CN113192199A - Three-dimensional vision-based storage yard anti-collision system - Google Patents
Three-dimensional vision-based storage yard anti-collision system Download PDFInfo
- Publication number
- CN113192199A CN113192199A CN202110610685.1A CN202110610685A CN113192199A CN 113192199 A CN113192199 A CN 113192199A CN 202110610685 A CN202110610685 A CN 202110610685A CN 113192199 A CN113192199 A CN 113192199A
- Authority
- CN
- China
- Prior art keywords
- bridge crane
- storage yard
- artificial intelligence
- field bridge
- dimensional
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/36—Input/output arrangements for on-board computers
- G01C21/3626—Details of the output of route guidance instructions
- G01C21/3635—Guidance using 3D or perspective road maps
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Computer Graphics (AREA)
- Control And Safety Of Cranes (AREA)
Abstract
The invention belongs to the field of artificial intelligence algorithms, in particular to a three-dimensional vision-based storage yard anti-collision system, which aims at the problem that the conventional storage yard anti-collision system only uses laser radars, a single laser radar has a large visual angle blind area, and a plurality of expensive laser radars have high cost and cannot give consideration to both cost and efficiency, and provides the following scheme, wherein the system comprises two groups of camera arrays, an industrial control device, a field bridge crane and an artificial intelligence controller, the camera arrays are arranged at the top of the field bridge crane, an electric room is arranged in the field bridge crane, the industrial control device is arranged in the electric room, the artificial intelligence controller is connected with the two groups of camera arrays, the invention utilizes a digital camera to shoot different-angle pictures of a storage yard below the field bridge crane or a shore bridge crane, and then uses a multi-view three-dimensional reconstruction algorithm and an artificial intelligence algorithm to generate an electronic virtual map of the whole storage yard below the field bridge crane, the container dislocation of the adjacent berths can be better protected, and the cost performance is better.
Description
Technical Field
The invention relates to the technical field of artificial intelligence algorithms, in particular to a three-dimensional vision-based storage yard anti-collision system.
Background
The storage yard anticollision system, also called as storage yard anti-hitting bowling system (LCPS for short), is mainly used for three functions during the operation of automatic or semi-automatic container port and wharf slings, and has the functions of car and cart direction anticollision protection: in the advancing direction of the trolley, if an empty hanger or a position with a load of the hanger is lower than an obstacle, the LCPS calculates the horizontal distance between the obstacle and the load (possibly no load) of the hanger according to the current position of the trolley read by the PLC, limits the moving speed of the trolley when the trolley is close to the current position according to the distance, automatically stops the trolley when the trolley is close to the current position, gives out the reason of emergency stop and suggests the minimum distance for rising, only when an operation or automatic control system improves the load of the hanger on the obstacle, the collision of the trolley is avoided, the obstacle detected by the LCPS needs to realize the collision prevention function of the hanger and the obstacle of a storage yard adjacent to the direction of the trolley, for example, when the storage yard adjacent to the direction of the trolley is staggered or the trolley inclines, the containers of the adjacent storage yard can protrude into the storage yard, and the potential safety hazard of the running of the trolley is caused; planning an optimal path: on the basis of the functions, the LCPS can be used for intelligently and optimally planning the path of the whole container, and is divided into a basic function, an advanced function and a high-order function according to the degree of automation, the LCPS in the basic function can provide the height information of the obstacle at a target position to a semi-automatic system, the distance close to the top of a task box is displayed in real time in a main picture of a driver cab by comparing with a lifting height value so as to be convenient for a driver to determine the falling distance, meanwhile, the LCPS can calculate the running route of a parabolic trolley lifting appliance for the specified target container position and give an operation suggestion and an operation limitation, namely when the trolley is at different positions and the lifting appliance is at different heights, the LCPS limits the running speeds of the trolley and the lifting appliance so as to realize intelligent soft landing, the automation degree of a control system in the advanced landing function is higher, and then the parabolic running route is provided, the system can directly and automatically operate, an operator only needs to monitor the system, namely, the lifting appliance automatically moves to a lower height above a target container position in a parabolic manner, the LCPS system in a high-order function can intelligently analyze the stacking condition on a storage yard or a cargo ship and the storage yard and transmit the stacking condition to the TOS system to give a selection suggestion of the target container position, and the operator can conveniently reset the target container position to any new storage yard on the storage yard or the cargo ship through an interactive interface;
