技术领域technical field
本发明涉及定位技术领域，更具体地说，涉及一种室内定位方法和系统。The present invention relates to the technical field of positioning, and more specifically, to an indoor positioning method and system.
背景技术Background technique
人们80％以上时间在室内活动，70％以上的通信量来自室内，室内定位导航的需求愈显突出，购物导航、室内救援、灾难逃生导引、医疗救护、机场向导、社交网络、特殊群体关爱救助等新的应用必将引发新的业务模式，极大提高数据流量，提供新的业务增值点，室内定位将成为基于位置的服务(Location Based Service，LBS)的主要市场。People spend more than 80% of their time indoors, and more than 70% of their traffic comes from indoors. The demand for indoor positioning and navigation is becoming more and more prominent, such as shopping navigation, indoor rescue, disaster escape guidance, medical rescue, airport guide, social network, and care for special groups. New applications such as rescue will inevitably lead to new business models, greatly increase data traffic, and provide new business value-added points. Indoor positioning will become the main market for location-based services (Location Based Service, LBS).
在室内需要定位时，一般选用可见光成像的定位方法进行室内定位，在采用可见光进行定位时，每个时刻定位处的结果只使用了一组特征点坐标信息，导致定位结果精准度低。When positioning is required indoors, the positioning method of visible light imaging is generally used for indoor positioning. When using visible light for positioning, only a set of feature point coordinate information is used for the positioning results at each moment, resulting in low accuracy of positioning results.
发明内容Contents of the invention
本发明的目的在于提供一种室内定位方法和系统，用于解决现有技术中采用可见光成像法定位时精准度低的问题。The purpose of the present invention is to provide an indoor positioning method and system for solving the problem of low accuracy in positioning using visible light imaging in the prior art.
为实现上述目的，本发明实施例提供了如下技术方案：In order to achieve the above object, the embodiment of the present invention provides the following technical solutions:
一种室内定位方法，应用于定位装置中，包括：An indoor positioning method, applied to a positioning device, comprising:
在t1至t2时间段内采集定位区域的帧图像；Collect frame images of the positioning area during the time period from t1 to t2;
提取采集到的所述帧图像上的特征点信息；extracting feature point information on the collected frame image;
采用可见光成像定位系统对所述特征点信息进行可见光定位，获得与t1至t2时间采集到的每个帧图像所匹配的可行解；Visible light positioning is performed on the feature point information by using a visible light imaging positioning system, and a feasible solution matching each frame image collected from time t1 to t2 is obtained;
判断所述帧图像中的特征点信息的数量；Judging the quantity of feature point information in the frame image;
当所述特征点的数量不小于预设值时，提取与t1至t2时间段内的预设时刻tm拍摄到的帧图像所匹配的可行解P(tm)；When the number of the feature points is not less than the preset value, extract a feasible solution P(tm) that matches the frame image captured at the preset moment tm within the time period from t1 to t2;
获取惯性导航系统t1至t2时间段内连续测得的运动体航向角和速度；Obtain the heading angle and velocity of the moving body continuously measured by the inertial navigation system during the time period from t1 to t2;
采用惯性导航系统依据所述可行解P(tm)、所述运动体航向角和所述速度计算得到t1至t2内各个时刻定位装置的位置信息；Using an inertial navigation system to calculate the position information of the positioning device at each time from t1 to t2 according to the feasible solution P(tm), the heading angle of the moving body and the speed;
采用最小二乘法对由可见光成像定位系统得到的t1至t2时间采集到的每个帧图像所匹配的可行解和所述惯性导航系统进行计算，得到的t1至t2内各个时刻的位置信息进行曲线拟合，得到拟合后的预设时刻的位置信息P(tm1)；The least square method is used to calculate the feasible solution matched by each frame image collected by the visible light imaging and positioning system from t1 to t2 and the inertial navigation system, and the obtained position information at each time point from t1 to t2 is plotted Fitting, obtaining the position information P(tm1) at the preset moment after fitting;
采用惯性导航系统依据所述预设时刻的位置信息P(tm1)和所述运动体航向角和速度计算得到t1至t2内各个时刻定位装置的位置信息并输出；Using the inertial navigation system to calculate and output the position information of the positioning device at each time from t1 to t2 according to the position information P(tm1) at the preset time and the heading angle and speed of the moving body;
其中，所述预设值为不小于4的正整数。Wherein, the preset value is a positive integer not less than 4.
优选的，上述室内定位方法中，还可以包括：Preferably, the above-mentioned indoor positioning method may also include:
当所述特征点的数量小于预设值时，获取所述可见光成像定位系统得到的与t1至t2时间段内采集到的各个帧图像所匹配的多个可行解；When the number of the feature points is less than the preset value, obtain multiple feasible solutions obtained by the visible light imaging positioning system and matched with each frame image collected during the time period from t1 to t2;
获取与所述多个可行解相匹配的相机主光轴信息；Obtaining the main optical axis information of the camera matching the plurality of feasible solutions;
将所述多个可行解中与所述相机主光轴信息所匹配的可行解作为定位结果输出。Outputting, among the plurality of feasible solutions, a feasible solution that matches the main optical axis information of the camera as a positioning result.
优选的，上述室内定位方法中，当所述特征点的数量值等于3时，所述将所述多个可行解中与所述主光轴信息所匹配的可行解作为定位结果输出，包括：Preferably, in the above indoor positioning method, when the number of feature points is equal to 3, outputting the feasible solution among the plurality of feasible solutions that matches the main optical axis information as a positioning result includes:
将所述多个可行解中与相机主光轴方向相一致可行解作为定位结果输出。A feasible solution consistent with the main optical axis direction of the camera among the plurality of feasible solutions is output as a positioning result.
优选的，上述室内定位方法中，当所述特征点的数量值等于2时，所述将所述多个可行解中与所述主光轴信息所匹配的可行解作为定位结果输出，包括：Preferably, in the above-mentioned indoor positioning method, when the number of the feature points is equal to 2, outputting the feasible solution among the plurality of feasible solutions that matches the main optical axis information as a positioning result includes:
将所述多个可行解中与所述相机主光轴相交叉的可行解作为定位结果输出。Outputting a feasible solution intersecting the main optical axis of the camera among the plurality of feasible solutions as a positioning result.
