CN111241995B - Loss compensation method and system for tracked object and computer equipment - Google Patents
Loss compensation method and system for tracked object and computer equipment Download PDFInfo
- Publication number
- CN111241995B CN111241995B CN202010021020.2A CN202010021020A CN111241995B CN 111241995 B CN111241995 B CN 111241995B CN 202010021020 A CN202010021020 A CN 202010021020A CN 111241995 B CN111241995 B CN 111241995B
- Authority
- CN
- China
- Prior art keywords
- lost
- label
- labels
- tag
- main
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Abstract
The invention discloses a loss compensation method, a system and computer equipment of a tracked object, wherein the method comprises the following steps: setting labels for the tracked objects without labels in the space to be detected in real time, wherein each tracked object only corresponds to one label at the same time; when no main label is generated, judging the number of lost labels within threshold time; when the number of the lost tags is 1, directly performing tag compensation; and when the number of the lost labels is multiple, judging the distance, and compensating the labels according to the distance judgment result. The method can compensate the object tracking in the space to be detected, and prevent the tracked object from losing.
Description
Technical Field
The invention belongs to the technical field of object tracking, and particularly relates to a loss compensation method and system for a tracked object and computer equipment.
Background
Tracking of moving objects or human bodies is required in logistics storage, "unmanned stores". The judgment and the behavior analysis of the movement track of the mobile terminal are realized through tracking.
The 'unmanned shop' without cashiers integrates multiple technologies such as artificial intelligence, big data, cloud computing and the like, intelligent automatic processing is carried out through technical means, manual intervention does not exist in the whole process, millisecond-level checkout can be achieved, namely the customer can take the customer away, and the payment time of the customer is greatly shortened. The 'unmanned shop' relates to the combined use of a plurality of new technologies in the operation process, including a gravity recognition commodity technology, a human face image recognition technology, a human body tracking technology in a visual three-dimensional space and the like.
The problem that human body tracking is lost exists in the process of tracking the human body in the three-dimensional space by means of vision, the accuracy of the whole free shopping process is directly influenced, and therefore the goods loss of an unmanned store is increased. In the field of unmanned warehousing, the robot also needs to be tracked and positioned, and the problem of robot tracking loss exists in the tracking and positioning process. Therefore, when the prior art tracks a moving object, the tracking loss is often encountered.
Disclosure of Invention
The invention solves the technical problem of providing a loss compensation method, a loss compensation system and computer equipment for a tracked object.
The technical solution for realizing the purpose of the invention is as follows: a loss compensation method for a tracked object, comprising the steps of:
setting labels for the tracked objects without labels in the space to be detected in real time, wherein each tracked object only corresponds to one label at the same time;
when no main label is generated, judging the number of lost labels within threshold time;
when the number of the lost tags is 1, directly performing tag compensation;
and when the number of the lost labels is multiple, judging the distance, and compensating the labels according to the distance judgment result.
Preferably, the directly performing tag compensation specifically includes:
judging the number of tracked objects in the space to be detected;
the number of the tracked objects in the space to be detected is 1, and the generated non-main label is compensated to the tracked object corresponding to the lost label;
the number of the tracked objects in the space to be detected is larger than 1, only one label of the tracked object is lost, and the generated non-main label is used as a new label of the tracked object.
Preferably, when the number of lost tags is multiple, the distance judgment is performed, and the tag compensation according to the distance judgment result specifically comprises:
step 1, forming a no-main label set by using no-main labels, and forming a lost label set by using a plurality of lost labels;
step 2, selecting a non-main label in the non-main label set;
step 3, selecting the lost labels meeting the distance judgment condition with the non-main label in the lost label set, associating the lost labels with the non-main label, deleting the two associated labels from the non-main label set and the lost label set respectively, and then returning to the step 2 until the number of the lost labels in the lost label set is equal to zero;
and 4, replacing the lost tag with the non-main tag associated with the lost tag.
Preferably, the distance determination condition is: only one shortest distance exists in the distances between the selected non-master tag and each lost tag in the lost tag set.
Preferably, the threshold time is 3 to 5 seconds.