because of the lack of effective technical means in the past, in an outdoor complex illumination environment, a plane image shot by a camera cannot be accurately and quickly converted into three-dimensional point cloud, so that the traditional storage yard anti-collision system independently uses a laser radar, utilizes a laser scanning ranging principle to obtain real-time data on one scanning line below, and regards the single-line data as the condition of height distribution of a lower container to plan a movement path of a lifting appliance so as to achieve the anti-collision purpose, but in practice, the height distribution mode of the containers below the lifting appliance in the storage yard has hundreds of possible situations after arrangement and combination, and a single laser radar has a large visual angle blind area and can not be detected, and the situation that the containers in the adjacent storage yard in the direction of a large vehicle are staggered causes protection loopholes, although the loophole compensation can be performed by increasing the number of the laser radars, however, because the data of the lidar is not intuitive, a developer needs to pay huge time and management cost, manual debugging and optimization of synthesis of multiple radar data are required, and in addition, the scanning range of the cheap lidar is limited, the lidar is easily interfered by outdoor complex weather such as rain, snow, haze and the like, so that the LCPS using the lidar in the prior art needs to be combined and used, and the cost and the efficiency cannot be considered at the same time.
Disclosure of Invention
The invention aims to solve the problems that in the prior art, all storage yard anti-collision systems independently use laser radars, a single laser radar has a large visual angle blind area, and a plurality of expensive laser radars have high cost, so that cost and efficiency cannot be considered at the same time, and provides a storage yard anti-collision system based on three-dimensional vision.
In order to achieve the purpose, the invention adopts the following technical scheme:
the three-dimensional vision-based storage yard anti-collision system comprises two groups of camera arrays, industrial control equipment, a yard bridge crane and an artificial intelligent controller, the camera array is arranged at the top of the field bridge crane, an electric room is arranged in the field bridge crane, the industrial control equipment is arranged in the electric room, the artificial intelligent controller is connected with the two groups of camera arrays, the electric room is internally provided with a field bridge crane PLC, the industrial control equipment is connected with the field bridge crane PLC, the camera adopted by the camera array is a digital camera which is used for continuously shooting the stacks in the container yard downwards, and sending the shot multi-view high-definition photo group to an artificial intelligence controller, wherein the artificial intelligence controller is used for carrying out high-precision digital three-dimensional reconstruction on the photo group to generate an electronic virtual map of the whole lower storage yard, and then planning the load path of the lifting appliance on the electronic virtual map so as to generate control parameters of the lifting appliance and the trolley.
Preferably, the high-precision digital three-dimensional reconstruction process is as follows: the method comprises the steps of firstly identifying corners of a container as feature points by using a deep convolutional neural network instance segmentation algorithm, obtaining instance label numbers of the feature points, forming matching points by using the feature points with the same label numbers in every two pictures, namely the feature points of the same corner of the same container, carrying out iterative computation on the matching points by using the optimization computation without baseline constraint to obtain an intrinsic matrix, and converting every two-dimensional images into a piece of three-dimensional point cloud with textures by using the intrinsic matrix.
Preferably, the spreader load path planning process is as follows: firstly, obtaining coordinates of each corner of a container below by using a pattern recognition algorithm, using the coordinates as a control point row, then calculating a plane parabolic equation which is higher than all control points and has the shortest length as possible by using an optimization method, finally cutting off the part of the parabola which is higher than the ultimate rise height of the lifting appliance, and using a horizontal straight line segment for substitution to obtain the final lifting appliance load motion track which has the advantages of no collision with stacking, lower running time and lower lifting appliance load motion track.