优选的，上述室内定位方法中，其特征在于，当所述特征点的数量值等于1时，所述将所述多个可行解中与所述主光轴信息所匹配的可行解作为定位结果输出，包括：Preferably, in the above-mentioned indoor positioning method, it is characterized in that, when the number of the feature points is equal to 1, the feasible solution among the plurality of feasible solutions that matches the main optical axis information is taken as the positioning result output, including:
依据所述相机主光轴方向和点光源方向确定相机光心所在的位置，将穿过所述相机光心的所述点光源方向上的可行解作为定位结果输出。The position of the optical center of the camera is determined according to the direction of the main optical axis of the camera and the direction of the point light source, and a feasible solution in the direction of the point light source passing through the optical center of the camera is output as a positioning result.
一种室内定位系统，包括：An indoor positioning system, comprising:
图像采集模块，用于在t1至t2时间段内采集定位区域的帧图像，将采集到的帧图像发送至特征点提取模块；An image acquisition module, configured to acquire frame images of the positioning area within the time period from t1 to t2, and send the acquired frame images to the feature point extraction module;
特征点提取模块，用于提取采集到的所述帧图像上的特征点信息，将提取到的所述特征点信息发送至可见光定位系统；A feature point extraction module, configured to extract feature point information on the collected frame image, and send the extracted feature point information to a visible light positioning system;
可见光成像定位系统，用于采用可见光成像定位法对所述特征点信息进行可见光定位，获得与t1至t2时间采集到的每个帧图像所匹配的可行解；The visible light imaging positioning system is used to perform visible light positioning on the feature point information by using the visible light imaging positioning method, and obtain a feasible solution matching each frame image collected from time t1 to t2;
特征点信息判断模块，用于判断所述帧图像中的特征点的数量，当所述特征点的数量不小于预设值时，输出第一数据信息至惯性导航系统，否则输出与所述特征点的数量相匹配的数据信息至所述惯性导航系统；The feature point information judging module is used to judge the number of feature points in the frame image, and when the number of feature points is not less than a preset value, output the first data information to the inertial navigation system, otherwise output the first data information to the inertial navigation system, otherwise output the same information as the feature point the number of points matching the data information to the inertial navigation system;
惯性导航系统，用于当获取到所述第一数据信息时，用于提取与t1至t2时间段内的预设时刻tm拍摄到的帧图像所匹配的可行解P(tm)，获取t1至t2时间段内连续测得的运动体航向角和速度，依据所述可行解P(tm)和所述运动体航向角和速度计算得到t1至t2内各个时刻定位装置的位置信息，采用最小二乘法对由可见光成像定位系统得到的t1至t2时间采集到的每个帧图像所匹配的可行解和计算得到的t1至t2内各个时刻的位置信息进行曲线拟合，得到拟合后的预设时刻的位置信息P(tm1)，采用惯性导航系统依据所述预设时刻的位置信息P(tm1)和所述运动体航向角和速度计算得到t1至t2内各个时刻定位装置的位置信息并输出；The inertial navigation system is used to extract the feasible solution P(tm) matching the frame image captured at the preset time tm within the time period from t1 to t2 when the first data information is obtained, and obtain the The course angle and speed of the moving body continuously measured in the time period t2 are calculated according to the feasible solution P(tm) and the heading angle and speed of the moving body to obtain the position information of the positioning device at each time from t1 to t2, and the least squares method is used Multiplication performs curve fitting on the feasible solution matched by each frame image collected from time t1 to t2 obtained by the visible light imaging positioning system and the calculated position information at each time from t1 to t2 to obtain the fitted preset The position information P(tm1) at the time, using the inertial navigation system to calculate the position information of the positioning device at each time from t1 to t2 based on the position information P(tm1) at the preset time and the heading angle and speed of the moving body, and output ;
所述预设值为不小于4的正整数。The preset value is a positive integer not less than 4.
优选的，上述室内定位系统中，当所述惯性导航系统获取到与所述特征点的数量相匹配的数据信息时，还用于：Preferably, in the above indoor positioning system, when the inertial navigation system acquires data information matching the number of feature points, it is further used for:
获取所述可见光成像定位系统得到的与t1至t2时间段内采集到的各个帧图像所匹配的多个可行解；获取与所述多个可行解相匹配的相机主光轴信息；将所述多个可行解中与所述相机主光轴信息所匹配的可行解作为定位结果输出。Obtain multiple feasible solutions obtained by the visible light imaging positioning system and matched with each frame image collected in the time period from t1 to t2; obtain the main optical axis information of the camera that matches the multiple feasible solutions; Among the multiple feasible solutions, a feasible solution that matches the main optical axis information of the camera is output as a positioning result.
优选的，上述室内定位系统中，当所述惯性导航系统获取到所述特征点的数量为3时的数据信息时，所述惯性导航系统具体用于：Preferably, in the above-mentioned indoor positioning system, when the inertial navigation system acquires the data information when the number of the feature points is 3, the inertial navigation system is specifically used for:
将所述多个可行解中与相机主光轴方向相一致可行解作为定位结果输出。A feasible solution consistent with the main optical axis direction of the camera among the plurality of feasible solutions is output as a positioning result.
优选的，上述室内定位系统中，当所述惯性导航系统获取到所述特征点的数量为2时的数据信息时，所述惯性导航系统具体用于：Preferably, in the above-mentioned indoor positioning system, when the inertial navigation system obtains the data information when the number of the feature points is 2, the inertial navigation system is specifically used for:
将所述多个可行解中与所述相机主光轴相交叉的可行解作为定位结果输出。Outputting a feasible solution intersecting the main optical axis of the camera among the plurality of feasible solutions as a positioning result.
优选的，上述室内定位系统中，当所述惯性导航系统获取到所述特征点的数量为1时的数据信息时，所述惯性导航系统具体用于：Preferably, in the above-mentioned indoor positioning system, when the inertial navigation system obtains the data information when the number of the feature points is 1, the inertial navigation system is specifically used for:
依据所述相机主光轴方向和点光源方向确定相机光心所在的位置，将穿过所述相机光心的所述点光源方向上的可行解作为定位结果输出。The position of the optical center of the camera is determined according to the direction of the main optical axis of the camera and the direction of the point light source, and a feasible solution in the direction of the point light source passing through the optical center of the camera is output as a positioning result.