Preferably, the tag includes an ID of the tracked object, and coordinates of the tracked object.
A loss compensation system for a tracked object, comprising:
the tag generation module is used for setting tags for the tracked objects without tags in the space to be detected in real time, and each tracked object corresponds to only one tag at the same time;
the tag loss following judging module is used for judging the number of lost tags within threshold time when no main tag is generated;
the tag tracking loss compensation module is used for directly performing tag compensation when the number of the lost tags is 1; and when the number of the lost labels is multiple, judging the distance, and compensating the labels according to the distance judgment result.
Compared with the prior art, the invention has the following remarkable advantages: 1) The method can compensate the tracked object after being lost, ensures the tracking accuracy, and has wide application field, relating to the fields of storage, unmanned stores and the like; 2) The method combines the time and the distance of generating and losing the new label, and logically judges the relation between the newly generated label and the lost label within the threshold time and threshold distance, thereby realizing the automatic compensation of the tracking and achieving the purpose of compensating the tracking; 3) According to the embodiment of the invention, the problem that the tracking process in the visual three-dimensional space loses the ID is compensated through the visual ID management method, the in-store regenerated non-dominant visual ID can be analyzed, and the non-dominant visual ID can be bound to a customer again when the local mechanism condition is met; 4) According to the embodiment of the invention, the whole shopping experience is improved by compensating the human body tracking in the visual three-dimensional space, the missing of commodities in order settlement is prevented, the rate of losing orders is reduced, and the goods loss of an unmanned shop is reduced.
The present invention is described in further detail below with reference to the attached drawing figures.
Drawings
FIG. 1 is a flowchart of a loss compensation method for a tracked object according to the present invention.
FIG. 2 is a flowchart illustrating distance estimation compensation according to the present invention.
FIG. 3 is a diagram of a loss compensation system for a tracked object in accordance with the present invention.
Fig. 4 is a flowchart of an ID tracking loss compensation method in a visual three-dimensional space according to an embodiment of the present invention.
Detailed Description
Referring to fig. 1, a loss compensation method for a tracked object of the present invention includes the following steps:
setting labels for the tracked objects without labels in the space to be detected in real time, wherein each tracked object only corresponds to one label at the same time; the tag includes the ID of the tracked object, the coordinates of the tracked object, and the like. As long as the tracked objects can be distinguished, they can be set as tags.
When no main label is generated, judging the number of lost labels within threshold time; the threshold time may be set as needed, and is preferably 3 to 5 seconds in the present invention.
When the number of the lost tags is 1, directly performing tag compensation; directly replacing the newly generated tags with the lost tags, and in reality, according to the number of the tracked objects, judging as follows: judging the number of tracked objects in the space to be detected; the number of the tracked objects in the space to be detected is 1, and the generated non-main tags are compensated into lost tags; the number of the tracked objects in the space to be detected is larger than 1, only one label of the tracked object is lost, and the generated non-main label is used as a new label of the tracked object of the lost label.
When the number of the lost labels is multiple, distance judgment is carried out, label compensation is carried out according to the distance judgment result, and the distance judgment principle is as follows: determining the distance between the newly generated non-main label and each lost label; and comparing a plurality of the distances, and replacing the lost label corresponding to the shortest distance with the newly generated non-master label when only one shortest distance exists in the distances. When the number of the lost tags is multiple, the number of the lost tags is consistent with the number of the generated no-main tags. With reference to fig. 2, specifically:
step 1, forming a no-main label set by the no-main labels, and forming a lost label set by a plurality of lost labels;
step 2, selecting one non-main label from the non-main label set;
step 3, selecting the lost labels meeting the distance judgment condition with the non-main label in the lost label set, associating the lost labels with the non-main label, deleting the two associated labels from the non-main label set and the lost label set respectively, and then returning to the step 2 until the number of the lost labels in the lost label set is equal to zero;
and 4, replacing the lost tag with the non-main tag associated with the lost tag.
