby place of the destination from the database, and calculates distances between the candidates of the destination and the candidates of the nearby place; and wherein, in checking whether the number of found candidates of the destination is plural, the controller sets a found candidate of the destination as a navigation destination when the number of found candidates of the destination is one. The image capturing device is an indoor camera installed in a vehicle.

2. The apparatus of claim 1, wherein, The vision-based recognition device recognizes text and figures from the rough map image, extracts a region including location information, recognizes a marker place in the region including location information and nearby text of the marker place, and determines the destination and the nearby place of the destination based on the marker place and the nearby text of the marker place.

3. The apparatus of claim 1, wherein, In extracting the region including location information from the rough map image, in recognizing the figures, the vision-based recognition device calculates a horizontal range and a vertical range of a region for grouping all recognized figures, and extracts the region including location information from the rough map image based on the calculated horizontal range and vertical range.

4. The apparatus of claim 3, wherein, In recognizing the marker place and the nearby text of the marker place, the vision-based recognition device recognizes the marker place by analyzing figures in the region including location information based on a pre-learned figure object, and recognizes nearby text located near the recognized marker place.

5. The apparatus of claim 3, wherein, ​ 6. The apparatus of claim 3, wherein, In determining the destination, the vision-based recognition device determines the destination by comparing the landmark based on at least one of a shape, a size, or a color of the landmark.

7. The apparatus of claim 3, wherein, In determining the destination, the vision-based recognition device determines the destination by comparing the nearby text of the landmark based on at least one of a size or a font of the nearby text.

8. The apparatus of claim 1, wherein, The vision-based recognition device comprises: a text recognition device configured to recognize text from the rough map image; a pattern recognition device configured to recognize patterns from the rough map image; and a destination determiner configured to recognize a landmark and nearby text of the landmark based on the recognized text and patterns from the rough map image and determine the destination.

9. The apparatus of claim 1, wherein, In capturing the rough map image, when a user input for recognizing the rough map is received, the controller controls the image capturing device to activate the image capturing device, provide a guide frame focused on the rough map image of the captured image when the image capturing device captures the image, recognize an area of the rough map located in the guide frame, and capture the rough map image when the area of the rough map of the captured image is located in the guide frame, and provide the captured rough map image to the vision-based recognition device.

10. The apparatus of claim 1, wherein, In selecting the final candidate, the controller selects a candidate of the destination located at a shortest distance from the nearby landmark candidates as the final candidate based on the calculated distances.

11. A method of setting a navigation destination of an apparatus for setting a navigation destination, the apparatus comprising an image capturing device and a controller configured to control the image capturing device and a vision-based recognition device, the method comprising: checking, by the controller, whether a user input for requesting recognition of a rough map is received; activating, by the controller, the image capturing device when the user input is received; capturing, by the image capturing device, a predetermined image; recognizing, by the controller, an area of the rough map from the captured image and capturing a rough map image; recognizing, by the vision-based recognition device, a destination and nearby landmarks of the destination from the rough map image; searching, by the controller, for candidates corresponding to the destination; checking, by the controller, whether a number of the candidates of the destination is plural; searching, by the controller, for candidates of the nearby landmarks when the number of the candidates of the destination is plural; calculating, by the controller, distances between the candidates of the destination and the candidates of the nearby landmarks; selecting, by the controller, a final candidate based on the calculated distances; and setting, by the controller, the final candidate as the navigation destination. ​ The checking whether the number of the candidates of the destination is plural includes, when the number of the candidates of the destination found is one, setting the candidate of the destination found as the navigation destination.

12. The method of claim 11, wherein, The capturing the rough map image includes: providing a frame for focusing on the rough map image from the captured image; checking whether the area of the rough map of the captured image is located in the frame; when the area of the rough map is located in the frame, recognizing the area of the rough map located in the frame and capturing the rough map image; and providing the captured rough map image to the vision-based recognition device.

13. The method of claim 11, wherein, The recognizing the destination and the nearby place of the destination includes: recognizing text and graphics from the rough map image; separating a text area and an area including location information from the rough map image and extracting the area including location information; recognizing a marked place in the area including location information and nearby text of the marked place; and determining the destination and the nearby place of the destination based on the marked place and the nearby text of the marked place.

14. The method of claim 13, wherein, The determining the destination includes determining the destination by comparing the marked place based on at least one of a shape, a size, or a color of the marked place.

15. The method of claim 13, wherein, The determining the destination includes determining the destination by comparing nearby text based on at least one of a size or a font of the nearby text of the marked place.

16. The method of claim 11, wherein, The selecting the final candidate includes: selecting, as the final candidate, a candidate of the destination located at a shortest distance from the nearby place based on the calculated distances.

17. A vehicle comprising: an input device configured to receive a user input for requesting recognition of a rough map; and a navigation destination setting device configured to set a destination recognized from a rough map image as a navigation destination according to the user input, wherein, when the user input is received, the navigation destination setting device recognizes an area of the rough map from a captured image and captures a rough map image, recognizes the destination and a nearby place of the destination from the rough map image, searches for candidates of the destination from map data, searches for candidates of the nearby place from the map data, and when the number of the candidates of the destination is plural, calculates distances between the candidates of the destination and the candidates of the nearby place, selects a final candidate based on the calculated distances, and sets the final candidate as the navigation destination, wherein, in the checking whether the number of the candidates of the destination is plural, if the number of the candidates of the destination found is one, the navigation destination setting device sets the candidate of the destination found as the navigation destination.

18. The vehicle of claim 17, wherein, The input device comprises a manipulation system configured to receive a user command for requesting the identification of the coarse map or a microphone configured to receive a coarse map identification voice command of the user.

Images