通过以上方案可知，本发明实施例提供的室内定位方法，在t1至t2时间段内采集定位区域的帧图像，通过当获取到采用可见光成像定位系统计算得到的可行解后，依据预设时刻所对应的可行解P(tm)和t1至t2时间段内的运动体航向角和速度计算得到t1至t2时间段内定位装置的位置信息，再采用最小二乘法对由可见光成像定位系统得到的t1至t2时间采集到的每个帧图像所匹配的可行解和所述惯性导航系统计算得到的t1至t2内各个时刻的位置信息进行曲线拟合，得到拟合后的预设时刻的位置信息P(tm1)，再次P(tm1)和t1至t2时间段内的运动体航向角和速度计算得到t1至t2时间段内定位装置的位置信息，并作为定位结果输出，可见在计算预设时刻tm的位置信息时融合了整段时间(t1-t2)的特征点信息，所以可以获得更高精度的定位，而其他时刻的位置信息又是可以通过较高精度的惯性导航信息递推得到的，因而采用本申请上述实施例公开的技术方案可以有效提高定位精度。It can be seen from the above scheme that the indoor positioning method provided by the embodiment of the present invention collects the frame images of the positioning area within the time period from t1 to t2, and obtains the feasible solution calculated by the visible light imaging positioning system according to the preset time The corresponding feasible solution P(tm) and the course angle and velocity of the moving body in the time period from t1 to t2 are calculated to obtain the position information of the positioning device in the time period from t1 to t2, and then the least square method is used to compare the t1 obtained by the visible light imaging positioning system Perform curve fitting on the feasible solution matched by each frame image collected at time t2 and the position information at each time from t1 to t2 calculated by the inertial navigation system to obtain the fitted position information P at the preset time (tm1), again P(tm1) and the course angle and velocity of the moving body in the time period from t1 to t2 are calculated to obtain the position information of the positioning device in the time period from t1 to t2, and output as the positioning result, it can be seen that at the calculation of the preset time tm The location information of the whole time (t1-t2) is integrated with the feature point information, so higher-precision positioning can be obtained, and the location information at other times can be obtained recursively through higher-precision inertial navigation information. Therefore, the positioning accuracy can be effectively improved by adopting the technical solutions disclosed in the foregoing embodiments of the present application.
附图说明Description of drawings
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.
图1为本发明实施例公开的一种室内定位方法的流程图；FIG. 1 is a flowchart of an indoor positioning method disclosed in an embodiment of the present invention;
图2为本申请公开的定位方法与可见光成像定位法定位结果的对比示意图；Fig. 2 is a schematic diagram of the comparison between the positioning method disclosed in the present application and the positioning results of the visible light imaging positioning method;
图3为当帧图像上的特诊点数量少于预设值时，本申请公开的室内定位方法的流程图；Fig. 3 is a flow chart of the indoor positioning method disclosed in the present application when the number of special diagnosis points on the frame image is less than the preset value;
图4为本申请实施例公开的当帧图像上的特征点数量为1时，采用本申请公开的方法定得到的位结果的示意图；Fig. 4 is a schematic diagram of the bit result obtained by using the method disclosed in the present application when the number of feature points on the frame image disclosed in the embodiment of the present application is 1;
图5为本申请实施例公开的一种室内定位系统的示意图。Fig. 5 is a schematic diagram of an indoor positioning system disclosed in an embodiment of the present application.
具体实施方式detailed description
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，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
目前手机终端大多都有惯性导航系统，该系统包括陀螺仪、加速度传感器、重力传感器，地磁传感器等。其中陀螺仪、重力传感器和地磁传感器数据组合后可以获得手机当前的姿态和角加速度。当已知起始时刻手机的位置和姿态后，使用角加速度和位置加速度值的二次积分，即可获得新时刻手机的位置和姿态。At present, most mobile terminals have an inertial navigation system, which includes a gyroscope, an acceleration sensor, a gravity sensor, and a geomagnetic sensor. Among them, the current attitude and angular acceleration of the mobile phone can be obtained after the data of the gyroscope, the gravity sensor and the geomagnetic sensor are combined. When the position and attitude of the mobile phone at the initial time are known, the position and attitude of the mobile phone at the new time can be obtained by using the quadratic integral of the angular acceleration and the position acceleration value.
申请人研究发现惯性导航系统的定位精度会随时间推移而逐步下降，但是短时间内，如秒级，惯性导航系统能够提供较高精度的相对运动估计。利用惯性导航系统提供的精度较高的相对运动信息，可以有效提高可见光定位精度。The applicant's research found that the positioning accuracy of the inertial navigation system will gradually decrease over time, but in a short period of time, such as seconds, the inertial navigation system can provide relatively high-precision relative motion estimation. Using the high-precision relative motion information provided by the inertial navigation system can effectively improve the positioning accuracy of visible light.
图1为本申请实施例公开的一种融合基于可见光成像定位法和惯性导航法的室内定位方法，应用于定位装置中，所述定位装置例如手机，其具体方法流程，包括：Fig. 1 is an indoor positioning method based on the fusion of visible light imaging positioning method and inertial navigation method disclosed in the embodiment of the present application, which is applied to a positioning device. The positioning device is such as a mobile phone. The specific method flow includes:
首先，采用可见光成像定位法对目标区域进行定位，该步骤包括：First, use the visible light imaging positioning method to locate the target area. This step includes:
步骤S101：在t1至t2时间段内采集定位区域的帧图像；Step S101: Collect frame images of the positioning area within the time period from t1 to t2;
在该步骤中，采用照相机对目标区域内在t1-t2时间段内进行连续拍摄，获取连续的、按时间轴排列的帧图像，需要说明的是，所述t1-t2的时间间隔十分短，导致各个帧图像上的特征点的数量基本相同；In this step, the camera is used to continuously shoot within the time period t1-t2 in the target area to obtain continuous frame images arranged on the time axis. It should be noted that the time interval between t1-t2 is very short, resulting in The number of feature points on each frame image is basically the same;
步骤S102：提取采集到的所述帧图像上的特征点信息；Step S102: Extracting feature point information on the collected frame image;
步骤S103：采用可见光成像定位系统对所述特征点信息进行可见光定位，获得与t1至t2时间采集到的每个帧图像所匹配的可行解；Step S103: Using a visible light imaging and positioning system to perform visible light positioning on the feature point information, and obtain a feasible solution matching each frame image collected from time t1 to t2;
需要说明的时，所述可见光成像定位方法为现有技术中的一种技术较为成熟的定位方法，其具体实现方式在此并不再具体介绍；When it needs to be explained, the visible light imaging positioning method is a relatively mature positioning method in the prior art, and its specific implementation method will not be specifically introduced here;
在采用可见光成像定位方法获取到每个帧图像对应的可行解后，依据所述特征点的数量调用惯性导航系统，实现目标区域的精确定位，具体过程包括：After the feasible solution corresponding to each frame image is obtained by using the visible light imaging positioning method, the inertial navigation system is called according to the number of the feature points to realize the precise positioning of the target area. The specific process includes:
步骤S104：判断所述帧图像中的特征点信息的数量；Step S104: judging the quantity of feature point information in the frame image;
步骤S105：当所述特征点的数量不小于预设值时，提取与t1至t2时间段内的预设时刻tm拍摄到的帧图像所匹配的可行解P(tm)，所述预设值为不小于4的正整数；Step S105: When the number of feature points is not less than a preset value, extract a feasible solution P(tm) that matches the frame image captured at a preset time tm within the time period from t1 to t2, the preset value is a positive integer not less than 4;
可以理解的是，在采用可见光成像法进行定位时，理论上，至少需要采集到4个特征点才可以实现定位，且特征点数量越多，定位精度越高，因而本申请上述方法中将所述预设值的大小设置为不小于4的正整数。本步骤中的所述预设时刻tm可以根据用户需求设置为t1-t2之间的任意一时刻，优选的，本申请上述实施例中，所述tm时刻为t1-t2时间段内的中间时刻，即tm＝(t1+t2)/2；It can be understood that when the visible light imaging method is used for positioning, in theory, at least four feature points need to be collected to achieve positioning, and the greater the number of feature points, the higher the positioning accuracy. Therefore, in the above method of this application, all The size of the preset value is set to a positive integer not less than 4. The preset time tm in this step can be set to any time between t1-t2 according to user needs. Preferably, in the above-mentioned embodiments of the present application, the time tm is an intermediate time within the time period of t1-t2 , namely tm=(t1+t2)/2;
步骤S106：获取惯性导航系统t1至t2时间段内连续测得的各个时刻的运动体航向角和速度；Step S106: Obtain the heading angle and velocity of the moving body at each moment continuously measured by the inertial navigation system during the time period from t1 to t2;
步骤S107：采用惯性导航系统依据所述可行解P(tm)和所述运动体航向角和速度计算得到t1至t2内各个时刻定位装置的位置信息；Step S107: Using the inertial navigation system to calculate the position information of the positioning device at each time from t1 to t2 according to the feasible solution P(tm) and the heading angle and speed of the moving body;
假设在[t1,t2]区间内，用照相机对光源(目标区域)进行拍照定位。设预设时刻tm时，手机的位置是P(tm)，利用惯性导航系统提供的较精确的相对运动信息(即所述运动体航向角和速度)，可以依据P(tm)向前后递推出P(t),t∈[t1,t2]的位置。也就是说只要估计出P(tm)，就可以估计P(t),t∈[t1,t2]；Assume that in the interval [t1, t2], the camera is used to take pictures and locate the light source (target area). When the preset time tm is set, the position of the mobile phone is P(tm), and the more accurate relative motion information provided by the inertial navigation system (that is, the heading angle and speed of the moving body) can be deduced forward and backward based on P(tm). P(t), the position of t∈[t1,t2]. That is to say, as long as P(tm) is estimated, P(t), t∈[t1,t2] can be estimated;
步骤S108：采用最小二乘法对由可见光成像定位系统得到的t1至t2时间采集到的各个帧图像所匹配的可行解和由所述惯性导航系统计算得到的t1至t2内各个时刻的定位装置的位置信息进行曲线拟合，得到拟合后的预设时刻的位置信息P(tm1)；Step S108: Use the least squares method to match the feasible solutions obtained by the visible light imaging and positioning system for each frame image collected at time t1 to t2 and the positioning device at each time from t1 to t2 calculated by the inertial navigation system. Perform curve fitting on the position information to obtain the fitted position information P(tm1) at the preset moment;
步骤S109：采用惯性导航系统依据所述预设时刻的位置信息P(tm1)和所述运动体航向角和速度计算得到t1至t2内各个时刻定位装置的位置信息并输出，此时所述第二次计算得到的t1至t2内各个时刻定位装置的位置信息即为定位装置的当前位置信息。Step S109: Use the inertial navigation system to calculate and output the position information of the positioning device at each time from t1 to t2 based on the position information P(tm1) at the preset time and the heading angle and speed of the moving body, and output it. The position information of the positioning device at each time from t1 to t2 obtained through the secondary calculation is the current position information of the positioning device.
所述步骤S108和109中，综合[t1,t2]区间内拍摄的帧图像的可行解和由P(tm)决定的P(t)建立最小二乘估计，即可获得更准确的预设时刻tm的位置信息P(tm1)，再采用所述惯性导航系统依据所述P(tm1)进一步估计即可得到更精确的P(t0)信息。In the steps S108 and 109, the least squares estimation is established by integrating the feasible solutions of the frame images captured in the interval [t1, t2] and P(t) determined by P(tm), so as to obtain a more accurate preset time The position information P(tm1) of tm can be further estimated by the inertial navigation system based on the P(tm1) to obtain more accurate P(t0) information.
如图2所示，图2中所示每个点为该时刻的帧图像所对应的可行解，所示曲线为采用本申请上述实施例公开的技术方案得到的位置信息P(t0)，参见图2可见，若每个时刻分别用可见光成像发进行定位，其定位结果的误差较大，而联合惯性导航定位信息后，可以获得更高精度的定位。这是因为若仅用可见光逐帧定位，每个时刻只用了一组特征点坐标信息，而可见光定位与惯性导航联合定位后，计算预设时刻tm的位置信息时融合了整段时间(t1-t2)的特征点信息，所以可以获得更高精度的定位。而其他时刻(为获取帧图像的时刻)的位置信息又是可以通过较高精度的惯性导航信息递推得到的，因而采用本申请上述实施例公开的技术方案可以有效提高定位精度。As shown in Figure 2, each point shown in Figure 2 is the feasible solution corresponding to the frame image at this moment, and the curve shown is the position information P(t0) obtained by adopting the technical solution disclosed in the above-mentioned embodiments of the application, see It can be seen from Figure 2 that if visible light imaging is used for positioning at each moment, the error of the positioning result is relatively large, but after combining inertial navigation positioning information, higher precision positioning can be obtained. This is because if only visible light positioning is used for frame-by-frame positioning, only a set of feature point coordinate information is used at each moment, but after joint positioning of visible light positioning and inertial navigation, the entire period of time (t1 -t2) feature point information, so higher-precision positioning can be obtained. The location information at other times (for acquiring frame images) can be obtained by recursion of higher-precision inertial navigation information. Therefore, the technical solutions disclosed in the above-mentioned embodiments of the present application can effectively improve the positioning accuracy.
可以理解的是，在实时性要求较高的应用中，往往无法保证照相机拍摄到的每个帧图像都能获取到足够多的特征点，有时甚至连4个都达不到。此时就需要将所述惯性导航系统融合到可见光成像定位系统中，以弥补连贯性不佳的缺点，此时，在所述步骤S104中，判定出所述帧图像中的特征点信息的数量后，当所述特征点的数量小于预设值时，为了实现用户定位，上述方法还可以包括：It is understandable that in applications with high real-time requirements, it is often impossible to ensure that each frame of image captured by the camera can obtain enough feature points, sometimes even four. At this time, it is necessary to integrate the inertial navigation system into the visible light imaging positioning system to make up for the shortcoming of poor coherence. At this time, in the step S104, determine the number of feature point information in the frame image Finally, when the quantity of the feature points is less than the preset value, in order to realize user positioning, the above method may also include:
步骤S110：获取所述可见光成像定位系统得到的与t1至t2时间段内采集到的各个帧图像所匹配的多个可行解和获取与所述多个可行解相匹配的相机主光轴信息，所述与所述多个可行解相匹配的相机主光轴信息，可以理解为：所述每个图像帧对应多个可行解，且每个图像帧均对应一拍摄时刻，所述拍摄时刻所对应一相机的主光轴信息；Step S110: Obtain multiple feasible solutions obtained by the visible light imaging positioning system that match each frame image collected within the time period from t1 to t2, and acquire the main optical axis information of the camera that matches the multiple feasible solutions, The information about the main optical axis of the camera that matches the plurality of feasible solutions can be understood as: each image frame corresponds to a plurality of feasible solutions, and each image frame corresponds to a shooting moment. Corresponding to the main optical axis information of a camera;
步骤S111：将所述多个可行解中与所述相机主光轴信息所匹配的可行解作为定位结果输出。Step S111 : output a feasible solution among the plurality of feasible solutions that matches the main optical axis information of the camera as a positioning result.
可以理解的是，当每个帧图像上的特征点的数量小于4时，依据所述特征点的数量的不同，所得到的可行解也就不同，例如，当所述特征点的数量为3个时，每个帧图像对应的可行解的数量为两个，当所述特征点的数量为2个时，所述帧图像对应的可行解为空间中的一个已知半径的圆，当所述特征点的数量为1个时，每个帧图像所对应的可行解为具有一定角度的、以光源为中心的漏斗面。It can be understood that when the number of feature points on each frame image is less than 4, depending on the number of feature points, the obtained feasible solutions are different, for example, when the number of feature points is 3 , the number of feasible solutions corresponding to each frame image is two, and when the quantity of the feature points is 2, the feasible solution corresponding to the frame image is a circle with a known radius in space, when the When the number of the above-mentioned feature points is 1, the feasible solution corresponding to each frame image is a funnel surface with a certain angle and centered on the light source.
可以理解的是，当判断到所述特征点的数量为3个时，上述方法步骤S111，包括：It can be understood that, when it is determined that the number of the feature points is 3, step S111 of the above method includes:
将所述多个可行解中与相机主光轴方向相一致可行解作为定位结果输出。A feasible solution consistent with the main optical axis direction of the camera among the plurality of feasible solutions is output as a positioning result.
当所述帧图像仅能拍摄到3个特征点时(每个特征点为一光源)，仅依据这3个特征点，使用可见光成像定位法可得到2个可行解，且这两个可行解的主光轴方向是不一致的，此时可依据惯性导航系统提供的相机姿态信息获取相机主光轴，排除两个可行解中与所述相机主光轴方向不一致的一个错误的可行解，从而实现3个特征点的情况下的定位。When the frame image can only capture 3 feature points (each feature point is a light source), only based on these 3 feature points, two feasible solutions can be obtained by using the visible light imaging positioning method, and these two feasible solutions The direction of the main optical axis of the camera is inconsistent. At this time, the main optical axis of the camera can be obtained according to the camera attitude information provided by the inertial navigation system, and a wrong feasible solution among the two feasible solutions that is inconsistent with the direction of the main optical axis of the camera can be excluded, so that Realize the positioning in the case of 3 feature points.
可以理解的是，当判断到所述特征点的数量为2个时，上述方法步骤S111，包括：It can be understood that, when it is determined that the number of the feature points is 2, step S111 of the above method includes:
将所述多个可行解中与所述相机主光轴相交叉的可行解作为定位结果输出。Outputting a feasible solution intersecting the main optical axis of the camera among the plurality of feasible solutions as a positioning result.
当每个帧图像仅能拍摄到2个特征点时，此时得到的可行解是空间中的一个已知半径的圆，且该圆的圆心即为光源所在，利用惯性导航系统提供的手机姿态信息获取相机主光轴信息，所述相机主光轴穿过所述光源与所述半径已知的圆相交叉，将交叉点所对应的可行解作为定位结果输出。When only two feature points can be captured in each frame image, the feasible solution obtained at this time is a circle with a known radius in space, and the center of the circle is where the light source is located. Using the attitude of the mobile phone provided by the inertial navigation system The information acquires the information of the main optical axis of the camera, the main optical axis of the camera passes through the light source and intersects the circle with known radius, and outputs the feasible solution corresponding to the intersection point as a positioning result.
可以理解的是，当判断到所述特征点的数量为1个时，上述方法步骤S111，包括：It can be understood that, when it is determined that the number of the feature points is 1, step S111 of the above method includes:
依据所述相机主光轴方向和点光源方向确定相机光心所在的位置，将穿过所述相机光心的所述点光源方向上的可行解作为定位结果输出。The position of the optical center of the camera is determined according to the direction of the main optical axis of the camera and the direction of the point light source, and a feasible solution in the direction of the point light source passing through the optical center of the camera is output as a positioning result.
当所述帧图像上的特征点的数量为1个时，所述可行解为中心为光源的、具有一特定角度的漏斗形面。利用惯性导航系统可以获得相机主光轴方向，所述特定角度为光源方向与相机主光轴垂直方向上的夹角，进一步可以依据照片中主光轴与光源方向的夹角，确定相机光心所在的直线，参见图4，将穿过所述相机光心和所述光源的直线上的可行解所组成的直线作为定位结果输出。When the number of feature points on the frame image is one, the feasible solution is a funnel-shaped surface with a specific angle at the center of the light source. The direction of the main optical axis of the camera can be obtained by using the inertial navigation system. The specific angle is the angle between the direction of the light source and the direction perpendicular to the main optical axis of the camera. Further, the optical center of the camera can be determined according to the angle between the main optical axis and the direction of the light source in the photo. For the straight line, see FIG. 4 , the straight line formed by the feasible solutions on the straight line passing through the optical center of the camera and the light source is output as the positioning result.
可以理解的是，当所述特征点为1个时，所述可行解为具有一特定角度的直线，且该直线上的每个点所对应的相机的高度是不同的，因此用户还可以通过手机系统获取相机的高度信息，将与所述高度信息相匹配的可行解作为定位结果输出。It can be understood that when there is one feature point, the feasible solution is a straight line with a specific angle, and the height of the camera corresponding to each point on the straight line is different, so the user can also use The mobile phone system obtains the height information of the camera, and outputs a feasible solution matching the height information as a positioning result.
可以理解的是，与上述方法相对应，本申请还用开了一种室内定位系统，两者可相互借鉴，参见图5，所述系统包括：It can be understood that, corresponding to the above method, this application also uses an indoor positioning system, the two can learn from each other, see Figure 5, the system includes:
图像采集模块1，用于在t1至t2时间段内采集定位区域的帧图像，将采集到的帧图像发送至特征点提取模块；An image acquisition module 1, configured to acquire frame images of the positioning area within the time period from t1 to t2, and send the acquired frame images to the feature point extraction module;
特征点提取模块2，与所述图像采集模块1相连，用于提取采集到的所述帧图像上的特征点信息，将提取到的所述特征点信息发送至可见光定位系统3；A feature point extraction module 2, connected to the image acquisition module 1, for extracting feature point information on the collected frame image, and sending the extracted feature point information to the visible light positioning system 3;
与所述特征点提取模块2相连的可见光成像定位系统3，用于采用可见光成像定位法对所述特征点信息进行可见光定位，获得与t1至t2时间采集到的每个帧图像所匹配的可行解；The visible light imaging and positioning system 3 connected to the feature point extraction module 2 is used to perform visible light positioning on the feature point information by using the visible light imaging and positioning method, and obtain a feasible image matching each frame image collected from time t1 to t2. untie;
与所述可见光成像定位系统3相连的特征点信息判断模块4，用于判断所述帧图像中的特征点的数量，当所述特征点的数量不小于预设值时，所述预设值为不小于4的正整数，输出第一数据信息至惯性导航系统，否则输出与所述特征点的数量相匹配的数据信息至所述惯性导航系统；The feature point information judging module 4 connected to the visible light imaging positioning system 3 is used to judge the number of feature points in the frame image. When the number of feature points is not less than a preset value, the preset value is a positive integer not less than 4, output the first data information to the inertial navigation system, otherwise output the data information matching the number of the feature points to the inertial navigation system;
与所述可见光成像定位系统3和所述特征点信息判断模块4相连的惯性导航系统5，当获取到所述第一数据信息时，用于提取与t1至t2时间段内的预设时刻tm拍摄到的帧图像所匹配的可行解P(tm)，获取t1至t2时间段内连续测得的运动体航向角和速度，依据所述可行解P(tm)和所述运动体航向角和速度计算得到t1至t2内各个时刻定位装置的位置信息，采用最小二乘法对由可见光成像定位系统3得到的t1至t2时间采集到的每个帧图像所匹配的可行解和t1至t2内各个时刻的位置信息进行曲线拟合，得到拟合后的预设时刻的位置信息P(tm1)，再依据所述预设时刻的位置信息P(tm1)和所述运动体航向角和速度计算得到t1至t2内各个时刻定位装置的位置信息并输出，将第二次计算得到的所述位置信息作为定位结果输出。The inertial navigation system 5 connected to the visible light imaging positioning system 3 and the feature point information judgment module 4 is used to extract the preset time tm within the time period from t1 to t2 when the first data information is obtained. Feasible solution P(tm) matched by the captured frame image, obtain the heading angle and velocity of the moving body continuously measured during the time period from t1 to t2, according to the feasible solution P(tm) and the heading angle and velocity of the moving body Calculate the speed to obtain the position information of the positioning device at each time from t1 to t2, and use the least square method to match the feasible solution of each frame image collected from the time t1 to t2 obtained by the visible light imaging positioning system 3 and each time period from t1 to t2 Curve fitting is performed on the position information at the time to obtain the fitted position information P(tm1) at the preset time, and then calculated based on the position information P(tm1) at the preset time and the heading angle and speed of the moving body The location information of the positioning device at each time from t1 to t2 is output, and the location information obtained by the second calculation is output as a positioning result.
与上述方法相对应，当所述惯性导航系统获取到与所述特征点的数量相匹配的数据信息时，即此时所述特征点的数量小于预设值，所述惯性导航系统还用于：Corresponding to the above method, when the inertial navigation system acquires data information that matches the number of feature points, that is, the number of feature points is less than a preset value at this time, the inertial navigation system is also used to :
获取所述可见光成像定位系统3得到的与t1至t2时间段内采集到的各个帧图像所匹配的多个可行解；获取与所述多个可行解相匹配的相机主光轴信息；将所述多个可行解中与所述相机主光轴信息所匹配的可行解作为定位结果输出。Obtain multiple feasible solutions obtained by the visible light imaging positioning system 3 and matched with each frame image collected during the time period from t1 to t2; obtain the main optical axis information of the camera that matches the multiple feasible solutions; Among the plurality of feasible solutions, the feasible solution that matches the main optical axis information of the camera is output as a positioning result.
与上述方法相对应，当所述惯性导航系统获取到所述特征点的数量为3时的数据信息时，所述惯性导航系统具体用于：Corresponding to the above method, when the inertial navigation system obtains the data information when the number of the feature points is 3, the inertial navigation system is specifically used for:
将所述多个可行解中与相机主光轴方向相一致可行解作为定位结果输出。A feasible solution consistent with the main optical axis direction of the camera among the plurality of feasible solutions is output as a positioning result.
与上述方法相对应，当所述惯性导航系统获取到所述特征点的数量为2时的数据信息时，所述惯性导航系统具体用于：Corresponding to the above method, when the inertial navigation system acquires the data information when the number of the feature points is 2, the inertial navigation system is specifically used for:
将所述多个可行解中与所述相机主光轴相交叉的可行解作为定位结果输出。Outputting a feasible solution intersecting the main optical axis of the camera among the plurality of feasible solutions as a positioning result.
与上述方法相对应，当所述惯性导航系统获取到所述特征点的数量为1时的数据信息时，所述惯性导航系统具体用于：Corresponding to the above method, when the inertial navigation system acquires the data information when the number of the feature points is 1, the inertial navigation system is specifically used for:
依据所述相机主光轴方向和点光源方向确定相机光心所在的位置，将穿过所述相机光心的所述点光源方向上的可行解作为定位结果输出。The position of the optical center of the camera is determined according to the direction of the main optical axis of the camera and the direction of the point light source, and a feasible solution in the direction of the point light source passing through the optical center of the camera is output as a positioning result.
可以理解的是，本申请还公开了一种应用上述任一一项实施例公开的室内定位系统的手机。It can be understood that the present application also discloses a mobile phone using the indoor positioning system disclosed in any one of the above embodiments.
为了描述的方便，描述以上系统时以功能分为各种模块分别描述。当然，在实施本申请时可以把各模块的功能在同一个或多个软件和/或硬件中实现。For the convenience of description, when describing the above system, the functions are divided into various modules and described separately. Of course, when implementing the present application, the functions of each module can be realized in one or more pieces of software and/or hardware.
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于系统或系统实施例而言，由于其基本相似于方法实施例，所以描述得比较简单，相关之处参见方法实施例的部分说明即可。以上所描述的系统及系统实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性劳动的情况下，即可以理解并实施。Each embodiment in this specification is described in a progressive manner, the same and similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiment. The systems and system embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is It can be located in one place, or it can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without creative effort.
专业人员还可以进一步意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。Professionals can further realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software or a combination of the two. In order to clearly illustrate the possible For interchangeability, in the above description, the composition and steps of each example have been generally described according to their functions. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present invention.
结合本文中所公开的实施例描述的方法或算法的步骤可以直接用硬件、处理器执行的软件模块，或者二者的结合来实施。软件模块可以置于随机存储器(RAM)、内存、只读存储器(ROM)、电可编程ROM、电可擦除可编程ROM、寄存器、硬盘、可移动磁盘、CD-ROM、或技术领域内所公知的任意其它形式的存储介质中。The steps of the methods or algorithms described in connection with the embodiments disclosed herein may be directly implemented by hardware, software modules executed by a processor, or a combination of both. Software modules can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other Any other known storage medium.
还需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。It should also be noted that in this article, relational terms such as first and second etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that these entities or operations Any such actual relationship or order exists between. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes elements not expressly listed. other elements of or also include elements inherent in such a process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.
对所公开的实施例的上述说明，使本领域专业技术人员能够实现或使用本发明。对这些实施例的多种修改对本领域的专业技术人员来说将是显而易见的，本文中所定义的一般原理可以在不脱离本发明的精神或范围的情况下，在其它实施例中实现。因此，本发明将不会被限制于本文所示的这些实施例，而是要符合与本文所公开的原理和新颖特点相一致的最宽的范围。The above description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710010838.2ACN106840140B (en) | 2017-01-06 | 2017-01-06 | An indoor positioning method and system |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710010838.2ACN106840140B (en) | 2017-01-06 | 2017-01-06 | An indoor positioning method and system |
| Publication Number | Publication Date |
|---|---|
| CN106840140Atrue CN106840140A (en) | 2017-06-13 |
| CN106840140B CN106840140B (en) | 2020-05-22 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710010838.2AExpired - Fee RelatedCN106840140B (en) | 2017-01-06 | 2017-01-06 | An indoor positioning method and system |
| Country | Link |
|---|---|
| CN (1) | CN106840140B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108955718A (en)* | 2018-04-10 | 2018-12-07 | 中国科学院深圳先进技术研究院 | A kind of visual odometry and its localization method, robot and storage medium |
| CN110057352A (en)* | 2018-01-19 | 2019-07-26 | 北京图森未来科技有限公司 | A kind of camera attitude angle determines method and device |
| CN110324781A (en)* | 2019-07-16 | 2019-10-11 | 拉扎斯网络科技（上海）有限公司 | Indoor positioning method and device, electronic equipment and computer readable storage medium |
| US10949998B2 (en) | 2018-01-16 | 2021-03-16 | Boe Technology Group Co., Ltd. | Indoor space positioning based on Voronoi diagram |
| US11340074B2 (en) | 2018-03-14 | 2022-05-24 | Boe Technology Group Co., Ltd. | Positioning method, positioning apparatus, and computer-program product |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106961833B (en)* | 2006-05-10 | 2010-03-10 | 中国人民解放军国防科学技术大学 | Single camera is to space movement target localization method |
| US20110178708A1 (en)* | 2010-01-18 | 2011-07-21 | Qualcomm Incorporated | Using object to align and calibrate inertial navigation system |
| CN102435188A (en)* | 2011-09-15 | 2012-05-02 | 南京航空航天大学 | A Monocular Vision/Inertial Fully Autonomous Navigation Method for Indoor Environment |
| CN103808319A (en)* | 2014-02-26 | 2014-05-21 | 上海交通大学 | Indoor Hybrid Positioning System and Method Based on Inertial Positioning and VLC Technology |
| CN104181500A (en)* | 2014-08-19 | 2014-12-03 | 北京邮电大学 | Real-time locating method based on inertia information and chance wireless signal characteristics |
| CN105674986A (en)* | 2016-04-05 | 2016-06-15 | 中国电子科技集团公司第二十研究所 | Indoor positioning method adopting visible light and inert composition |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106961833B (en)* | 2006-05-10 | 2010-03-10 | 中国人民解放军国防科学技术大学 | Single camera is to space movement target localization method |
| US20110178708A1 (en)* | 2010-01-18 | 2011-07-21 | Qualcomm Incorporated | Using object to align and calibrate inertial navigation system |
| CN102435188A (en)* | 2011-09-15 | 2012-05-02 | 南京航空航天大学 | A Monocular Vision/Inertial Fully Autonomous Navigation Method for Indoor Environment |
| CN103808319A (en)* | 2014-02-26 | 2014-05-21 | 上海交通大学 | Indoor Hybrid Positioning System and Method Based on Inertial Positioning and VLC Technology |
| CN104181500A (en)* | 2014-08-19 | 2014-12-03 | 北京邮电大学 | Real-time locating method based on inertia information and chance wireless signal characteristics |
| CN105674986A (en)* | 2016-04-05 | 2016-06-15 | 中国电子科技集团公司第二十研究所 | Indoor positioning method adopting visible light and inert composition |
| Title |
|---|
| 张朝飞等: "一种复杂多介质环境下的视觉/惯性自适应组合导航方法", 《中国惯性技术学报》* |
| 李永佳等: "改进Harris特征点的机器人定位算法", 《传感器与微系统》* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10949998B2 (en) | 2018-01-16 | 2021-03-16 | Boe Technology Group Co., Ltd. | Indoor space positioning based on Voronoi diagram |
| CN110057352A (en)* | 2018-01-19 | 2019-07-26 | 北京图森未来科技有限公司 | A kind of camera attitude angle determines method and device |
| US11715232B2 (en) | 2018-01-19 | 2023-08-01 | Beijing Tusen Zhitu Technology Co., Ltd. | Method and device to determine the camera position and angle |
| US12205321B2 (en) | 2018-01-19 | 2025-01-21 | Beijing Tusen Zhitu Technology Co., Ltd. | Method and device to determine the camera position and angle |
| US11340074B2 (en) | 2018-03-14 | 2022-05-24 | Boe Technology Group Co., Ltd. | Positioning method, positioning apparatus, and computer-program product |
| CN108955718A (en)* | 2018-04-10 | 2018-12-07 | 中国科学院深圳先进技术研究院 | A kind of visual odometry and its localization method, robot and storage medium |
| CN110324781A (en)* | 2019-07-16 | 2019-10-11 | 拉扎斯网络科技（上海）有限公司 | Indoor positioning method and device, electronic equipment and computer readable storage medium |
| CN110324781B (en)* | 2019-07-16 | 2020-08-21 | 拉扎斯网络科技（上海）有限公司 | Indoor positioning method, device, electronic device, and computer-readable storage medium |
| US12010588B2 (en) | 2019-07-16 | 2024-06-11 | Rajax Network Technology (Shanghai) Co., Ltd. | Indoor positioning methods, apparatuses, electronic device and computer readable storage medium |
| Publication number | Publication date |
|---|---|
| CN106840140B (en) | 2020-05-22 |
| Publication | Publication Date | Title |
|---|---|---|
| CN106840140A (en) | A kind of indoor orientation method and system | |
| EP2434256B1 (en) | Camera and inertial measurement unit integration with navigation data feedback for feature tracking | |
| CN104173054B (en) | Measuring method and measuring device for height of human body based on binocular vision technique | |
| CN105627932B (en) | A kind of distance measuring method and device based on binocular vision | |
| CN108801209A (en) | Filming apparatus, image processing method and program | |
| CN105571583B (en) | A user location positioning method and server | |
| CN107478220A (en) | Unmanned plane indoor navigation method, device, unmanned plane and storage medium | |
| CN111623765B (en) | Indoor positioning method and system based on multimodal data | |
| CN107103056B (en) | Local identification-based binocular vision indoor positioning database establishing method and positioning method | |
| JPWO2020039937A1 (en) | Position coordinate estimation device, position coordinate estimation method and program | |
| WO2017201663A1 (en) | Moving object monitoring method, wearable apparatus, and server | |
| Liu et al. | Multiview and multimodal pervasive indoor localization | |
| CN110260857A (en) | Calibration method, device and the storage medium of vision map | |
| TWM560099U (en) | Indoor precise navigation system using augmented reality technology | |
| CN109902681A (en) | User group's relationship determines method, apparatus, equipment and storage medium | |
| CN113063421A (en) | Navigation method and related device, mobile terminal and computer readable storage medium | |
| CN114494582A (en) | A dynamic update method of 3D model based on visual perception | |
| WO2024083010A9 (en) | Visual localization method and related apparatus | |
| CN112422653A (en) | Scene information pushing method, system, storage medium and equipment based on location service | |
| CN109040525A (en) | Image processing method, device, computer-readable medium and electronic equipment | |
| JP7136344B2 (en) | Camera calibration method, camera and program | |
| CN108322698B (en) | System and method based on fusion of multiple cameras and inertial measurement unit | |
| KR101601726B1 (en) | Method and system for determining position and attitude of mobile terminal including multiple image acquisition devices | |
| Clark et al. | Robust vision-based indoor localization | |
| CN108235764B (en) | Information processing method, apparatus, cloud processing device, and computer program product |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee | Granted publication date:20200522 |