CN115222804A - Industrial material cage identification and positioning method based on depth camera point cloud data - Google Patents
Industrial material cage identification and positioning method based on depth camera point cloud data Download PDFInfo
- Publication number
- CN115222804A CN115222804A CN202211079835.1A CN202211079835A CN115222804A CN 115222804 A CN115222804 A CN 115222804A CN 202211079835 A CN202211079835 A CN 202211079835A CN 115222804 A CN115222804 A CN 115222804A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- cloud data
- cage
- point
- depth camera
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 239000012770 industrial material Substances 0.000 title claims abstract description 14
- 239000000463 material Substances 0.000 claims abstract description 39
- 238000000926 separation method Methods 0.000 claims abstract description 11
- 238000013519 translation Methods 0.000 claims description 13
- 230000009466 transformation Effects 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 3
- 230000004807 localization Effects 0.000 claims 2
- 238000012545 processing Methods 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000013480 data collection Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000013077 target material Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Forklifts And Lifting Vehicles (AREA)
Abstract
The invention discloses an industrial material cage identification and positioning method based on depth camera point cloud data, which comprises the following steps: s1: a depth camera acquires scene point cloud data; s2: carrying out Euclidean distance separation on the acquired scene point cloud data; s3: the depth camera collects template point cloud data of the material cage; s4: matching the separated point cloud data with template point cloud data of the collected material cage to obtain material cage point cloud; s5: performing secondary separation on the stock cage point cloud to obtain a stock cage front point cloud; s6: and determining the central position and the central shaft angle of the material cage by the point cloud data on the front surface of the material cage to obtain the pose of the material cage. Before the forklift moves to the material, the depth camera starts point cloud data collection, the point cloud data are used for identifying the position of a central hole of the stock cage, the stock cage is used for navigation and positioning when the stock cage is inserted and taken, and a parallel processing algorithm is adopted to execute a template matching algorithm, so that the calculation efficiency is improved, and the matching time of the point cloud of the stock cage is reduced.
Description
Technical Field
The invention relates to the technical field of point cloud processing and target identification, in particular to an industrial material cage identification and positioning method based on depth camera point cloud data.
Background
The intelligent positioning and navigation functions are more and more widely applied in the field of intelligent warehousing, and the technology of installing a 3D depth camera in a forklift to identify and position a target material cage is just one of the technologies. With the rapid development of Chinese economy, traditional enterprises which depend on manual transportation begin to change from mechanization to automation and intelligence, and the demands of logistics and warehouse logistics in factories on automatic transportation equipment with high flexibility degree increase rapidly. The forklift is used as a main force in logistics carrying equipment, and gradually approaches to advanced technologies such as intelligent identification and autonomous navigation positioning, and the intelligent forklift is researched and designed under the background.
Fork truck generally uses the fork to get the form of goods unloading cage through the fork and carries out transporting of material, and prior art can't accomplish the great material cage of auto-picking angle of deflection, needs personnel to control, and degree of automation and intellectuality is not high, increases the personnel cost of enterprise to harm the interests of enterprise, along with scientific and technological progress's development, because traditional fork truck can not automatic accomplish the operation, can't satisfy the high efficiency of commodity circulation industry, the operation demand of long term. Through long-term research of the inventor, the invention provides an industrial material cage identification and positioning method based on depth camera point cloud data.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an industrial material cage identification and positioning method based on depth camera point cloud data.
The purpose of the invention is realized by the following technical scheme: an industrial material cage identification and positioning method based on depth camera point cloud data comprises the following steps:
s1: acquiring scene point cloud data through a depth camera and preprocessing the scene point cloud data;
s2: carrying out Euclidean distance separation on the acquired scene point cloud data;
s3: acquiring template point cloud data of the material cage through a depth camera;
s4: matching the separated point cloud data with template point cloud data of the collected material cage to realize material cage identification and obtain material cage point cloud;
s5: performing secondary separation on the stock cage point cloud to obtain a stock cage front point cloud;
s6: and determining the center position and the center shaft angle of the material cage according to the point cloud data on the front surface of the material cage to obtain the pose of the material cage, wherein the pose is used for navigation and positioning of the material cage when the material cage is inserted and taken.
Preferably, in step S1, the depth camera needs to be fixed at an installation position, a relative relationship between the depth camera and a standard coordinate system is obtained through measurement, the point cloud data is preprocessed, and the point cloud data is separated from the ground in height.
Preferably, in step S2, the camera point cloud data is divided into N types according to the distance, and the separation distance and the size of each type of point cloud data are set.
Preferably, the depth camera point cloud data is classified according to Euclidean distance, and the method comprises the following steps:
a1: carrying out distance clustering on the input point cloud data according to a Euclidean method;
a2: creating a Kd-Tree expression P for the input disordered point cloud to realize rapid search;
a3: an empty cluster list C is set and a set of points Q waiting to be checked.
b2: searchingSet of all point configurations within a sphere of radius r as the centerTo, forEach point inIf not treated, is added toQIn, whenQAll the points in the process are processed, and the process is carried outQJoining a cluster listCWill beQResetting to empty;
Preferably, in step S4, each type of segmented point cloud data is matched with the acquired template point cloud data of the stock cage by using a data registration algorithm of a nearest neighbor iteration method, and the point cloud with the highest matching score is calculated as the point cloud where the stock cage is located, wherein the matching formula is
Where Q is a set of points, i =1,2,3.. Denotes the first set of points, i.e., point cloud data for each class,i =1,2,3.. Indicate a second point set, namely point cloud data of the stock cage template, the alignment registration of the two point sets is converted to minimize the target function, R is a rotation matrix, and T is a translation matrix, namely rotation parameters and translation parameters between the point cloud data to be registered and the reference point cloud data, so that the optimal matching between the two point set data is satisfied.
Preferably, E1: calculating the corresponding closest point of each point in the P in the Q point set;
e2: obtaining rigid body transformation which enables the average distance of the corresponding points to be minimum, and obtaining translation parameters and rotation parameters;
e3: obtaining a new transformation point set P' by using the translation parameter and the rotation parameter obtained in the E2 for the P;
e4: and if the average distance between the new transformation point set and the reference point set is smaller than a given threshold value, stopping iterative computation, otherwise, taking the new transformation point set P' as a new input to continue iteration until the requirement is met.
The invention has the following advantages: according to the method, when the forklift moves to the front of the material, the depth camera starts to acquire point cloud data, the position of a center hole of the stock cage is identified by using the point cloud data, so that the stock cage is navigated and positioned when the stock cage is inserted and taken, the template matching algorithm is executed by adopting the parallel processing algorithm, the calculation efficiency is improved, the matching time of the point cloud of the stock cage is reduced, the original point cloud of the depth camera is separated from the ground by cutting the original point cloud of the depth camera in height, the influence of the ground point cloud on template matching can be avoided, and the influence of the ground point cloud on the original point cloud is reduced and the matching efficiency is improved.
Drawings
FIG. 1 is a schematic diagram of the structure of a flow of an identification algorithm;
fig. 2 is a schematic structural diagram of a positioning algorithm flow.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings of the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be obtained by a person skilled in the art without inventive efforts based on the embodiments of the present invention, are within the scope of protection of the present invention.
In addition, the embodiments of the present invention and the features of the embodiments may be combined with each other without conflict.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, or orientations or positional relationships that the products of the present invention conventionally lay out when in use, or orientations or positional relationships that are conventionally understood by those skilled in the art, which are merely for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the device or element referred to must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like are used merely to distinguish one description from another, and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should also be noted that, unless otherwise explicitly specified or limited, the terms "disposed," "mounted," "connected," and "connected" are to be construed broadly and may, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In this embodiment, referring to fig. 1-2 together, an industrial material cage identification and positioning method based on depth camera point cloud data includes the following steps:
s1: acquiring scene point cloud data through a depth camera and preprocessing the scene point cloud data;
s2: carrying out Euclidean distance separation on the acquired scene point cloud data;
s3: acquiring template point cloud data of the material cage through a depth camera;
s4: matching the separated point cloud data with template point cloud data of the collected material cage to realize material cage identification and obtain material cage point cloud;
s5: performing secondary separation on the stock cage point cloud to obtain a stock cage front point cloud;
s6: and determining the center position and the center shaft angle of the material cage according to the point cloud data on the front surface of the material cage to obtain the pose of the material cage, wherein the pose is used for navigation and positioning of the material cage when the material cage is inserted and taken. When the forklift moves to the front of the material, the depth camera starts to acquire point cloud data, the position of a center hole of the stock cage is identified by using the point cloud data, so that the stock cage is navigated and positioned when the stock cage is inserted and taken, a template matching algorithm is executed by adopting a parallel processing algorithm to improve the calculation efficiency and reduce the matching time of the point cloud of the stock cage, the original point cloud of the depth camera is separated from the ground by cutting the original point cloud of the depth camera in height, the influence of the point cloud of the ground on template matching can be avoided, and the influence of the point cloud of the ground on the original point cloud is reduced and the matching efficiency is improved.
Further, in step S1, the depth camera needs to be fixed at an installation position, a relative relationship between the depth camera and a standard coordinate system is obtained through measurement, the point cloud data is preprocessed, and the point cloud data is separated from the ground in height. Specifically, after a camera is fixed in position, a depth camera is used for collecting front data point clouds of a stock cage in a close range and taking the front data point clouds as source data matched with a template, camera point clouds issued by an IntelRealsense depth camera are received through communication, meanwhile, preprocessing is needed to be carried out on original point clouds, the preprocessing comprises coordinate conversion on the camera depth point cloud data, coordinates of each point under a camera coordinate system need to be converted into a reference coordinate system with a forklift as an origin, the camera range is limited, and therefore the influence of point cloud noise outside the range on the stock cage point clouds is reduced.
In this embodiment, in step S2, the camera point cloud data is divided into N types according to the distance, and the separation distance and the size of each type of point cloud data are set. Specifically, as many types of point clouds exist in the visual field range of the camera, euclidean distance clustering is carried out on the processed point clouds, the point clouds are divided into different types according to the distance, the divided point clouds of different types are used for subsequent template matching, and thus the point cloud with the highest matching degree with the template is matched, namely the point cloud for identifying the stock cage in the point cloud data of the camera.
Further, the depth camera point cloud data classification according to the Euclidean distance comprises the following steps:
a1: carrying out distance clustering on the input point cloud data according to an Euclidean method;
a2: creating a Kd-Tree expression P for the input disordered point cloud to realize rapid search;
a3: an empty cluster list C and a set of points Q waiting to be checked are set. Still further, each point in P in A2The following steps are performed: b1: will be provided withAdding to the current point set Q; b2: searchingSet of all point configurations within a sphere of radius r as the centerTo, forEach point inIf not treated, is added toQIn, whenQAll the points in the process are processed, and the process is carried outQJoining a Cluster ListCWill beQResetting to empty; b3: when all points areAre all being processed, at that timeCMemory storageAll clusters are put.
In this embodiment, referring to fig. 2 for description, in step S4, each type of point cloud data after segmentation is matched with the acquired template point cloud data of the stock cage by using a data registration algorithm of a nearest neighbor iteration method, and the point cloud with the highest matching score is calculated as the point cloud where the stock cage is located, where the matching formula is
Where Q is a set of points, i =1,2,3.. Denotes the first set of points, i.e., point cloud data for each class,i =1,2,3.. Indicate a second point set, namely point cloud data of the stock cage template, the alignment registration of the two point sets is converted to minimize the target function, R is a rotation matrix, and T is a translation matrix, namely rotation parameters and translation parameters between the point cloud data to be registered and the reference point cloud data, so that the optimal matching between the two point set data is satisfied. Further, E1: calculating the corresponding closest point of each point in the P in the Q point set; e2: obtaining rigid body transformation which enables the average distance of the corresponding points to be minimum, and obtaining translation parameters and rotation parameters; e3: obtaining a new transformation point set P' by using the translation parameter and the rotation parameter obtained in the step E2 for P; e4: and if the average distance between the new transformation point set and the reference point set is smaller than a given threshold value, stopping iterative computation, otherwise, taking the new transformation point set P' as a new input to continue iteration until the requirement is met. Specifically, template matching is carried out on different types of point clouds after Euclidean distance segmentation through a nearest neighbor iteration method, corresponding points between a source point cloud and a target point cloud are obtained, a rotation and translation matrix is constructed based on the corresponding points, the source point cloud is transformed to a coordinate system of the target point cloud by using the obtained matrix, an error function of the transformed source point cloud and the target point cloud is estimated, if an error function value is larger than a threshold value, the operation is carried out iteratively until a given error requirement is met, and therefore the matching degree between the camera point cloud and the template point cloud is calculated, and the matching degree is the highestThe high point cloud is the material cage.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that various changes in the embodiments and/or modifications of the invention can be made, and equivalents and modifications of some features of the invention can be made without departing from the spirit and scope of the invention.
Claims (7)
1. An industrial material cage identification and positioning method based on depth camera point cloud data is characterized by comprising the following steps: the method comprises the following steps:
s1: acquiring scene point cloud data through a depth camera and preprocessing the scene point cloud data;
s2: carrying out Euclidean distance separation on the acquired scene point cloud data;
s3: acquiring template point cloud data of the material cage through the depth camera;
s4: matching the separated point cloud data with template point cloud data of the collected material cage to realize material cage identification and obtain material cage point cloud;
s5: performing secondary separation on the stock cage point cloud to obtain a stock cage front point cloud;
s6: and determining the center position and the center shaft angle of the material cage according to the point cloud data on the front surface of the material cage to obtain the pose of the material cage, wherein the pose is used for navigation and positioning of the material cage when the material cage is inserted and taken.
2. The industrial material cage identification and positioning method based on the point cloud data of the depth camera as claimed in claim 1, wherein: in the step S1, the depth camera needs to be fixed at a position, a relative relationship between the depth camera and a standard coordinate system is obtained through measurement, point cloud data is preprocessed, and the point cloud data is separated from the ground in height.
3. The method for identifying and locating industrial cages based on point cloud data of depth cameras as claimed in claim 2, characterized in that: in the step S2, the camera point cloud data is divided into N types according to the distance, and the separation distance and the size of each type of point cloud data are set.
4. The industrial material cage identification and positioning method based on the point cloud data of the depth camera as claimed in claim 3, wherein: classifying the depth camera point cloud data according to Euclidean distance, comprising the following steps:
a1: carrying out distance clustering on the input point cloud data according to a Euclidean method;
a2: creating a Kd-Tree expression P for the input disordered point cloud to realize rapid search;
a3: an empty cluster list C and a set of points Q waiting to be checked are set.
5. The method of claim 4 for industrial material cage identification and localization based on depth camera point cloud data, wherein: each point in P in said step A2Executing the following steps:
b2: searchingSet of all point configurations in a sphere of radius r as centerTo, forEach point inIf notTreated and added toQIn, whenQAll the points in the process are processed, and the process is carried outQJoining a cluster listCWill beQResetting to empty;
6. The method for identifying and locating the industrial material cage based on the point cloud data of the depth camera according to claim 1, wherein: in the step S4, each type of segmented point cloud data is matched with the acquired template point cloud data of the stock cage by using a data registration algorithm of a nearest neighbor iteration method, and the point cloud with the highest matching score is calculated as the point cloud where the stock cage is located, wherein the matching formula is as follows:
where Q is a set of points, i =1,2,3,. Denotes the first set of points, i.e. the point cloud data of each class,i =1,2,3.. Indicate a second point set, i.e., point cloud data of the stock cage template, the alignment registration of the two point sets is converted to minimize the target function, R is a rotation matrix, T is a translation matrix, i.e., a rotation parameter and a translation parameter between the point cloud data to be registered and the reference point cloud data, so that the optimal matching between the two point set data is satisfied, and n is the number of point sets representing actual point clouds.
7. The depth camera point cloud data-based industrial material cage identification and localization method according to claim 6, characterized by comprising the following steps:
step E1: calculating the corresponding closest point of each point in the P in the Q point set;
step E2: obtaining rigid body transformation which enables the average distance of the corresponding points to be minimum, and obtaining translation parameters and rotation parameters;
step E3: obtaining a new transformation point set P' by using the translation parameter and the rotation parameter obtained in the step E2 for P;
step E4: and if the average distance between the new transformation point set and the reference point set is smaller than a given threshold value, stopping iterative computation, otherwise, taking the new transformation point set P' as a new input to continue iteration until the requirement is met.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211079835.1A CN115222804A (en) | 2022-09-05 | 2022-09-05 | Industrial material cage identification and positioning method based on depth camera point cloud data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211079835.1A CN115222804A (en) | 2022-09-05 | 2022-09-05 | Industrial material cage identification and positioning method based on depth camera point cloud data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115222804A true CN115222804A (en) | 2022-10-21 |
Family
ID=83617186
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211079835.1A Pending CN115222804A (en) | 2022-09-05 | 2022-09-05 | Industrial material cage identification and positioning method based on depth camera point cloud data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115222804A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111950500A (en) * | 2020-08-21 | 2020-11-17 | 成都睿芯行科技有限公司 | Real-time pedestrian detection method based on improved YOLOv3-tiny in factory environment |
CN114419150A (en) * | 2021-12-21 | 2022-04-29 | 未来机器人(深圳)有限公司 | Forklift goods taking method and device, computer equipment and storage medium |
CN114694134A (en) * | 2022-03-23 | 2022-07-01 | 成都睿芯行科技有限公司 | Tray identification and positioning method based on depth camera point cloud data |
CN114820391A (en) * | 2022-06-28 | 2022-07-29 | 山东亚历山大智能科技有限公司 | Point cloud processing-based storage tray detection and positioning method and system |
-
2022
- 2022-09-05 CN CN202211079835.1A patent/CN115222804A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111950500A (en) * | 2020-08-21 | 2020-11-17 | 成都睿芯行科技有限公司 | Real-time pedestrian detection method based on improved YOLOv3-tiny in factory environment |
CN114419150A (en) * | 2021-12-21 | 2022-04-29 | 未来机器人(深圳)有限公司 | Forklift goods taking method and device, computer equipment and storage medium |
CN114694134A (en) * | 2022-03-23 | 2022-07-01 | 成都睿芯行科技有限公司 | Tray identification and positioning method based on depth camera point cloud data |
CN114820391A (en) * | 2022-06-28 | 2022-07-29 | 山东亚历山大智能科技有限公司 | Point cloud processing-based storage tray detection and positioning method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Lin et al. | Color-, depth-, and shape-based 3D fruit detection | |
CN111680542B (en) | Steel coil point cloud identification and classification method based on multi-scale feature extraction and Pointnet neural network | |
CN110222702B (en) | Industrial vehicle with dome lamp based positioning | |
CN109000649B (en) | Omni-directional mobile robot pose calibration method based on right-angle bend characteristics | |
CN114820391B (en) | Point cloud processing-based storage tray detection and positioning method and system | |
CN111260289A (en) | Micro unmanned aerial vehicle warehouse checking system and method based on visual navigation | |
CN114694134A (en) | Tray identification and positioning method based on depth camera point cloud data | |
CN113253737B (en) | Shelf detection method and device, electronic equipment and storage medium | |
CN111198496A (en) | Target following robot and following method | |
CN111539429A (en) | Automatic circulation box positioning method based on image geometric features | |
CN115321090B (en) | Method, device, equipment, system and medium for automatically receiving and taking luggage in airport | |
CN116128841A (en) | Tray pose detection method and device, unmanned forklift and storage medium | |
Holz et al. | Fast edge-based detection and localization of transport boxes and pallets in rgb-d images for mobile robot bin picking | |
Naumann et al. | Literature review: Computer vision applications in transportation logistics and warehousing | |
CN113469195B (en) | Target identification method based on self-adaptive color quick point feature histogram | |
CN113420648B (en) | Target detection method and system with rotation adaptability | |
Tazir et al. | Cluster ICP: Towards sparse to dense registration | |
CN115222804A (en) | Industrial material cage identification and positioning method based on depth camera point cloud data | |
CN102564424A (en) | Multiple sensor-based data fusion method | |
Li et al. | Pallet detection and localization with RGB image and depth data using deep learning techniques | |
CN113111899A (en) | Object recognition or object registration method based on image classification and computing system | |
CN106845317A (en) | Many bar code localization methods, device and terminal | |
CN112288038B (en) | Object recognition or object registration method based on image classification and computing system | |
Fontana et al. | A combinatorial approach to detection of box pallet layouts | |
Zhu et al. | Object detection and recognition method based on binocular |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221021 |