WO2016145789A1 - 一种提示方法、终端及计算机存储介质 - Google Patents
一种提示方法、终端及计算机存储介质 Download PDFInfo
- Publication number
- WO2016145789A1 WO2016145789A1 PCT/CN2015/088368 CN2015088368W WO2016145789A1 WO 2016145789 A1 WO2016145789 A1 WO 2016145789A1 CN 2015088368 W CN2015088368 W CN 2015088368W WO 2016145789 A1 WO2016145789 A1 WO 2016145789A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- obstacle
- image
- terminal
- analyzed
- user
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims abstract description 26
- 238000004590 computer program Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 239000010813 municipal solid waste Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000004397 blinking Effects 0.000 description 1
- 230000037237 body shape Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Definitions
- the present invention relates to the field of terminal applications, and in particular, to a prompting method, a terminal, and a computer storage medium.
- terminals such as smartphones, tablets, and smart watches enter the lives of users, more and more conveniences are brought to users, making users increasingly dependent on terminals.
- an embodiment of the present invention provides a prompting method, a terminal, and a computer storage medium, to indicate that a user avoids an obstacle or prompts other users to avoid the user, prevents accidents, and improves the intelligence of the terminal. Good user experience.
- an embodiment of the present invention provides a prompting method, which is applied to a terminal, including: obtaining at least one image to be analyzed; performing at least one depth of field calculation on the at least one image to be analyzed, and obtaining the at least one image to be analyzed.
- the type of the obstacle and the object information generating, according to the object information, prompt information corresponding to the type of the obstacle, wherein the prompt information is used to indicate that the user avoids the obstacle or prompt other users Avoid the user.
- the at least one depth of field calculation is performed on the at least one image to be analyzed, and the type of the obstacle and the object information in the at least one image to be analyzed are obtained, including: performing depth of field on the at least one image to be analyzed. Calculating, obtaining a distance value between the obstacle in the at least one image to be analyzed and the terminal; determining, after the type of the obstacle is a fixed object based on the plurality of the distance values, contouring the obstacle Identifying, and determining an object size value of the obstacle according to the recognition result and the distance value; determining the distance value and the object size value as object information of the obstacle.
- the generating and outputting the prompt information corresponding to the type of the obstacle according to the object information includes: when the type of the obstacle is a fixed object, generating and outputting according to the object information
- the prompt information including a moving route causes the user to move according to the moving route to avoid the obstacle.
- the generating and outputting the prompt information according to the object information includes: when the type of the obstacle is a moving object, determining a moving direction of the obstacle according to the object information; when the obstacle is When the object moves toward the terminal, and the object information satisfies a preset condition, the prompt information is generated and output to prompt the other user to avoid the user; when the obstacle moves toward the terminal, and When the object information does not satisfy the preset condition, the prompt information is generated and output to instruct the user to avoid the obstacle.
- the image is provided with two image acquisition units, the two image acquisition units are oriented in the same direction, and the relative positions are unchanged; and the obtaining the image to be analyzed includes: controlling the two image collections.
- the unit simultaneously collects its own image acquisition area to obtain two images to be analyzed.
- an embodiment of the present invention provides a terminal, including: an obtaining unit, an image processing unit, and a prompting unit; wherein the obtaining unit is configured to obtain at least one image to be analyzed; the image processing unit is configured to be Performing at least one depth of field calculation on the at least one image to be analyzed, obtaining the type of the obstacle and the object information in the at least one image to be analyzed; The prompting unit is configured to generate and output prompt information corresponding to the type of the obstacle according to the object information, wherein the prompt information is used to instruct the user to avoid the obstacle or prompt other users to avoid the User.
- the image processing unit includes: a depth of field calculation subunit, an image recognition subunit, and a determination subunit; the depth of field calculation subunit is further configured to perform depth of field calculation on the at least one image to be analyzed, and obtain a distance value between the obstacle in the at least one image to be analyzed and the terminal; further configured to determine that the type of the obstacle is a fixed object based on the plurality of the distance values; the image recognition subunit, configured After the depth of field calculation subunit determines that the obstacle is a fixed object based on the distance value, the contour of the obstacle is identified, and the object of the obstacle is determined according to the recognition result and the distance value. a size value; the determining subunit configured to determine the distance value and the object size value as object information of the obstacle.
- the prompting unit is further configured to: when the type of the obstacle is a fixed object, generate and output the prompt information including a moving route according to the object information, so that the user follows the The moving route moves to avoid the obstacle.
- the prompting unit is further configured to: when the type of the obstacle is a moving object, determine a moving direction of the obstacle according to the object information; when the obstacle moves toward the terminal, and When the object information meets the preset condition, the prompt information is generated and outputted to prompt the other user to avoid the user; when the obstacle moves toward the terminal, and the object information does not satisfy the preset In the case of the condition, the prompt information is generated and output to instruct the user to avoid the obstacle.
- the terminal further includes two image acquisition units, the two image acquisition units are oriented in the same direction, and the relative positions are unchanged; the obtaining unit is configured to control the two image acquisition units simultaneously The self-image collection area is collected to obtain two images to be analyzed.
- an embodiment of the present invention provides a computer storage medium.
- the computer storage medium provided by the embodiment of the present invention stores a computer program, where the computer program is configured to execute the prompting method.