The above-mentioned contents can be implemented by the following steps:
step 1, forming a plurality of non-main labels into a non-main label set, and forming a plurality of lost labels into a lost label set;
step 2, selecting a non-main label in the non-main label set;
step 3, judging the distance between the selected non-main label and each lost label in the lost label set;
step 4, if the distance judgment condition is met, associating the non-main label with the corresponding lost label, deleting the two associated labels from the non-main label set and the lost label set respectively, and then executing step 5; otherwise, selecting another non-main label in the non-main label set and executing the step 3; after traversing all the non-main labels in the non-main label set, if all the non-main labels do not accord with the distance judgment condition, ending the operation; the distance judgment conditions are as follows: only one shortest distance exists in the distances between the selected non-main label and each lost label in the lost label set.
Step 5, judging the number of the remaining non-main tags in the non-main tag set, if only 1 non-main tag exists, associating the non-main tag with the remaining lost tags in the lost tag set, then executing step 6, and if not, returning to the step 2;
and 6, replacing the lost label with the non-main label associated with the lost label. Compensation for lost tags is accomplished.
With reference to fig. 3, a loss compensation system for a tracked object, comprising:
the tag generation module is used for setting tags for the tracked objects without tags in the space to be detected in real time, and each tracked object corresponds to only one tag at the same time;
the tag tracking and losing judgment module is used for judging the number of lost tags within threshold time when no main tag is generated;
the tag tracking loss compensation module is used for directly performing tag compensation when the number of the lost tags is 1; and when the number of the lost labels is multiple, judging the distance, and compensating the labels according to the distance judgment result.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
setting labels for the tracked objects without labels in the space to be detected in real time, wherein each tracked object only corresponds to one label at the same time;
when no main label is generated, judging the number of lost labels within threshold time;
when the number of the lost tags is 1, directly performing tag compensation;
and when the number of the lost labels is multiple, judging the distance, and compensating the labels according to the distance judgment result.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
setting labels for the tracked objects without labels in the space to be detected in real time, wherein each tracked object only corresponds to one label at the same time;
when no main label is generated, judging the number of lost labels within threshold time;
when the number of the lost tags is 1, directly performing tag compensation;
and when the number of the lost labels is multiple, judging the distance, and compensating the labels according to the distance judgment result.
The specific details of the steps have been described above and will not be described herein. The method can compensate the tracked object after being lost, ensures the tracking accuracy, has application fields related to the fields of storage, unmanned stores and the like, and is widely applied to the following further detailed description by combining the embodiment.
Examples
The method applied to the visual three-dimensional space for tracking and compensating the human body ID specifically comprises the following steps:
with reference to fig. 4, a method for compensating ID loss tracking in a visual three-dimensional space includes the following steps:
newly generating a no-main ID in a visual three-dimensional space;
judging the number of lost IDs in the visual three-dimensional space within threshold time;
and executing corresponding compensation operation according to the number of ID loss.
And judging the number of ID losses in the visual three-dimensional space within the threshold time, specifically judging that the number of ID losses within the threshold time is equal to 1 or greater than 1.
The executing the corresponding compensation operation according to the number of ID loss specifically includes:
when the number of lost IDs is equal to 1, executing a single ID compensation method to compensate the lost IDs; the method comprises the following specific steps:
compensating the newly generated no-master ID to a lost ID within a threshold time by:
the number of tracked objects in the visual three-dimensional space is 1, and the newly generated non-master ID is compensated to be a lost ID;
the number of tracked objects in the visual three-dimensional space is more than 1, a certain ID is changed, and the changed ID is used as a new ID corresponding to the tracked object before the ID is changed.
And when the number of lost IDs is more than 1, a multi-ID compensation method is executed to compensate the lost IDs. The method specifically comprises the following steps:
determining the distance between the newly generated ID and each lost ID;
judging the distance, and if the number of lost IDs corresponding to the shortest distance is more than two, not processing; and if the shortest distance corresponds to a lost ID, replacing the newly generated ID with the lost ID. The threshold time is 3-5 seconds.