Compared with the prior art, the invention has the beneficial effects that:
the invention relates to a hanger load anti-collision system for operation in a container yard, which utilizes a digital camera to shoot different angle pictures of the yard below a yard crane or a shore crane, then uses a multi-view three-dimensional reconstruction algorithm and an artificial intelligence algorithm to generate an electronic virtual map of the whole yard below the yard, and then carries out parabolic container path planning on the electronic virtual map, thereby realizing the purposes of preventing the occurrence of container stacking accidents caused by collision and scattering of hangers and improving the container operation efficiency.
Drawings
Fig. 1 is a schematic diagram of a connection structure of components of a three-dimensional vision-based yard collision avoidance system according to the present invention;
fig. 2 is a schematic view of a workflow diagram of a three-dimensional vision-based yard collision avoidance system according to the present invention;
fig. 3 is a schematic operation diagram of the three-dimensional vision-based yard collision avoidance system according to the present invention;
fig. 4 is a schematic operation diagram of the three-dimensional vision-based yard collision avoidance system according to the present invention;
fig. 5 is a three-dimensional reconstruction effect diagram of a storage yard electronic virtual map of the three-dimensional vision-based storage yard anti-collision system provided by the invention.
In the figure: the system comprises a camera array 1, an industrial control device 2, a bridge crane 3, a camera unit 4 and a shore bridge crane 5.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Example one
Referring to fig. 1-5, the three-dimensional vision-based storage yard anti-collision system comprises two groups of camera arrays 1, an industrial control device 2, a field bridge crane 3 and an artificial intelligence controller, wherein the camera arrays 1 are arranged at the top of the field bridge crane 3, an electric room is arranged in the field bridge crane 3, the industrial control device 2 is arranged in the electric room, the artificial intelligence controller is connected with the two groups of camera arrays 1, a field bridge crane PLC is arranged in the electric room, the industrial control device 2 is connected with the field bridge crane PLC, a camera adopted by the camera arrays 1 is a digital camera, a shot multi-view high-definition photo group is sent to the artificial intelligence controller, the artificial intelligence controller carries out high-precision digital three-dimensional reconstruction on the photo group, an electronic virtual map of the whole lower storage yard is generated, then, a hanger load path planning is carried out on the electronic virtual map, and therefore control parameters of hangers and trolleys are generated.
In this embodiment, the high-precision digital three-dimensional reconstruction process is as follows: the method comprises the steps of firstly identifying corners of a container as feature points by using a deep convolutional neural network instance segmentation algorithm, obtaining instance label numbers of the feature points, forming matching points by using the feature points with the same label numbers in every two pictures, namely the feature points of the same corner of the same container, carrying out iterative computation on the matching points by using the optimization computation without baseline constraint to obtain an intrinsic matrix, and converting every two-dimensional images into a piece of three-dimensional point cloud with textures by using the intrinsic matrix.
In this embodiment, the spreader load path planning process is as follows: firstly, obtaining coordinates of each corner of a container below by using a pattern recognition algorithm, using the coordinates as a control point row, then calculating a plane parabolic equation which is higher than all control points and has the shortest length as possible by using an optimization method, finally cutting off the part of the parabola which is higher than the ultimate rise height of the lifting appliance, and using a horizontal straight line segment for substitution to obtain the final lifting appliance load motion track which has the advantages of no collision with stacking, lower running time and lower lifting appliance load motion track.