- the terminal obtains at least one image to be analyzed, and then performs at least the depth of field calculation on the image to be analyzed, and obtains the type of the obstacle and the object information in the image, and then According to the object information, the prompt information corresponding to the above type is generated and output, and the prompt information is used to instruct the user to avoid the obstacle or prompt other users to avoid the user.
- the terminal can actively prompt the user and instruct the user to avoid the obstacle; in particular, when the user is blind, the terminal can autonomously output prompt information to other users, Prompt them to actively evade the user. In this way, it is possible to prevent accidents and improve the intelligence of the terminal and provide a good user experience.
- FIG. 1 is a schematic flowchart diagram of a prompting method according to an embodiment of the present invention
- FIG. 2 is a schematic structural diagram of a terminal in an embodiment of the present invention.
- FIG. 3 is a schematic structural diagram of an image processing unit according to an embodiment of the present invention.
- FIG. 4 is another schematic structural diagram of a terminal according to an embodiment of the present invention.
- the embodiment of the invention provides a prompting method, which is applied to a terminal, and the terminal can be a smart phone, a tablet computer, a smart watch, a smart bracelet, smart glasses, and the like.
- An image acquisition unit such as a camera, is disposed on the terminal.
- it may also be two image acquisition units, the two image acquisition units are oriented in the same direction, and the distance between the two is constant.
- the method includes:
- S101 Obtain at least one image to be analyzed
- the obstacle reminding function can be manually turned on, and the image collecting unit of the terminal can collect the area located in front of the user, or the terminal can detect whether the user is moving, and if so, automatically start the obstacle.
- the terminal controls the image acquisition unit to collect an image in the collection area, that is, the preset range in front of the user, and the image is the image to be analyzed. Since the two image acquisition units, that is, the dual camera structure, can also be set on the terminal, the terminal controls the two image acquisition units to simultaneously collect the image collection area of the image, and obtain two images to be analyzed.
- the frame rate of the image acquired by the image acquisition unit is usually about 30 frames.
- the processing speed of the central processing unit (CPU) of the terminal is limited, one frame of data can be processed every three frames.
- S102 Perform at least depth of field calculation on at least one image to be analyzed, and obtain type and object information of the obstacle in the at least one image to be analyzed;
- the obstacle can be a fixed object, such as a utility pole, a fire hydrant, a trash can, a newsstand, etc., and can also be a moving object, such as a pedestrian, a vehicle, etc.
- a fixed object such as a utility pole, a fire hydrant, a trash can, a newsstand, etc.
- the obstacle list is added, and the current distance value of the obstacle is recorded.
- the obstacle is marked. To fix the object.
- the distance values measured for three consecutive times may be slightly decremented, but roughly the same. If there is too large or too small value, the data will be discarded and will be retested once. If the distance value appears to increase continuously or rapidly, the obstacle is marked as a moving object. In the above list, the moving object has the highest priority, and the fixed object depends on the distance value from large to small. Sub-arrangement.
- the object information only includes the depth of field of the object, that is, the distance between the object and the terminal, the distance value can represent the distance between the obstacle and the user; and when the obstacle is a fixed object
- the S102 may include: performing depth of field calculation on the at least one image to be analyzed, obtaining a distance value between the obstacle and the terminal in the at least one image to be analyzed; determining the type of the obstacle as the fixed object based on the plurality of distance values, and facing the obstacle The contour of the object is identified, and the object size value of the obstacle is determined according to the recognition result and the distance value; and the distance value and the object size value are determined as the object information of the obstacle.
- the terminal performs depth of field calculation on at least one image to be analyzed, obtains a distance value between the obstacle and the terminal in the at least one image to be analyzed, and determines whether the obstacle is a fixed object or a moving object according to the distance value of the obstacle.
- the terminal also needs to calculate the size of the obstacle, and then the terminal recognizes the contour of the obstacle.
- the width of the image formed by the obstacle is approximately equal to the number of pixels multiplied by the size of the pixel, and then the distance between the obstacle and the object can be The width on the image is analyzed, and the actual width is obtained according to the relationship of similar triangles, that is, the size value of the obstacle is detected. Then, the terminal determines the distance value and the object size value as the object information of the obstacle.
- the distance value of the acquisition unit usually the left image acquisition unit).
- S103 Generate and output prompt information according to the object information, wherein the prompt information is used to instruct the user to avoid the obstacle or prompt other users to avoid the user.
- S103 can exist in the following cases.
- the terminal when the type of the obstacle is a fixed object, the terminal generates and outputs prompt information including a moving route according to the object information, so that the user moves according to the moving route to avoid the obstacle.
- the terminal After determining that the type of the obstacle is a fixed object by S102, the terminal generates a moving route according to the distance value of the obstacle and the size value of the object, and outputs the motion to the user by voice, vibration, etc., and the user follows the moving route. Move, you can avoid obstacles.
- the terminal may further determine whether the object size value of the obstacle is less than or equal to a preset value, and if so, the obstacle is relatively small, which may be a utility pole, An object such as a trash can.
- the moving route may be “moving left/right two steps”; if the object size value of the obstacle is greater than or equal to a preset value, it indicates that the obstacle is relatively large, possibly a newsstand.
- the above-mentioned moving route may be “moving five steps to the left/right and then moving the camera three steps forward”, which is not limited in detail.
- the terminal determines the moving direction of the obstacle according to the object information; when the obstacle moves toward the terminal, and the object information satisfies the preset condition, the prompt information is generated and outputted, The other user is prompted to avoid the user; when the obstacle moves toward the terminal, and the object information does not satisfy the preset condition, the prompt information is generated and outputted to instruct the user to avoid the obstacle.
- the terminal when the obstacle is a moving object, the terminal first determines the moving direction of the obstacle according to the object information, that is, the distance value, and if the obstacle moves away from the terminal, at this time, the user may not be prompted. If the obstacle is moving toward the terminal, the terminal needs to determine whether the distance of the obstacle from the terminal is relatively long, that is, whether the object information is greater than or equal to the preset value, and if so, the object information satisfies the pre- Setting the condition, on the contrary, indicates that the object information does not satisfy the preset condition.
- the object information that is, the distance value
- the terminal when the object information satisfies the preset condition, the terminal generates and outputs prompt information, such as prompting light blinking, outputting a prompt sound, etc., prompting other users to avoid the current user of the terminal; when the object information does not satisfy the preset condition, that is, Said that the obstacle is very close to the user, then, at this time, the terminal can generally generate and output a prompt message as in the first case to instruct the user to avoid the obstacle.
- prompt information such as prompting light blinking, outputting a prompt sound, etc.
- the terminal obtains at least one image to be analyzed, and then performs at least depth of field calculation on the image to be analyzed, obtains the type of the obstacle in the image, and the object information, and then generates and outputs the corresponding type according to the object information.
- the prompt information is configured to instruct the user to avoid the obstacle or prompt other users to avoid the user.
- the terminal can actively prompt the user and instruct the user to avoid the obstacle; in particular, when the user is blind, the terminal can autonomously output prompt information to other users, Prompt them to actively evade the user. In this way, it is possible to prevent accidents and improve the intelligence of the terminal and provide a good user experience.
- an embodiment of the present invention provides a terminal that is consistent with the terminal described in one or more of the foregoing embodiments.
- the terminal includes: an obtaining unit 21, an image processing unit 22, and a prompting unit 23; wherein the obtaining unit 21 is configured to obtain at least one image to be analyzed; the image processing unit 22 is configured to analyze at least one to be analyzed At least the depth of field calculation is performed on the image to obtain at least one The type of the obstacle in the image to be analyzed and the object information; the prompting unit 23 is configured to generate and output prompt information corresponding to the type of the obstacle according to the object information, wherein the prompt information is used to indicate that the user avoids the obstacle or prompts Other users avoid the user.
- the image processing unit 22 includes: a depth of field calculation sub-unit 221, an image recognition sub-unit 222, and a determination sub-unit 223; the depth-of-depth calculation sub-unit 221 is further configured to view at least one image to be analyzed.
- the prompting unit 23 is further configured to generate and output prompt information including a moving route according to the object information when the type of the obstacle is a fixed object, so that the user moves according to the moving route to avoid the obstacle.
- the prompting unit 23 is further configured to: when the type of the obstacle is a moving object, determine the moving direction of the obstacle according to the object information; when the obstacle moves toward the terminal, and the object information satisfies the preset condition, generate And prompting information to prompt other users to avoid the user; when the obstacle moves toward the terminal, and the object information does not satisfy the preset condition, the prompt information is generated and outputted to instruct the user to avoid the obstacle.
- the terminal further includes two image acquisition units 41, the two image acquisition units 41 are oriented in the same direction, and the relative positions are unchanged; the obtaining unit 21 is configured to control two image acquisitions.
- the unit 41 simultaneously collects its own image acquisition area to obtain two images to be analyzed.
- each unit in the terminal can be implemented by a central processing unit (CPU) and a microprocessor (Micro) located in the terminal.
- CPU central processing unit
- Micro microprocessor
- MPU Processor Unit
- DSP Digital Signal Processor
- FPGA Field Programmable Gate Array
- the apparatus for tracking the service signaling may also be stored in a computer readable storage medium if it is implemented in the form of a software function module and sold or used as a separate product.
- the technical solution of the embodiments of the present invention may be embodied in the form of a software product in essence or in the form of a software product stored in a storage medium, including a plurality of instructions.
- a computer device (which may be a personal computer, server, or network device, etc.) is caused to perform all or part of the methods described in various embodiments of the present invention.
- the foregoing storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read only memory (ROM), a magnetic disk, or an optical disk.
- program codes such as a USB flash drive, a mobile hard disk, a read only memory (ROM), a magnetic disk, or an optical disk.
- the embodiment of the present invention further provides a computer storage medium, wherein a computer program is stored, and the computer program is used to execute the prompting method of the embodiment of the present invention.
- embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention can take the form of a hardware embodiment, a software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) including computer usable program code.
- the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
- the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
- These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
- the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
本发明实施例公开了一种提示方法，应用于一终端，包括：获得至少一个待分析图像；对所述至少一个待分析图像至少进行景深计算，获得所述至少一个待分析图像中的障碍物的物体信息；根据所述物体信息，生成并输出提示信息，其中，所述提示信息用于指示用户避开所述障碍物，或者提示其他用户避开所述用户。本发明实施例同时还公开了一种终端及计算机存储介质。
Description
本发明涉及终端应用领域，尤其涉及一种提示方法、终端及计算机存储介质。
随着智能手机、平板电脑、智能手表等终端进入用户的生活，为用户带来越来越多的便利，使得用户越来越依赖于终端。
目前，在用户行走或者过马路的过程中，可能因为在接打电话，或者收发短信、邮件等，忽略了周围环境中潜在的危险，如飞驰的汽车、迎面而来的行人、消防栓、电线杆、书报亭等，这些障碍物可能会引起事故的发生，对用户的人身安全造成威胁。但是，现有技术中并不存在一种合理方法来解决上述问题。
发明内容
为解决上述技术问题，本发明实施例提供了一种提示方法、终端及计算机存储介质，以指示用户避开障碍物或者提示其他用户避开该用户，防止意外发生，提升终端的智能程度，提供良好的用户体验。
为达到上述目的，本发明的技术方案是这样实现的：
第一方面，本发明实施例提供一种提示方法，应用于一终端，包括：获得至少一个待分析图像；对所述至少一个待分析图像至少进行景深计算，获得所述至少一个待分析图像中的障碍物的类型以及物体信息；根据所述物体信息，生成并输出所述障碍物的类型对应的提示信息，其中，所述提示信息用于指示用户避开所述障碍物，或者提示其他用户避开所述用户。
在上述方案中，所述对所述至少一个待分析图像至少进行景深计算，获得所述至少一个待分析图像中的障碍物的类型以及物体信息，包括：对所述至少一个待分析图像进行景深计算，获得所述至少一个待分析图像中的障碍物与所述终端之间的距离值；基于多个所述距离值确定所述障碍物的类型为固定物体后，对所述障碍物的轮廓进行识别，并根据识别结果以及所述距离值，确定所述障碍物的物体尺寸值；将所述距离值与所述物体尺寸值确定为所述障碍物的物体信息。
在上述方案中，所述根据所述物体信息，生成并输出所述障碍物的类型对应的提示信息，包括：当所述障碍物的类型为固定物体时，根据所述物体信息，生成并输出包含一移动路线的所述提示信息，使得所述用户按照所述移动路线移动，以避开所述障碍物。
在上述方案中，所述根据所述物体信息，生成并输出提示信息，包括：当所述障碍物的类型为移动物体时，根据物体信息，确定所述障碍物的移动方向；当所述障碍物朝向所述终端移动，且所述物体信息满足预设条件时，生成并输出所述提示信息，以提示所述其他用户避开所述用户；当所述障碍物朝向所述终端移动，且所述物体信息不满足预设条件时，生成并输出所述提示信息，以指示所述用户避开所述障碍物。
在上述方案中，所述终端上设置有两个图像采集单元，所述两个图像采集单元朝向同一方向，且相对位置不变；所述获得待分析图像，包括：控制所述两个图像采集单元同时对自身图像采集区域进行采集，获得两张所述待分析图像。
第二方面，本发明实施例提供一种终端，包括：获得单元、图像处理单元以及提示单元；其中，所述获得单元，配置为获得至少一个待分析图像；所述图像处理单元，配置为对所述至少一个待分析图像至少进行景深计算，获得所述至少一个待分析图像中的障碍物的类型以及物体信息；所
述提示单元，配置为根据所述物体信息，生成并输出所述障碍物的类型对应的提示信息，其中，所述提示信息用于指示用户避开所述障碍物，或者提示其他用户避开所述用户。
在上述方案中，所述图像处理单元，包括：景深计算子单元、图像识别子单元以及确定子单元；所述景深计算子单元，还配置为对所述至少一个待分析图像进行景深计算，获得所述至少一个待分析图像中的障碍物与所述终端之间的距离值；还配置为基于多个所述距离值确定所述障碍物的类型为固定物体；所述图像识别子单元，配置为在所述景深计算子单元基于所述距离值确定所述障碍物为固定物体后，对所述障碍物的轮廓进行识别，并根据识别结果以及所述距离值，确定所述障碍物的物体尺寸值；所述确定子单元，配置为将所述距离值与所述物体尺寸值确定为所述障碍物的物体信息。
在上述方案中，所述提示单元，还配置为当所述障碍物的类型为固定物体时，根据所述物体信息，生成并输出包含一移动路线的所述提示信息，使得所述用户按照所述移动路线移动，以避开所述障碍物。
在上述方案中，所述提示单元，还配置为当所述障碍物的类型为移动物体时，根据物体信息，确定所述障碍物的移动方向；当所述障碍物朝向所述终端移动，且所述物体信息满足预设条件时，生成并输出所述提示信息，以提示所述其他用户避开所述用户；当所述障碍物朝向所述终端移动，且所述物体信息不满足预设条件时，生成并输出所述提示信息，以指示所述用户避开所述障碍物。
在上述方案中，所述终端，还包括两个图像采集单元，所述两个图像采集单元朝向同一方向，且相对位置不变；所述获得单元，配置为控制所述两个图像采集单元同时对自身图像采集区域进行采集，获得两张所述待分析图像。
第三方面，本发明实施例提供一种计算机存储介质，本发明实施例提供的计算机存储介质存储有计算机程序，该计算机程序配置为执行上述提示方法。
本发明实施例所提供的提示方法、终端及计算机存储介质中，终端获得至少一个待分析图像，然后对该待分析图像至少进行景深计算，获得图像中的障碍物的类型和物体信息，接下来，根据物体信息，生成并输出与上述类型对应的提示信息，该提示信息用于指示用户避开障碍物，或者提示其他用户避开用户。这样，当用户在行走或者是过马路的时候，终端能够主动的提示用户，并且指示用户避开该障碍物；特别地，当用户是盲人时，终端能够自主的向其他用户输出提示信息，以提示他们主动避让该用户。这样，就能够防止意外发生，并且提升了终端的智能程度，提供良好的用户体验。
图1为本发明实施例中的提示方法的流程示意图；
图2为本发明实施例中的终端的一种结构示意图；