A lost person situation occurs:
when only one ID is lost during in-store visual ID tracking and a new ID is regenerated within a threshold time, the newly generated ID is considered to be the lost ID. Such as:
a) When only one person is in the store, the regenerated ID within the threshold time is the lost ID
b) If there are four people in the store, the corresponding visual IDs are ID1, ID2, ID3, and ID4, and the visual IDs become ID1, ID2, ID3, and ID5 within a threshold time, it is considered that ID5 is generated by ID4 being lost, and ID4 and ID5 are the same person.
A lost multiple person situation occurs:
when a plurality of person IDs are lost and generated in the in-store visual ID tracking process, the judgment can be carried out according to the generation time of the new ID, the distance between the new ID and the lost ID, and the specific logic is as follows:
the method comprises the following steps: newly generated IDs appear, and lost IDs within a threshold time (such as 3 seconds) are searched;
step two: calculating the distance between the newly generated ID and each lost ID;
step three: if only finding a plurality of lost IDs with the shortest same distance within the threshold time, not satisfying the policy rule and not compensating; if only one lost ID with the shortest distance is found within the threshold time, the newly generated ID is associated with the lost ID with the shortest distance, namely the lost ID is compensated by the newly generated ID, and the new ID and the old ID can be considered as the same person.
The method compensates the problem that the ID is lost in the tracking process of the human body in the visual three-dimensional space through the visual ID management method, can analyze the non-main visual ID regenerated in a store, and can bind the non-main visual ID to a customer again when the system condition is met. The method can improve the overall shopping experience, prevent orders from clearing and omitting commodities, reduce the rate of losing the orders and reduce the goods loss of unmanned stores. The invention can also be applied to the field of unmanned warehousing and is used for tracking and positioning unmanned planes and unmanned vehicles.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not to be understood as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (8)
1. A method for loss compensation of a tracked object, comprising the steps of:
setting labels for the tracked objects without labels in the space to be detected in real time, wherein each tracked object only corresponds to one label at the same time;
when no main label is generated, judging the number of lost labels within threshold time;
when the number of the lost tags is 1, directly performing tag compensation;
when losing the label quantity and being a plurality of, carry out distance judgement to carry out label compensation according to distance judgement result, specifically do:
step 1, forming a no-main label set by the no-main labels, and forming a lost label set by a plurality of lost labels;
step 2, selecting one non-main label from the non-main label set;
step 3, selecting the lost labels meeting the distance judgment condition with the non-main label in the lost label set, associating the lost labels with the non-main label, deleting the two associated labels from the non-main label set and the lost label set respectively, and then returning to the step 2 until the number of the lost labels in the lost label set is equal to zero;
and 4, replacing the lost label with the associated non-main label.
2. The method for compensating for loss of a tracked object according to claim 1, wherein the directly performing tag compensation specifically comprises:
judging the number of tracked objects in the space to be detected;
the number of the tracked objects in the space to be detected is 1, and the generated non-main label is compensated to the tracked object corresponding to the lost label;
the number of the tracked objects in the space to be detected is larger than 1, only one label of the tracked object is lost, and the generated non-main label is used as a new label of the tracked object.
3. The method of claim 1, wherein the distance determining condition is: only one shortest distance exists in the distances between the selected non-master tag and each lost tag in the lost tag set.
4. The loss compensation method for the tracked object according to claim 1, wherein the threshold time is 3 to 5 seconds.
5. The method of claim 1, wherein the tag comprises an ID of the tracked object, and coordinates of the tracked object.
6. A loss compensation system for a tracked object, comprising:
the tag generation module is used for setting tags for the tracked objects without tags in the space to be detected in real time, and each tracked object corresponds to only one tag at the same time;
the tag tracking and losing judgment module is used for judging the number of lost tags within threshold time when no main tag is generated;
the tag loss tracking compensation module is used for directly performing tag compensation when the number of the lost tags is 1; when losing the label quantity and being a plurality of, carry out distance judgement to carry out label compensation according to distance judgement result, specifically do:
step 1, forming a no-main label set by using no-main labels, and forming a lost label set by using a plurality of lost labels;
step 2, selecting one non-main label from the non-main label set;
step 3, selecting the lost labels meeting the distance judgment condition with the non-main label in the lost label set, associating the lost labels with the non-main label, deleting the two associated labels from the non-main label set and the lost label set respectively, and then returning to the step 2 until the number of the lost labels in the lost label set is equal to zero;
and 4, replacing the lost tag with the non-main tag associated with the lost tag.
7. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 5 when executing the computer program.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010021020.2A CN111241995B (en) | 2020-01-09 | 2020-01-09 | Loss compensation method and system for tracked object and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010021020.2A CN111241995B (en) | 2020-01-09 | 2020-01-09 | Loss compensation method and system for tracked object and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111241995A CN111241995A (en) | 2020-06-05 |
| CN111241995B true CN111241995B (en) | 2022-12-30 |
Family
ID=70874433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010021020.2A Active CN111241995B (en) | 2020-01-09 | 2020-01-09 | Loss compensation method and system for tracked object and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111241995B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015008432A1 (en) * | 2013-07-17 | 2015-01-22 | 日本電気株式会社 | Object tracking device, object tracking method, and object tracking program |
| CN106355603A (en) * | 2016-08-29 | 2017-01-25 | 深圳市商汤科技有限公司 | Method and device for human tracking |
-
2020
- 2020-01-09 CN CN202010021020.2A patent/CN111241995B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015008432A1 (en) * | 2013-07-17 | 2015-01-22 | 日本電気株式会社 | Object tracking device, object tracking method, and object tracking program |
| CN106355603A (en) * | 2016-08-29 | 2017-01-25 | 深圳市商汤科技有限公司 | Method and device for human tracking |
Non-Patent Citations (2)
| Title |
|---|
| Joint Multi-target Filtering and Track Maintenance;Yunxiang Li 等;《The 2014 7th International Congress on Image and Signal Processing 》;20150108;全文 * |
| 动态背景下的视频目标检测与跟踪研究;李恒年;《全国硕士学位论文全文库（信息科技辑）》;20170215;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111241995A (en) | 2020-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7072054B2 (en) | Methods and equipment for sorting cargo | |
| CN111445501B (en) | Multi-target tracking method, device and storage medium | |
| US20090164305A1 (en) | System and method for managing product quality | |
| CN113239719B (en) | Trajectory prediction method and device based on abnormal information identification and computer equipment | |
| CN110766194A (en) | Order processing method and device, warehousing system, computer equipment and storage medium | |
| CN109544078B (en) | Cargo management method based on block chain technology | |
| CN113537850A (en) | Storage optimization method and device, computer equipment and storage medium | |
| CN104834719B (en) | Applied to the Database Systems under real-time big data scene | |
| CN112633205A (en) | Pedestrian tracking method and device based on head and shoulder detection, electronic equipment and storage medium | |
| CN111354022A (en) | Target tracking method and system based on kernel correlation filtering | |
| CN111626519A (en) | Flight arrival time prediction method and device and electronic equipment | |
| CN111241995B (en) | Loss compensation method and system for tracked object and computer equipment | |
| CN111652641B (en) | Data processing method, device, equipment and computer readable storage medium | |
| CN113269483A (en) | Management method, device, medium and electronic equipment of intelligent vault system | |
| CN110598989B (en) | Goods source quality evaluation method, device, equipment and storage medium | |
| CN111369583B (en) | Tracking loss compensation method, system and computer equipment | |
| CN115660524A (en) | E-commerce logistics monitoring method and system | |
| CN115587769A (en) | Method and device for detecting commodity out-of-stock state, computer equipment and storage medium | |
| CN113506164B (en) | Wind control decision method and device, electronic equipment and machine-readable storage medium | |
| CN112885105B (en) | Commuting vehicle identification method and device based on high-definition checkpoint data and storage medium | |
| Zhang et al. | Logistics information traceability mechanism of fresh e-commerce based on image recognition technology | |
| CN111915347A (en) | Method, device and system for effectively storing and applying promotion purchase price | |
| CN112330241A (en) | Logistics visualization method, device, equipment and medium | |
| CN110992129A (en) | Vehicle order matching method and device, computer equipment and storage medium | |
| US20230266468A1 (en) | Track Association Method and System for Tracking Objects |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |