3119 results about "Parking space" patented technology

The invention discloses a non-continuous vehicle illegal parking detection method and a non-continuous vehicle illegal parking detection system fusing multiple terminals. The method comprises the following steps: acquiring pictures of the same area shot by terminals carried on different devices in different time periods and on different routes, so as to obtain a plurality of non-continuous pictures; performing spatial-temporal clustering and correction, positioning a vehicle by using a static landmark extraction technology, determining a vehicle area, and constructing position fingerprints for cross-time comparison to determine whether the vehicle is in a static state; wherein on the basis of the corrected discontinuous picture, multi-view information fusion is carried out, so that complete scene description information is fused; when the vehicle is in a static state, determining a parking space area and environment characteristics; judging whether the vehicle has illegal parking behaviors or not; if yes, subdividing illegal parking types of the vehicles; and creating a structured illegal parking report. By implementing the method provided by the invention, comprehensive and efficient monitoring of different types of illegal parking behaviors can be realized, and meanwhile, the accuracy and reliability of monitoring data are ensured.

The invention relates to the technical field of charging parking space guiding control, and particularly discloses a parking space charging reservation and intelligent guiding method, device, equipment and medium, and the method comprises the steps: obtaining vehicle battery state data and a user reservation time window through an Internet of Things terminal; synchronously acquiring charging pile state data, real-time traffic flow data and power grid load information in the parking lot; fusing the obtained multi-source heterogeneous data based on a federated learning framework, constructing a dynamic charging demand prediction model, and predicting charging pile occupancy rate distribution in a preset time period by using a space-time diagram convolutional network; through the combination of the dynamic charging demand prediction model and the space-time diagram convolutional network, the occupancy rate distribution of the charging piles is accurately predicted, the scheduling strategy of the charging piles is adjusted in real time, the problem of unreasonable resource allocation is avoided, and the waiting time of a user is shortened; the application of the quantum genetic algorithm optimizes the matching process of the charging pile through global optimal solution search, thereby ensuring the balance of the power grid load and the rationality of the charging strategy.

The invention discloses a method and system for cooperatively positioning a vehicle through a door lock, and the method comprises the steps: obtaining and dynamically updating a neighbor door lock list through the detected door lock of the vehicle according to the broadcast and scanning data of a Bluetooth tag on a moving vehicle; according to the periodic detection report of the door locks on the vehicle and the global analysis of the management system, the cooperative timers of the related door locks are synchronized, and timing management for preventing repeated triggering is implemented; according to the response of the obtained neighbor door lock which initiates multicast query after the collaborative timer expires, the door lock which initiates the query verifies whether all responders are in the neighbor list, so as to judge whether the vehicle is stably parked; and according to the vehicle parking information confirmed by the door lock, the management system updates the global state and sends a parking position notification to the owner. According to the embodiment of the invention, accurate and low-misjudgment judgment of the parking state of the vehicle can be realized, and the reliability and real-time performance of vehicle positioning management are improved by means of global state synchronization.

The invention relates to the technical field of automatic driving, and discloses a parking assisting method and system for automatic driving. The method comprises the following steps: cascading and splicing a first fisheye image acquired by a main camera in a vehicle body and a second fisheye image acquired by a slave camera to obtain a panoramic image; performing parking space boundary identification and obstacle analysis on the panoramic image to obtain parking space boundary information and obstacle position information, and synchronously performing distance calculation on a radar echo signal of an ultrasonic sensor to obtain distance measurement data; and a parking environment map is created according to the parking space boundary information, the obstacle position information and the distance measurement data, path planning is carried out based on the parking environment map, a parking execution instruction is obtained, and the parking execution instruction is used for vehicle parking auxiliary control. According to the method, the view coverage range and the flexibility of the observation angle are expanded, and the execution precision and safety of parking auxiliary control are improved.

The embodiment of the invention provides a vehicle parking method and system and a vehicle. The method comprises the steps that initial multi-modal data of the environment where the vehicle is located is obtained; performing alignment processing on the initial multi-modal data to obtain target multi-modal data; calling a target model to carry out collaborative analysis on the target multi-modal data to obtain an information identification result of the vehicle and an information identification result of the environment; on the basis of the information identification result of the vehicle, the information identification result of the environment and track information matched with current execution parameters of the vehicle, a to-be-parked parking space of the vehicle and a driving path of the vehicle to be driven to the to-be-parked parking space are determined from the environment, and the current execution parameters are used for representing execution performance of an actuator in the vehicle; the track information is used for predicting the track of the vehicle in the moving process; and according to the driving path, the vehicle is controlled to drive to the to-be-parked space for parking. The technical problem that the parking efficiency of the vehicle is low is solved.

The invention discloses a new energy automobile charging pile parking space occupation detection and billing linkage control method, and relates to the technical field of urban public resource optimization distribution and new energy automobile charging pile parking space management. Comprising the steps of multi-source sensing and state fusion: sensing real-time occupation states, vehicle types and charging behavior states of all parking spaces in real time by using a parking space detector, an ALPR visual sensor, a Hall sensor and a charging pile state communication protocol, collecting original data, deploying edge nodes at the parking spaces, and fusing the original data in real time, outputting a unified parking space state object after fusion; original data are collected in real time through the parking space detector, the ALPR visual sensor, the Hall sensor and the charging pile state communication protocol, and through multi-dimensional behavior analysis of the parking space state, the abnormal behaviors that a fuel truck occupies a space for a long time, an electric vehicle occupies the space and is not charged, and the electric vehicle is detained after being charged can be accurately recognized; and an accurate basis is provided for subsequent charging processing and precise management.

The invention discloses a road shoulder vehicle exclusion method based on an inspection system, and relates to the technical field of intelligent transportation, and the method comprises the steps: obtaining a parking area image shot by an inspection vehicle, recognizing a vehicle target in the image, and extracting the license plate position information; based on vehicle three-dimensional feature reconstruction and space projection analysis, generating a space distribution thermodynamic diagram of the vehicle in the image coordinate system; constructing a dynamic segmentation line model, and adaptively generating a road shoulder region judgment boundary according to the parking space type and the road geometric parameters; and through a multi-target trajectory association algorithm, the berth vehicle and the road shoulder vehicle are distinguished, and the berth occupation state is output. According to the scheme provided by the invention, the spatial positioning precision and behavior judgment reliability in a complex scene can be remarkably improved, the limitations on environmental adaptability, vehicle type compatibility and time sequence continuity are broken through, and a road shoulder violation management and control solution with high robustness and full-time coverage is provided for urban traffic management.

The invention relates to the technical field of new energy automobile charging management, in particular to a new energy automobile charging pile orderly management system and method based on a WeChat applet, and the system comprises a multi-dimensional data collection module which is used for collecting the state of a charging pile, parking space occupation and power grid load data; the Internet of Things sensor group is deployed at the charging pile and is used for acquiring electrical parameters such as the state (during charging, idle charging and fault), charging power and voltage of the charging pile in real time; provided is a parking space visual monitoring device. Through combination of an interval tree data structure and a multi-target optimization scheduling model, space-time dimension dynamic management of charging pile resources is realized, the problems of reservation conflicts, resource idleness and the like in a traditional system are effectively solved, the utilization rate of the charging piles is remarkably improved, and an intelligent time period recommendation algorithm is based on user habits and a power grid load state. Users are guided to carry out peak shifting charging, balanced allocation of charging resources and power grid loads is promoted, and optimization of energy utilization efficiency is achieved.

The invention relates to the technical field of parking lot digital management, and discloses a digital twin enabling parking lot digital global management system. According to the system, a global digital twin model of a parking lot is generated, and multi-source sensing data such as parking space states, vehicle identities and environmental parameters are fused; generating a parking space distribution matrix with priorities and time windows in combination with the parking request of the user and the real-time parking space state; according to the parking space two-dimensional code hardware parameters, the digital twin model and the parking space distribution matrix, outputting a vehicle guiding path set with a timestamp; a real-time obstacle avoidance and dynamic adjustment system is constructed to generate a safe driving path set so as to dispatch vehicles; outputting a power distribution control instruction set and updating the digital twinborn model by combining the electric quantity of the energy storage unit, the power distribution network data and the safe driving path set; and finally, system knowledge evolution and end-to-end closed-loop optimization are realized through scheduling execution logs. According to the system, global efficient management of the parking lot is realized, and the parking space utilization, vehicle scheduling and energy utilization levels are improved.

The invention discloses a road section illegal parking space-time prediction system based on deep learning, and relates to the technical field of intelligent traffic management, and the system comprises a multi-source data fusion collection module, a space-time self-attention feature extraction module, a dynamic granularity parameter generation module, a space-time hybrid model prediction module and an illegal parking early warning visualization module. By collecting traffic camera video streams, vehicle-mounted sensor data, mobile phone signaling data and meteorological data in real time, comprehensive perception of the traffic environment is achieved, the multi-source heterogeneous data are mapped to a unified GIS grid after being subjected to space-time coordinate calibration, a multi-dimensional illegal parking influence factor database is constructed, and on the basis, the real-time monitoring of the illegal parking influence factor database is achieved. The space-time self-attention feature extraction module performs efficient space-time feature extraction on multi-source data by using a space-time diagram self-attention model, generates feature vectors with space-time relevance, and solves the problems of single data and insufficient feature extraction in a traditional method.

The invention relates to an intelligent port cargo scheduling method based on the Internet of Things, and the method comprises the steps: collecting cargo state information, equipment position coordinates, operation progress data and environment parameters in real time through Internet of Things sensor nodes disposed on a quay crane, a container truck, a storage yard sling and a cargo carrier, and fusing a port GIS map and a berth plan based on the real-time collected data, and establishing a multi-objective optimization model with maximization of the quay crane-container truck-storage yard cooperative efficiency as an objective and minimization of equipment conflict avoidance and path overlap as constraint conditions, and dynamically activating or sleeping storage yard operation partitions and adjusting the number of container truck marshalling according to the obtained storage yard congestion prediction index and the parking space vacancy rate.

The invention relates to the technical field of machine learning, and particularly discloses an intelligent parking guidance and reverse vehicle searching system based on multi-source heterogeneous data fusion. The system comprises a data perception fusion layer, a dynamic prediction decision-making layer and a user service interaction layer, realizes multi-step advanced probability prediction and dynamic optimal path planning of a parking space state through fusion of geomagnetic detection, video identification, payment flow, traffic situation and activity information, and realizes the optimal path planning of the parking space state based on multi-mode induction and live-action AR reverse vehicle searching guidance. And the parking efficiency and the user experience are improved.

The invention relates to a charging parking space intelligent occupation management linkage control method and system based on the Internet of Things, and belongs to the field of charging parking space management.The method comprises the steps that the state of a charging pile, the state of a parking space lock and occupation information are collected through Internet of Things equipment, and a dynamic parking space resource pool is constructed; based on knowledge graph semantic reasoning, matching parking spaces meeting vehicle type adaptation and available time periods, and combining historical late data of a user to set elastic reservation retention duration; the identity legality is verified by comparing the information of the reserved vehicle with the information of the actual parking vehicle; and when the charging pile is controlled to start charging and the parking space lock is unlocked, the block chain is synchronously associated to generate the transaction voucher, and the transaction record uploading is completed based on the voucher after the charging is finished, so that the technical effects of efficient matching and dynamic management of the charging parking space resources are realized.

The invention discloses a parking lot virtual green wave guiding method and related equipment. The core is to construct a space-time resource map, plan a path according to the space-time resource map, reserve a time window to form a virtual green wave band, issue an instruction to a vehicle terminal and an intelligent barrier gate, monitor vehicle position deviation, and trigger local re-planning if a threshold value is exceeded. According to the scheme, the defects in the prior art are accurately overcome, global space-time resource overall planning is achieved through a space-time resource map, an exclusive time window is reserved for vehicles, multi-vehicle path conflicts are eliminated from the source, and the defects of lack of global view and active scheduling are overcome; static road network navigation is replaced by a space and time coordinated virtual green wave band, vehicles are actively guided to pass orderly, microscopic traffic congestion is effectively solved, and the in-field passing efficiency is greatly improved; through a real-time monitoring and local re-planning mechanism, emergency situations such as vehicle faults can be rapidly handled, congestion diffusion is avoided, traffic flow stability is guaranteed, and finally seamless and non-stop passing of the vehicle from an entrance to a parking space is achieved.

The invention provides a new energy vehicle parking charging scheduling management method and system, and relates to the technical field of new energy charging management, and the method comprises the steps: receiving a charging reservation request sent by a new energy vehicle, including a vehicle identification code, a battery remaining capacity and an expected charging time period, obtaining a vehicle charging characteristic parameter, and combining with environment temperature correction; and the actual required charging time is accurately calculated. And on the basis of the charging duration, the expected charging time period and the charging pile operation state, a dynamic scoring method is adopted, a comprehensive score is calculated through duration matching score and reliability score weighting, and an optimal charging pile is selected for distribution according to a scoring result. According to the method, a weighted dynamic scoring method of the duration matching score and the reliability score is adopted, the user demand, the operation state of the charging pile and the environmental influence are comprehensively considered, the optimal distribution of the charging pile resources is ensured, and the overall operation efficiency and the service quality of the charging station are remarkably improved.

The invention relates to the technical field of charging and battery swapping, and discloses an electric truck battery swapping station pre-guiding accurate parking system and method, and the system comprises the ground, a battery swapping station, a battery swapping shed, an electric truck, a laser guiding system, a radar image system, and a parking line. The laser guiding system comprises a laser projector and an adjustable device which are installed on the top of a battery changing area of the battery changing station. The radar image system comprises a radar device installed below the head of the electric truck and a central control display device in the cab of the electric truck, the electric truck can more quickly and accurately drive into the battery replacement area of the battery replacement station through the pre-guiding accurate parking system, the repeated adjustment time caused by inaccurate parking position is reduced, and the accuracy of the electric truck is improved. Therefore, the overall efficiency of battery replacement is greatly improved, the battery replacement station can provide battery replacement service for more electric trucks in unit time, the occurrence rate of battery replacement faults caused by parking deviation is reduced, and the success rate and reliability of battery replacement operation are improved.

The application discloses a kind of unmanned vehicle accurate parking methods of port crane scene, through the setting of desired accurate parking position, adjust the distance and direction of vehicle, guide vehicle accurate parking, through the position that template map has saved desired accurate parking, and the plane parameter of crane, improve the accuracy of vehicle stop, can improve the efficiency of loading and unloading box operation, increase the economic benefit of single vehicle unit time, simultaneously, through laser radar, the point cloud data of crane can be directly scanned and obtained, realize the accurate parking of port crane scene, do not need to make any modification to crane equipment and install any equipment, there is no special requirement to crane structure, size etc., with good universality, the characteristics such as low introduction cost.

The invention specifically relates to a smart parking lot traffic management system based on traffic Internet of Things, and relates to the technical field of smart traffic and Internet of Things. A data processing and fusion module; a congestion prediction module; a prediction optimization module; and an induction information generation and release module. According to the invention, through multi-dimensional data acquisition, fusion and model optimization, accurate pre-judgment and dynamic adaptation of parking lot congestion are realized; the congestion prediction module constructs a multi-dimensional feature system of stagnation degree, unit average delay degree and occupancy degree, covers core inducements of vehicle retention, parking efficiency, resource mismatch and the like, combines historical data optimization factors and k value dynamic adjustment, and enables the prediction model to continuously adapt to changes of parking lot vehicle types, user habits and the like. Passive response of congestion treatment is upgraded to active prevention, invalid wandering of vehicles and lane congestion are reduced, the parking lot passing efficiency and the parking space turnover rate are remarkably improved, and the operation cost is reduced.

The embodiment of the invention provides a parking-out control method of a vehicle, electronic equipment and a computer readable storage medium, and the method comprises the steps: responding to a triggering operation for a parking-out function of the vehicle, and obtaining the environment feature information of the environment where the current parking space of the vehicle is located, and the parking space feature information of the parking space; based on the environment feature information and the parking space feature information, determining parking scene information of the vehicle; based on the parking-out scene information and expected driving information after the vehicle is parked out, a target orientation and a target position after the vehicle is parked out are determined, and the expected driving information is used for representing a driving destination after the vehicle is driven out of the parking space; determining a parking track of the vehicle based on the parking scene information, the target orientation, the target position and the position of the parking space; and according to the parking track, the vehicle is controlled to execute parking operation. The technical problem that the automatic parking-out function of the vehicle in a special scene is difficult to meet the actual driving requirement of the vehicle is solved.

Embodiments of the present application disclose an automatic parking control method and device and a computing device. The method comprises: acquiring first position information of a position where a vehicle is located, a vehicle inclination angle, second position information of a target empty parking space, and direction information; judging whether the vehicle is inclined relative to the target empty parking space based on the vehicle inclination angle and the direction information of the target empty parking space; if the vehicle is not inclined relative to the target empty parking space, determining a lateral movement distance and a lateral movement direction of the vehicle according to the first position information and the second position information; and controlling the vehicle to move laterally into the target empty parking space based on the lateral movement distance and the lateral movement direction, which helps to improve the efficiency of automatic parking.

The invention relates to the technical field of intelligent parking management, and discloses a curb parking dynamic charging and fee evasion prevention and control method based on multi-dimensional data fusion, which comprises the following steps: a data fusion reconstruction step: receiving a video stream, sensing a parking space state and reporting data through mobile inspection, performing fusion processing through space-time alignment and a confidence decision algorithm, and obtaining a data fusion result; outputting a standard parking event sequence; a dynamic charging decision-making step of matching a charging strategy model including time-phased elastic rate parameters according to the time-space attribute of the event sequence, calculating the cost and verifying the parking rights and interests in real time, and generating a parking order; and a fee evasion risk real-time prevention and control step: constructing a vehicle behavior portrait feature vector based on the event sequence and the historical order, obtaining a real-time risk level through a pre-trained risk grading model, and triggering a cascade response disposal action according to the real-time risk level, including exit interception and recovery of a high-risk vehicle. According to the invention, the charging accuracy is improved, and the rate dynamic adjustment and the active and accurate prevention and control of the fee evasion behavior are realized.

The invention relates to a park intelligent vehicle scheduling method and system, and the method comprises the steps: receiving vehicle reservation information, generating a vehicle parking space and elevator preliminary distribution scheme based on the reservation information and a current resource occupation state, carrying out the adjustment and optimization of the preliminary distribution scheme of a plurality of vehicles at a preset scheduling moment, and obtaining an updated distribution scheme, and when the vehicle arrives at the park, the distribution result of the vehicle is corrected based on the updated distribution scheme and the real-time resource occupation state. The system comprises a scheduling server, a plurality of data acquisition terminals which are respectively arranged at the entrance of a park, parking spaces, elevators and parking spaces, and a communication module which is connected with the scheduling server and the data acquisition terminals. By implementing the scheme, the preliminary allocation scheme is calculated in combination with the reservation information and the current resource occupation state, the multi-vehicle allocation scheme is adjusted at the preset scheduling moment, and the final allocation scheme is generated based on the real-time state when the vehicles arrive, so that the capability of coping with arrival time fluctuation and temporary operation change is improved.

A method may include, at a control system, receiving a trip request specifying an origin boarding zone and a destination boarding zone, determining a path for the trip request, the path extending from the origin boarding zone and along at least a portion of a trunk lane of a roadway system, assigning the trip request to a vehicle, determining, based at least in part on a location of a parking spot where the vehicle is parked at the origin boarding zone, an estimated transit duration of the vehicle from the parking spot to an entrance to the trunk lane, selecting, based at least in part on the estimated transit duration, a moving position-target from a set of candidate moving position-targets, and causing the vehicle to travel from the parking spot to the trunk lane and travel along the portion of the trunk lane by following the selected moving position-target.

The invention relates to the technical field of intelligent navigation, and discloses an indoor and outdoor integrated parking space navigation method and system based on reinforcement learning, and the indoor and outdoor integrated parking space navigation method based on reinforcement learning comprises the steps: carrying out the data collection and preprocessing of a multi-source sensor; identifying and switching indoor and outdoor scenes; high-precision positioning and mapping are carried out; predicting and evaluating the state of the parking space; reinforcement learning decision optimization; generating and adjusting real-time navigation; the indoor positioning precision is improved, the navigation response speed is increased, the path planning success rate is increased, the user experience is improved through a visual multi-mode man-machine interaction interface, a perfect safety monitoring and exception handling mechanism is established, the safety and reliability of the navigation process are ensured, and the navigation efficiency is improved. And the system can keep stable and efficient performance in long-term operation.

The invention relates to a hospital vehicle parking scheduling method and device, equipment and a medium. According to the method, a data association model of a doctor-seeing type and a historical parking time length is established, a vehicle doctor-seeing type is dynamically matched to generate a personalized parking time limit, a parking priority score is adjusted in a linkage manner by combining real-time monitoring and an overtime punishment mechanism, and accurate matching of parking resources and medical demands is realized based on a time-phased differential allocation strategy, so that the parking efficiency is improved. The rationality and turnover efficiency of parking space distribution are effectively improved, and meanwhile, the duration prediction accuracy is continuously optimized through a closed-loop feedback mechanism, so that the comprehensive technical effects of relieving peak congestion, balancing resource utilization and constraining illegal behaviors are finally achieved.