图3为本发明实施例中的图像处理单元的结构示意图；
图4为本发明实施例中的终端的另一种结构示意图。
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述。
本发明实施例提供一种提示方法，应用于一终端，该终端可以为智能手机、平板电脑、智能手表、智能手环、智能眼镜等。在终端上设置有一个图像采集单元，如摄像头，当然，也可以为两个图像采集单元，这两个图像采集单元朝向同一方向，并且两者之间的距离一定。
参见图1所示，该方法包括：
S101：获得至少一个待分析图像；
具体来说，当用户在行走时，可以手动开启障碍物提示功能，并使得终端的图像采集单元能够采集到位于用户前方的区域，或者，终端自行检测用户是否在移动，若是，自动开始障碍物提示功能，并提示用户将终端放置在能够使得终端的图像采集单元能够采集到位于用户前方的区域的位置。接下来，终端控制图像采集单元采集其采集区域内，也就是用户前方预设范围内的图像，该图像就是待分析图像。由于终端上还可以设置两个图像采集单元，即双摄像头结构，那么，终端控制两个图像采集单元同时对自身图像采集区域进行采集，获得两张待分析图像。
在实际应用中，通常图像采集单元采集图像的帧率在30帧左右,但是考虑到终端的中央处理器(CPU，Central Processing Unit)的处理速度有限.可以每隔3帧图像处理一帧数据。
S102：对至少一个待分析图像至少进行景深计算，获得至少一个待分析图像中的障碍物的类型和物体信息；
具体来说，由于障碍物可以为固定物体，如电线杆、消防栓、垃圾桶、书报亭等，还可以为移动物体，如行人、车辆等，那么，在获得障碍物的景深之后，还可以根据连续几个时刻同一障碍物的景深，确定该障碍物是固定物体还是移动物体。比如，对待分析图像中搜索范围为2米以内的首次发现的物体标号后加入障碍物列表.并同时记录该障碍物当前的距离值,连续3次被测定为1.5米内时，将该障碍物标记为固定物体。由于每秒计算多次，因此，在正常情况下，连续3次测得的距离值可能会略有递减，但大致相同。如果，其中出现过大过小值，就将该数据丢弃不用，补测一次。如果距离值出现连续快速增加或者快速减少，则将该障碍物标记为移动物体。在上述列表中，移动物体优先级最高,固定物体根据距离值由大到小依
次排列。
当障碍物为移动物体时，其物体信息仅包括物体的景深，也就是物体与终端之间的距离值，该距离值能够表征障碍物与用户之间的距离；而当障碍物为固定物体是，S102可以包括：对至少一个待分析图像进行景深计算，获得至少一个待分析图像中的障碍物与终端之间的距离值；基于多个距离值确定障碍物的类型为固定物体后，对障碍物的轮廓进行识别，并根据识别结果以及距离值，确定障碍物的物体尺寸值；将距离值与物体尺寸值确定为障碍物的物体信息。
具体来说，终端对至少一个待分析图像进行景深计算，获得至少一个待分析图像中的障碍物与终端之间的距离值，根据障碍物的距离值，确定该障碍物是固定物体还是移动物体，当该障碍物为固定物体时，为了避开该障碍物，终端就还需要计算障碍物的尺寸，于是，终端对障碍物的轮廓进行识别。由于图像采集单元的像素点的大小是已知的,则该障碍物所成的像的宽度大致等于像素点的个数乘以像素点的大小，那么，可以根据该障碍物的距离和在待分析图像上的宽度，依据相似三角形的关系，得出实际的宽度，即检测出障碍物的尺寸值，然后，终端将距离值与物体尺寸值确定为该障碍物的物体信息。
需要说明的是，当终端通过S101获得两张待分析图像时，对待分析图像进行景深计算的过程具体为：终端根据两个图像采集单元在出厂时的校准数据,＝把两张待分析图像校准到同一个三维坐标系中.使得两个图像采集单元在数学上完全平行放置，然后，使用立体匹配方法，如立体视觉算法(SGBM),计算出视差，再根据视差计算出障碍物到主图像采集单元(通常是左图像采集单元)的距离值。
实际使用中,在前进道路上有可以允许一人通过的空间即可,因此，需要在图像采集单元的采集区域内的图像中对搜索范围进行调整。由于搜索
范围太宽，可能导致过多障碍物提示，干扰用户使用，也会因为计算时间长，导致提示有延时；而搜索范围太窄,则有可能漏测，那么，通常设置为60cm，此时，用户即可小心通过。当然，用户也可以根据自己的体形和行走习惯自行设定搜索范围，本发明不做具体限定。
S103：根据物体信息，生成并输出提示信息，其中，提示信息用于指示用户避开障碍物，或者提示其他用户避开用户。
在实际应用中，S103可以存在以下几种情况。
第一种情况，当障碍物的类型为固定物体时，终端根据物体信息，生成并输出包含一移动路线的提示信息，使得用户按照移动路线移动，以避开障碍物。
具体来说，在通过S102确定障碍物的类型为固定物体后，终端就根据障碍物的距离值以及物体尺寸值生成一个移动路线，并以语音、震动等方式输出给用户，用户按照该移动路线移动，就能够避开障碍物。
需要说明的是，在终端确定障碍物的类型为固定物体时，终端还可以判断该障碍物的物体尺寸值是否小于等于预设值，若是，则表明该障碍物比较小，可能为电线杆、垃圾桶等物体，此时，上述移动路线可以为“向左/右移动两步”；若果该障碍物的物体尺寸值大于等于预设值，则表明该障碍物比较大，可能为书报亭等，此时需要绕行，那么，上述移动路线可以为“向左/右移动五步，再向前移动3步“，以实际为准，本发明不做具体限定。
第二种情况，当障碍物的类型为移动物体时，终端根据物体信息，确定障碍物的移动方向；当障碍物朝向终端移动，且物体信息满足预设条件时，生成并输出提示信息，以提示其他用户避开用户；当障碍物朝向终端移动，且物体信息不满足预设条件时，生成并输出提示信息，以指示用户避开障碍物。
具体来说，当障碍物为移动物体时，终端首先根据物体信息，也就是距离值，确定该障碍物的移动方向，如果障碍物是远离终端移动的，此时，就可以不用提示用户了，如果，障碍物是朝向终端移动的，此时，终端还需要判断该障碍物离终端的距离是不是比较远，也就是说判断物体信息是否大于等于预设值，若是，则表明物体信息满足预设条件，反之，则表明物体信息不满足预设条件。那么，当物体信息满足预设条件时，终端生成并输出提示信息，如提示灯闪烁、输出提示音等方式提示其他用户避开终端的当前用户；当物体信息不满足预设条件时，也就是说，障碍物离用户很近，那么，此时，终端可以如第一种情况一般生成并输出提示信息，以指示用户避开障碍物。
至此，就完成了终端提示用户避开障碍物，或者提示其他用户避开当前用户的过程。
由上述可知，终端获得至少一个待分析图像，然后对该待分析图像至少进行景深计算，获得图像中的障碍物的类型和物体信息，接下来，根据物体信息，生成并输出与上述类型对应的提示信息，该提示信息配置为指示用户避开障碍物，或者提示其他用户避开用户。这样，当用户在行走或者是过马路的时候，终端能够主动的提示用户，并且指示用户避开该障碍物；特别地，当用户是盲人时，终端能够自主的向其他用户输出提示信息，以提示他们主动避让该用户。这样，就能够防止意外发生，并且提升了终端的智能程度，提供良好的用户体验。
基于同一发明构思，本发明实施例提供一种终端，与上述一个或者多个实施例中所述的终端一致。
参见图2所示，该终端包括：获得单元21、图像处理单元22以及提示单元23；其中，获得单元21，配置为获得至少一个待分析图像；图像处理单元22，配置为对至少一个待分析图像至少进行景深计算，获得至少一个
待分析图像中的障碍物的类型以及物体信息；提示单元23，配置为根据物体信息，生成并输出障碍物的类型对应的提示信息，其中，提示信息用于指示用户避开障碍物，或者提示其他用户避开用户。
在上述方案中，参见图3所示，图像处理单元22，包括：景深计算子单元221、图像识别子单元222以及确定子单元223；景深计算子单元221，还配置为对至少一个待分析图像进行景深计算，获得至少一个待分析图像中的障碍物与终端之间的距离值；还配置为基于多个距离值确定障碍物的类型为固定物体；图像识别子单元222，配置为在景深计算子单元基于距离值确定障碍物为固定物体后，对障碍物的轮廓进行识别，并根据识别结果以及距离值，确定障碍物的物体尺寸值；确定子单元223，配置为将距离值与物体尺寸值确定为障碍物的物体信息。
在上述方案中，提示单元23，还配置为当障碍物的类型为固定物体时，根据物体信息，生成并输出包含一移动路线的提示信息，使得用户按照移动路线移动，以避开障碍物。
在上述方案中，提示单元23，还配置为当障碍物的类型为移动物体时，根据物体信息，确定障碍物的移动方向；当障碍物朝向终端移动，且物体信息满足预设条件时，生成并输出提示信息，以提示其他用户避开用户；当障碍物朝向终端移动，且物体信息不满足预设条件时，生成并输出提示信息，以指示用户避开障碍物。
在上述方案中，参见图4所示，上述终端，还包括两个图像采集单元41，两个图像采集单元41朝向同一方向，且相对位置不变；获得单元21，配置为控制两个图像采集单元41同时对自身图像采集区域进行采集，获得两张待分析图像。
在实际应用中，所述终端中的各个单元所实现的功能，均可由位于终端中的中央处理器(Central Processing Unit，CPU)、微处理器(Micro
Processor Unit，MPU)、数字信号处理器(Digital Signal Processor，DSP)、或现场可编程门阵列(Field Programmable Gate Array，FPGA)等实现。
本发明实施例上述业务信令跟踪的装置如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明实施例的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机、服务器、或者网络设备等)执行本发明各个实施例所述方法的全部或部分。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read Only Memory)、磁碟或者光盘等各种可以存储程序代码的介质。这样，本发明实施例不限制于任何特定的硬件和软件结合。
相应地，本发明实施例还提供一种计算机存储介质，其中存储有计算机程序，该计算机程序用于执行本发明实施例的提示方法。
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用硬件实施例、软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器和光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功
能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
以上所述，仅为本发明的较佳实施例而已，并非用于限定本发明的保护范围。
Claims (11)
- 一种提示方法，应用于一终端，包括：获得至少一个待分析图像；对所述至少一个待分析图像至少进行景深计算，获得所述至少一个待分析图像中的障碍物的类型以及物体信息；根据所述物体信息，生成并输出所述障碍物的类型对应的提示信息，其中，所述提示信息用于指示用户避开所述障碍物，或者提示其他用户避开所述用户。
- 根据权利要求1所述的方法，其中，所述对所述至少一个待分析图像至少进行景深计算，获得所述至少一个待分析图像中的障碍物的类型以及物体信息，包括：对所述至少一个待分析图像进行景深计算，获得所述至少一个待分析图像中的障碍物与所述终端之间的距离值；基于多个所述距离值确定所述障碍物的类型为固定物体后，对所述障碍物的轮廓进行识别，并根据识别结果以及所述距离值，确定所述障碍物的物体尺寸值；将所述距离值与所述物体尺寸值确定为所述障碍物的物体信息。
- 根据权利要求1所述的方法，其中，所述根据所述物体信息，生成并输出所述障碍物的类型对应的提示信息，包括：当所述障碍物的类型为固定物体时，根据所述物体信息，生成并输出包含一移动路线的所述提示信息，使得所述用户按照所述移动路线移动，以避开所述障碍物。
- 根据权利要求1所述的方法，其中，所述根据所述物体信息，生成并输出提示信息，包括：当所述障碍物的类型为移动物体时，根据物体信息，确定所述障碍物 的移动方向；当所述障碍物朝向所述终端移动，且所述物体信息满足预设条件时，生成并输出所述提示信息，以提示所述其他用户避开所述用户；当所述障碍物朝向所述终端移动，且所述物体信息不满足预设条件时，生成并输出所述提示信息，以指示所述用户避开所述障碍物。
- 根据权利要求1所述的方法，其中，所述终端上设置有两个图像采集单元，所述两个图像采集单元朝向同一方向，且相对位置不变；所述获得待分析图像，包括：控制所述两个图像采集单元同时对自身图像采集区域进行采集，获得两张所述待分析图像。
- 一种终端，包括：获得单元、图像处理单元以及提示单元；其中，所述获得单元，配置为获得至少一个待分析图像；所述图像处理单元，配置为对所述至少一个待分析图像至少进行景深计算，获得所述至少一个待分析图像中的障碍物的类型以及物体信息；所述提示单元，配置为根据所述物体信息，生成并输出所述障碍物的类型对应的提示信息，其中，所述提示信息用于指示用户避开所述障碍物，或者提示其他用户避开所述用户。
- 根据权利要求6所述的终端，其中，所述图像处理单元，包括：景深计算子单元、图像识别子单元以及确定子单元；所述景深计算子单元，还配置为对所述至少一个待分析图像进行景深计算，获得所述至少一个待分析图像中的障碍物与所述终端之间的距离值；还配置为基于多个所述距离值确定所述障碍物的类型为固定物体；所述图像识别子单元，配置为在所述景深计算子单元基于所述距离值确定所述障碍物为固定物体后，对所述障碍物的轮廓进行识别，并根据识别结果以及所述距离值，确定所述障碍物的物体尺寸值；所述确定子单元，配置为将所述距离值与所述物体尺寸值确定为所述障碍物的物体信息。
- 根据权利要求6所述的终端，其中，所述提示单元，还配置为当所述障碍物的类型为固定物体时，根据所述物体信息，生成并输出包含一移动路线的所述提示信息，使得所述用户按照所述移动路线移动，以避开所述障碍物。
- 根据权利要求6所述的终端，其中，所述提示单元，还配置为当所述障碍物的类型为移动物体时，根据物体信息，确定所述障碍物的移动方向；当所述障碍物朝向所述终端移动，且所述物体信息满足预设条件时，生成并输出所述提示信息，以提示所述其他用户避开所述用户；当所述障碍物朝向所述终端移动，且所述物体信息不满足预设条件时，生成并输出所述提示信息，以指示所述用户避开所述障碍物。
- 根据权利要求6所述的终端，其中，所述终端，还包括两个图像采集单元，所述两个图像采集单元朝向同一方向，且相对位置不变；所述获得单元，配置为控制所述两个图像采集单元同时对自身图像采集区域进行采集，获得两张所述待分析图像。
- 一种计算机存储介质，所述计算机存储介质中存储有计算机可执行指令，该计算机可执行指令配置为执行权利要求1-5任一项所述的提示方法。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510493305.5A CN106469288A (zh) | 2015-08-12 | 2015-08-12 | 一种提示方法及终端 |
| CN201510493305.5 | 2015-08-12 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2016145789A1 true WO2016145789A1 (zh) | 2016-09-22 |
Family
ID=56918283
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2015/088368 WO2016145789A1 (zh) | 2015-08-12 | 2015-08-28 | 一种提示方法、终端及计算机存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106469288A (zh) |
| WO (1) | WO2016145789A1 (zh) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108318706A (zh) * | 2017-12-29 | 2018-07-24 | 维沃移动通信有限公司 | 移动物体的测速方法和装置 |
| CN109426277A (zh) * | 2017-08-30 | 2019-03-05 | 广州极飞科技有限公司 | 移动轨迹规划的方法及装置 |
| CN112506204A (zh) * | 2020-12-17 | 2021-03-16 | 深圳市普渡科技有限公司 | 机器人遇障处理方法、装置、设备和计算机可读存储介质 |
| CN116468351A (zh) * | 2023-06-16 | 2023-07-21 | 深圳市磅旗科技智能发展有限公司 | 一种基于大数据的智慧物流管理方法 |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133572A (zh) * | 2017-04-11 | 2017-09-05 | 北京小米移动软件有限公司 | 基于用户运动状态下的障碍物提示方法、装置及终端 |
| CN107307980B (zh) * | 2017-06-16 | 2020-08-04 | 昆山肇观电子科技有限公司 | 一种向目标对象提示信息的方法及装置 |
| CN108009508B (zh) * | 2017-12-11 | 2021-10-08 | 惠州市德赛西威汽车电子股份有限公司 | 基于景深估计运动物体视觉检测方法与系统 |
| CN108230391A (zh) * | 2017-12-13 | 2018-06-29 | 深圳市鸿益达供应链科技有限公司 | 智能识别方法 |
| CN110191255A (zh) * | 2018-11-06 | 2019-08-30 | 广东小天才科技有限公司 | 一种基于可穿戴设备的提示方法及可穿戴设备 |
| CN109584632A (zh) * | 2018-12-14 | 2019-04-05 | 深圳壹账通智能科技有限公司 | 路况预警方法、装置、计算机设备和存储介质 |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120162412A1 (en) * | 2010-12-22 | 2012-06-28 | Electronics And Telecommunications Research Institute | Image matting apparatus using multiple cameras and method of generating alpha maps |
| CN104055657A (zh) * | 2014-06-18 | 2014-09-24 | 浙江师范大学 | 一种基于Kinect的导盲拐杖及其实现方法 |
-
2015
- 2015-08-12 CN CN201510493305.5A patent/CN106469288A/zh active Pending
- 2015-08-28 WO PCT/CN2015/088368 patent/WO2016145789A1/zh active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120162412A1 (en) * | 2010-12-22 | 2012-06-28 | Electronics And Telecommunications Research Institute | Image matting apparatus using multiple cameras and method of generating alpha maps |
| CN104055657A (zh) * | 2014-06-18 | 2014-09-24 | 浙江师范大学 | 一种基于Kinect的导盲拐杖及其实现方法 |
Non-Patent Citations (1)
| Title |
|---|
| CHEN, XI: "Stereoscopic Moving Object Detection and Tracking Based on Mutual Information", ELECTRONIC TECHNOLOGY & INFORMATION SCIENCE , CHINA MASTER'S THESES FULL-TEXT DATABASE, 15 December 2009 (2009-12-15) * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109426277A (zh) * | 2017-08-30 | 2019-03-05 | 广州极飞科技有限公司 | 移动轨迹规划的方法及装置 |
| CN109426277B (zh) * | 2017-08-30 | 2022-11-08 | 广州极飞科技股份有限公司 | 移动轨迹规划的方法及装置 |
| CN108318706A (zh) * | 2017-12-29 | 2018-07-24 | 维沃移动通信有限公司 | 移动物体的测速方法和装置 |
| CN112506204A (zh) * | 2020-12-17 | 2021-03-16 | 深圳市普渡科技有限公司 | 机器人遇障处理方法、装置、设备和计算机可读存储介质 |
| CN116468351A (zh) * | 2023-06-16 | 2023-07-21 | 深圳市磅旗科技智能发展有限公司 | 一种基于大数据的智慧物流管理方法 |
| CN116468351B (zh) * | 2023-06-16 | 2023-11-07 | 深圳市磅旗科技智能发展有限公司 | 一种基于大数据的智慧物流管理方法、系统以及存储介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106469288A (zh) | 2017-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2016145789A1 (zh) | 一种提示方法、终端及计算机存储介质 | |
| JP2020095748A (ja) | 眼輻輳に基づいた視覚不注意の検出 | |
| EP3190781B1 (en) | Autofocus method, device and electronic apparatus | |
| EP3131311B1 (en) | Monitoring | |
| KR102129698B1 (ko) | 자동 어류 계수 시스템 | |
| CN104966062B (zh) | 视频监视方法和装置 | |
| TWI474173B (zh) | 行走輔助系統及行走輔助方法 | |
| JP2013500536A5 (zh) | ||
| US20210089792A1 (en) | Method and apparatus for outputting information | |
| JP2020502559A5 (zh) | ||
| JP2017103688A5 (zh) | ||
| US20140175162A1 (en) | Identifying Products As A Consumer Moves Within A Retail Store | |
| CN109191513A (zh) | 基于全局优化的电力设备立体匹配方法 | |
| JP2009025910A (ja) | 障害物検出装置、障害物検出システム及び障害物検出方法 | |
| CN104869316A (zh) | 一种多目标的摄像方法及装置 | |
| JP2020513627A (ja) | インテリジェント盲導方法および装置 | |
| JP2021519983A (ja) | 画像処理方法及び装置、電子機器並びにコンピュータ可読記憶媒体 | |
| WO2019085519A1 (zh) | 面部跟踪方法及装置 | |
| CN104680563A (zh) | 一种图像数据的生成方法和装置 | |
| KR101648786B1 (ko) | 객체 인식 방법 | |
| KR101558805B1 (ko) | 스테레오 매칭용 보간 계수 보정 장치 | |
| US9449340B2 (en) | Method and system for managing an electronic shopping list with gestures | |
| WO2015198284A1 (en) | Reality description system and method | |
| KR20150086840A (ko) | 복수개의 카메라를 이용한 휴대 장치 및 제어방법 | |
| CN104133525A (zh) | 一种信息处理方法及电子设备 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 15885164 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 15885164 Country of ref document: EP Kind code of ref document: A1 |