Example two
Referring to fig. 1-2, a three-dimensional vision based yard anti-collision system comprises an artificial intelligence controller and a digital camera, wherein the digital camera is arranged on a beam above a yard crane or a shore crane in a multi-camera array or moving track mode, shoots a multi-view high-definition photo group stacked in a container yard right below and sends the multi-view high-definition photo group to the artificial intelligence controller, the artificial intelligence controller is arranged in an electric room of the yard crane or the shore crane, the digital camera and the artificial intelligence controller are connected after being converted into optical fibers through a network cable, the artificial intelligence controller is connected with a field crane or a shore crane PLC, if the digital camera is arranged in a camera array mode, the container at any position in the yard is ensured to be shot by at least one pair of adjacent digital cameras with the same focal length, namely, the container is covered in a public field of view, and if the digital camera is arranged in a moving track mode, the camera continuously shoots a video to cover all containers in a moving range, finally, images of any container are shot by two cameras with different installation positions or in different frames of the same video, so that at least two image pairs with larger parallax errors are obtained;
in the embodiment, after obtaining a parallax image pair, four corners of all containers in each image are found by using a deep neural network example segmentation algorithm to serve as important labeled feature points, next, a pair of feature points with the same label in the image pair are regarded as matching points of the same corner in images with different views, then, a single-camera internal parameter and an optimized multi-view image construction equation which are calibrated in advance are used for calculating to obtain a binocular intrinsic matrix of each image pair, the intrinsic matrix is provided, all pixels in a common area in paired images can be matched under the condition based on gray scale feature and base line constraint, the paired images are converted into a piece of three-dimensional point cloud with color texture, the sequence of each point cloud is determined according to the installation mode of a camera array or the moving sequence of the camera, and because each point cloud has a common part, therefore, the next piece of point cloud can be spliced to the previous piece of point cloud continuously, and finally the point cloud of the whole storage yard is finished, namely the required storage yard electronic virtual map;
in the implementation, after the electronic virtual map is provided, in order to avoid omission, three-dimensional corner coordinates of all containers are calculated again, which are potential collision points needing to be bypassed, the three-dimensional coordinates are projected onto a two-dimensional plane formed by descending of a mobile lifting appliance of a field bridge crane or a shore bridge crane trolley, a plane parabola fitting algorithm with constraint is further implemented to obtain a parabola equation, and finally, a part of the parabola equation, which is higher than the ascending limit of the lifting appliance, is flattened into a straight line segment to complete path planning once, preferably, when the total path of the planned parabola and the straight line path is smaller than that of the system without the electronic virtual map, a driver can visually observe operation paths of straight line ascending, straight line translation and straight line descending, and the phenomenon that the lifting appliance loads are stacked in a bowling shape due to dislocation possibly caused by the absence of the system or other imperfect systems is avoided, therefore, the safety is ensured and the operation efficiency is improved, and the embodiment shows that the sling load anti-collision system is respectively arranged on the site bridge crane and the shore bridge crane and is used for preventing container accidents in collision fields caused by misoperation or poor observation due to the fact that the sling with or without a container is used when ground container storage yards and container on-wheel storage yards are operated in the operation process.
EXAMPLE III
Referring to fig. 3, the three-dimensional vision based anti-collision system for the storage yard comprises an industrial control device 2 and a camera array 1, wherein the camera array 1 for shooting downwards is arranged on a top beam of the whole yard crane 3, the camera array 1 consists of 22 digital cameras (relative to the traveling direction of the trolley), 11 cameras on the left side and the right side are respectively arranged, the left side and the right side are completely symmetrical, the 11 digital cameras on the left side are taken as an example, the 11 digital cameras on the left side are divided into two groups, one group is 5 telephoto group cameras, a longer focal length is used, containers with first and second layer heights and ground marks in the storage yard are shot from front to back (relative to the traveling direction of the trolley), the other group is 6 close-shot group cameras, a shorter focal length is used, containers with third, fourth and fifth layer heights are shot from front to back, the same group of cameras in the two groups are half of the long side of a visual field when the closest interesting object is shot, so that the installation ensures the embodiment, containers at any height and position, in the current stall of the yard and at the current position of the yard bridge crane, can be covered by the common view field of at least two cameras in the same group, and further the multi-view three-dimensional reconstruction algorithm is suitable for the multi-view three-dimensional reconstruction algorithm.
In the implementation, the industrial control equipment 2 is installed in an electric room of a field bridge crane 3, the industrial control equipment 2 uses the optical fiber camera array 1 to receive operation field data, and the industrial control equipment 2 is connected with a field bridge crane PLC in the electric room by a network cable.
In this embodiment, the specific number of cameras in the camera array 1 should be determined according to different bridge crane form systems, for example, for a certain type of bridge crane which stacks only three layers of containers but has a longer span, the telephoto group camera may not be used, so that the number of camera arrays is reduced to only 12.
Example four
Referring to fig. 4, the three-dimensional vision-based yard anti-collision system comprises an industrial control device 2 and a camera set 4, wherein the industrial control device 2 is installed in an electrical room of a shore bridge crane 5, the industrial control device 2 uses the optical fiber camera set 4 to receive operation field data, and the industrial control device 2 is connected with a shore bridge crane PLC in the electrical room by a network cable.
In the embodiment, because the cross beam on the sea side of the shore bridge crane is generally very long, in order to reduce the number of cameras used by the camera array, 5 cameras with different focal sections are integrally installed on the moving track of the cross beam on one side, the 5 cameras are respectively responsible for shooting the boxes which are not arranged on the lowest layer of the cabin, the highest 18 layers of boxes which can be hung by the shore bridge crane of the model are arranged, and the cross beam on the other side is completely and symmetrically provided with the camera set, so that 10 cameras are used in the embodiment in total, and similarly, for different shore bridge crane shape systems, the number of the cameras used can be increased or reduced according to actual conditions.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical scope of the present invention and the equivalent alternatives or modifications according to the technical solution and the inventive concept of the present invention within the technical scope of the present invention.
Claims (3)
1. The three-dimensional vision-based storage yard anti-collision system comprises two groups of camera arrays (1), industrial control equipment (2), a field bridge crane (3) and an artificial intelligence controller, and is characterized in that the camera arrays (1) are arranged at the top of the field bridge crane (3), an electric room is arranged in the field bridge crane (3), the industrial control equipment (2) is arranged in the electric room, the artificial intelligence controller is connected with the two groups of camera arrays (1), a field bridge crane PLC is arranged in the electric room, the industrial control equipment (2) is connected with the field bridge crane PLC, the cameras adopted by the camera arrays (1) are digital cameras, the digital cameras are used for continuously shooting stacks in a container storage yard downwards and sending shot multi-view high-definition pictures to the artificial intelligence controller, the artificial intelligence controller is used for carrying out high-precision digital three-dimensional reconstruction on the pictures to generate an electronic virtual map of the storage yard below the whole, and then planning the load path of the lifting appliance on the electronic virtual map so as to generate control parameters of the lifting appliance and the trolley.
2. The three-dimensional vision based yard collision avoidance system according to claim 1, wherein said high precision digital three-dimensional reconstruction process is as follows: the method comprises the steps of firstly, identifying corners of a container as feature points by using a deep convolution neural network instance segmentation algorithm, obtaining instance tag numbers of each feature point, then, regarding each two pictures, obtaining feature points with the same tag numbers, namely, the same corner features of the same container which is shot, thereby forming matching points, then, applying the optimization calculation without baseline constraint to the matching points, carrying out iterative calculation to obtain an intrinsic matrix, and then, using the intrinsic matrix to convert each two-dimensional images into a piece of three-dimensional point cloud with textures.
3. The three-dimensional vision based yard collision avoidance system according to claim 1, wherein said spreader load path planning process is as follows: firstly, obtaining coordinates of each corner of a container below by using a pattern recognition algorithm, using the coordinates as a control point row, then calculating a plane parabolic equation which is higher than all control points and has the shortest length as possible by using an optimization method, finally cutting off the part of the parabola which is higher than the ultimate rise height of the lifting appliance, and using a horizontal straight line segment for substitution to obtain the final lifting appliance load motion track which has the advantages of no collision with stacking, lower running time and lower lifting appliance load motion track.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110610685.1A CN113192199A (en) | 2021-06-01 | 2021-06-01 | Three-dimensional vision-based storage yard anti-collision system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110610685.1A CN113192199A (en) | 2021-06-01 | 2021-06-01 | Three-dimensional vision-based storage yard anti-collision system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113192199A true CN113192199A (en) | 2021-07-30 |
Family
ID=76986189
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110610685.1A Pending CN113192199A (en) | 2021-06-01 | 2021-06-01 | Three-dimensional vision-based storage yard anti-collision system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113192199A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220009748A1 (en) * | 2018-11-14 | 2022-01-13 | Abb Schweiz Ag | Loading A Container On A Landing Target |
| CN114104980A (en) * | 2021-10-15 | 2022-03-01 | 福建电子口岸股份有限公司 | Shore bridge safe operation control method and system based on AI and vision combination |
-
2021
- 2021-06-01 CN CN202110610685.1A patent/CN113192199A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220009748A1 (en) * | 2018-11-14 | 2022-01-13 | Abb Schweiz Ag | Loading A Container On A Landing Target |
| CN114104980A (en) * | 2021-10-15 | 2022-03-01 | 福建电子口岸股份有限公司 | Shore bridge safe operation control method and system based on AI and vision combination |
| CN114104980B (en) * | 2021-10-15 | 2023-06-02 | 福建电子口岸股份有限公司 | Safe operation control method and system for quay crane based on combination of AI and vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12008824B2 (en) | Target positioning method and device, and unmanned aerial vehicle | |
| CN113192199A (en) | Three-dimensional vision-based storage yard anti-collision system | |
| CN110253570A (en) | The industrial machinery arm man-machine safety system of view-based access control model | |
| US11120280B2 (en) | Geometry-aware instance segmentation in stereo image capture processes | |
| CN110765922A (en) | AGV is with two mesh vision object detection barrier systems | |
| CN110902570A (en) | Dynamic measurement method and system for container loading and unloading operation | |
| CN108263950A (en) | Harbour gantry crane suspender based on machine vision it is automatic case system and method | |
| CN109828267A (en) | The Intelligent Mobile Robot detection of obstacles and distance measuring method of Case-based Reasoning segmentation and depth camera | |
| CN114241269B (en) | A collection card vision fuses positioning system for bank bridge automatic control | |
| Hui et al. | A novel autonomous navigation approach for UAV power line inspection | |
| CN111814936A (en) | Container identification method, system, equipment and storage medium based on space scanning | |
| CN110162066A (en) | Intelligent cruise vehicle control | |
| CN115273028B (en) | Intelligent parking lot semantic map construction method and system based on global perception | |
| CN111338382A (en) | Unmanned aerial vehicle path planning method guided by safety situation | |
| WO2021078812A1 (en) | Method and system for object detection for a mobile robot with time-of-flight camera | |
| Huang et al. | Robust lane marking detection under different road conditions | |
| CN111699410A (en) | Point cloud processing method, device and computer readable storage medium | |
| CN112507899A (en) | Three-dimensional laser radar image recognition method and equipment | |
| Chun-Fu et al. | Research on visual navigation algorithm of AGV used in the small agile warehouse | |
| Jun et al. | Autonomous driving system design for formula student driverless racecar | |
| Bian et al. | A point-line-based SLAM framework for UAV close proximity transmission tower inspection | |
| CN113674355A (en) | Target identification and positioning method based on camera and laser radar | |
| CN109885091B (en) | Unmanned aerial vehicle autonomous flight control method and system | |
| CN114782357A (en) | Self-adaptive segmentation system and method for transformer substation scene | |
| CN114879209A (en) | System and method for low-cost foreign matter detection and classification of airport runway |
Legal Events
| 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 |