The invention discloses a design method for optimizing urban scenic spot parking facility layout, which relates to the field of parking layout design, and comprises the following steps: acquiring emergency data around a scenic spot in real time, analyzing emergency types and geographic coordinates, and generating a structured data set which comprises fence boundary coordinates and event intensity factors; based on the structured data set, a gradient electronic fence is generated on a GIS platform, fence boundary coordinates and event intensity factors are input into a pre-constructed parking demand prediction model for parameter recombination, a parking resource demand prediction map is output, a response strategy is generated according to the electronic fence range and the parking resource demand prediction map, and a parking resource demand prediction map is obtained. A scheduling instruction set is formed, the identity of a reserved vehicle is verified through a V2X vehicle-road cooperation mechanism, vehicle physical parameters are matched in combination with available parking space resources in the scheduling instruction set, and a three-dimensional navigation packet is generated; accurate adaptation of resource supply is achieved through a spatial topology matching algorithm, and the emergency response period is shortened.

The invention discloses a parking space state monitoring method based on multi-sensor fusion. The parking space state monitoring method comprises the steps of 1, collecting multi-modal sensor data; 2, preprocessing the multi-modal sensor data to generate a standardized multi-modal data set; step 3, constructing an improved SwinFusion model, performing multi-modal feature extraction on the standardized multi-modal data set, and generating an asynchronous attention feature tensor sequence; 4, multi-scale feature decoding and space-time mapping are executed, and a feature mapping graph and an occupation probability graph are generated; 5, based on the feature mapping graph and the occupancy probability graph, executing state judgment and outputting a parking space state label; step 6, generating a real-time parking space state visual graph; and step 7, collecting an edge terminal identification result and sensor feedback data, and executing incremental updating on the improved SwinFusion model. According to the invention, the multi-sensing data fusion capability and the parking space state identification accuracy and robustness in a complex environment are improved.

An automatic charging device, arranged between two parking spaces. The automatic charging device comprises: charging guns (1); a gun receiving device (2), comprising two gun seats (21), wherein the gun seats are used for placing the charging guns; a two-section connector, wherein one end of the two-section connector is connected to the charging guns, the other end of the two-section connector is connected to a mechanical arm (3), and the two-section connector can be separated; and the mechanical arm, used for being docked with the charging guns in the gun receiving device by means of the two-section connector and then controlling the charging guns to automatically charge vehicles on both sides. The automatic charging device is arranged between two parking spaces, and the mechanical arm can automatically provide the charging gun in the gun receiving device to a left vehicle or a right vehicle on the basis of a charging port position, so that a single automatic charging device can serve parking spaces on both sides, thereby maximizing the utilization of the charging device, and allowing vehicles at different charging port positions, whether parked head-in or tail-in, to be charged.

The utility model discloses a plane moving double-car parking and taking stereo garage, which belongs to the technical field of stereo garages and comprises a steel structure frame, the steel structure frame comprises a plurality of layers, each layer of steel structure frame is provided with a transverse moving roadway, and a plurality of parking spaces are arranged on the steel structure frame on two sides of the transverse moving roadway. A vertical lifting roadway is arranged in the steel structure frame, a lift car driven by a lifting power device is vertically installed in the vertical lifting roadway in a sliding mode, and a first carrier driven by a first carrying power device and a second carrier driven by a second carrying power device are installed in the lift car in a sliding mode. Transverse moving trolleys are installed in the positions, located in the transverse moving roadways, in the steel structure frame in a sliding mode, and the ground layer of the steel structure frame is provided with a vehicle entrance and exit allowing two vehicles to enter and exit at the same time. The three-dimensional garage solves the technical problem of low vehicle access efficiency in a plane moving type three-dimensional garage, and is widely applied to three-dimensional garages.

Provided is a parking assistance device including a captured image acquisition unit imaging a road surface around a vehicle and an end detector detecting an end of a ground object on the road surface within a detection area in the captured image. A position calculator calculates position information indicating a positional relationship of the end of the ground object. A boundary line determiner determines whether or not a ground object having the end is a boundary line that defines a parking slot for the vehicle. A removal unit determines whether or not a rear end of a ground object determined as the boundary line by the boundary line determination unit is included in a removal range, determines that a ground object determined as the boundary line is not the boundary line when the rear end is included in the removal range, and excludes the ground object from boundary lines.