9 results about "Map labeling" patented technology

The present disclosure relates to a track map labeling method, device and system. The track map labeling method is applied to a labeling vehicle, and the method comprises: in response to a user's operation on the labeling vehicle, determining a working state in which the labeling vehicle is located, the working state comprising at least a labeling working state and a point searching working state; when it is determined that the labeling vehicle is in the labeling working state, determining whether a current labeling position is acquired; when it is determined that the current labeling position is acquired, labeling the current labeling position to obtain labeling information corresponding to the current labeling position. Through the present disclosure, the informationization of track map labeling data can be realized, the work efficiency is improved, and the introduction of human errors in the work process is avoided.

This application relates to a method, apparatus, electronic device, and mobile tool for annotating a grid map. The method includes: acquiring an occupied grid map and a reflectance grid map of a target area, wherein the reflectance grid map records the reflectance of point cloud data of the ground in the target area; mapping the reflectance of laser point clouds with reflectance less than a preset value in the reflectance grid map to a first interval, and mapping the reflectance of laser point clouds with reflectance greater than or equal to the preset value to the maximum value of the first interval, where the maximum value of the first interval is greater than the preset value; and annotating map features in the target area based on the occupied grid map and the adjusted reflectance grid map. This application solves the technical problem that the occupied grid map annotation is inaccurate and cannot reflect the obstacle situation within the area.

The application discloses a Beidou-based internet map digital intelligent labeling method and system, and belongs to the technical field of map labeling. The method specifically comprises the following steps: positioning and timing a mobile terminal by using a Beidou satellite navigation, generating trusted labeling data containing position information and a time stamp, collecting multi-modal sensing data by the mobile terminal, identifying and extracting labeling objects related to a map, and binding the labeling objects with the trusted labeling data to obtain a labeling object set, performing space-time normalization processing on the labeling object set, and converting the labeling object set into standardized labeling information available for an internet map service, aggregating and resolving conflicts of the standardized labeling information, and generating a trusted labeling result. The application improves the high precision and verifiability of labeling data, and also realizes cross-platform standardized intercommunication and real-time dynamic updating.

The utility model provides a map marking device, which relates to the technical field of map marking tools and comprises a bearing seat, a lighting part and a rolling assembly. During use, the paper map is arranged on the driven roller on one side of the bearing seat in a sleeved mode in a rolled state, the paper map is unfolded, the free end of the paper map is connected with the driving roller of the rolling assembly, and the lighting piece can light the unfolded part of the paper map through the bearing face made of the light-transmitting material. The driving roller can be rotated to pull the rolled paper map to rotate, so that the rolled paper map is continuously pulled to be unfolded, the unmarked part is displayed on the bearing surface, the marked part on the bearing surface is rolled to the driving roller, and therefore comprehensive display of a long map is achieved. And therefore, the function of assisting the staff to carry out labeling operation is realized.

The invention relates to the technical field of disaster emergency management and analog calculation, and relates to a dike scene rapid generation method and system based on graph calculation and topological optimization. The method comprises the following specific steps: S1, marking scene key information based on a GIS map; s2, analyzing the marked geometric data, and constructing a topological relation based on graph calculation; s3, after the topological relation is analyzed, elements needed by model calculation are extracted from the topological relation, and attributes of the elements are defined; s4, generating a rescue traffic network based on the defined element attributes and geometric information; s5, verifying the generated geometric data, the topological relation, the model elements and the traffic network; and S6, after the verification is passed, integrating all data to generate a complete simulation scene and outputting the simulation scene. According to the method, the simulation environment suitable for flood spread and breach scour calculation is rapidly constructed by marking key information of dike, breach point and simulation range scenes and combining geometric topological relation analysis and model element definition, and efficient and reliable technical support is provided for emergency response and auxiliary decision making of dike breach disasters.

The application provides a trajectory prediction method and device, electronic equipment and storage medium. The method comprises the following steps: obtaining a model prediction trajectory of a risk obstacle target located within a preset distance range of a vehicle; obtaining a first intention corresponding to the model prediction trajectory; generating a rule prediction trajectory and a second intention of the risk obstacle target based on information of the risk obstacle target and a preset rule; and determining a final prediction trajectory of the risk obstacle target from the model prediction trajectory and the rule prediction trajectory based on the first intention and the second intention. The generation of the rule prediction trajectory and the model prediction trajectory is two independent steps, the intentions are not confused, the two trajectories only have a replacement relationship and no fusion relationship, the rule does not directly modify the model prediction trajectory, and controllability is strong. In addition, the scene does not need to be recognized, the map does not need to be labeled, and the specialized model does not need to be used, so that the development, training and deployment costs are not consumed, and only the deep learning model needs to be continuously iterated to improve the upper limit of the model.

1. Name of the product in this design: Electronic device with graphical user interface of map annotation service center software. 2. Intended use of this design: for use in an electronic device. 3. The key design feature of this product lies in its graphical interface. 4. The image or photograph that best illustrates the design's key points: the front view. 5. Description of the changing states of the graphical user interface: The main view is the product homepage, showing the initial interface of the map annotation service center software; clicking any "Click to Annotate" button in the main view leads to the changing state diagram 1; clicking the "Next" button in changing state diagram 1 leads to the changing state diagram 2; clicking the "Pay and Annotate" button in changing state diagram 2 leads to the changing state diagram 3; after scanning the code to pay in changing state diagram 3, the system enters the changing state diagram 4. Attached is Expanded State Diagram 1, corresponding to the main view; Expanded State Diagram 2, corresponding to the changed state diagram 1.

One variation of a method for detecting and visualizing objects within a space includes: retrieving a map of the space annotated with known locations of target anchor objects and regions in the space; accessing a set of images annotated with object types and locations of objects captured by a set of sensor blocks; projecting the set of images onto the map to form a visualization representing objects in the space based on known locations of the set of sensor blocks; isolating a target anchor object at a known location in a region of the visualization; detecting a mutable object at a location in the region; calculating an offset distance between the location and the known location; and, in response to the offset distance exceeding an offset distance threshold, highlighting the mutable object in the visualization as a deviation; and generating a notification to investigate the mutable object in the region.

This document describes various examples of feature recognition models for autonomous and / or semi-autonomous systems and applications. The systems and methods described here can use one or more trained machine learning models to automatically generate map-like representations of traffic features, such as road markings and / or road edges. The one or more models can, for example, take as input an image depicting at least a section of a map showing one or more traffic features along with one or more references to points associated with those traffic features, as represented by the image.Based at least on the processing of the inputs, one or more models can generate and / or output data representing additional points associated with one or more traffic features, and / or a heatmap representing one or more lines depicting one or more traffic features. This output data can then be used to determine the one or more representations of the one or more traffic features for annotating the map.