CN112605999A - Robot obstacle detection method and system based on infrared deep camera technology - Google Patents
Robot obstacle detection method and system based on infrared deep camera technology Download PDFInfo
- Publication number
- CN112605999A CN112605999A CN202011526620.0A CN202011526620A CN112605999A CN 112605999 A CN112605999 A CN 112605999A CN 202011526620 A CN202011526620 A CN 202011526620A CN 112605999 A CN112605999 A CN 112605999A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- infrared
- robot
- set area
- area
- 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.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
- B25J9/1666—Avoiding collision or forbidden zones
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a robot obstacle detection method and system based on an infrared deep camera technology, wherein the method comprises the following steps: s1, acquiring data of the infrared depth sensor; s2, filtering data returned by the infrared sensors outside the set area, dividing the picture obtained by the infrared depth sensor into set points in the set area, and forming the set area by the set points; s3, returning the obstacle information when the set area detects the obstacle; the system comprises an obstacle detection module, a sensor information uploading module, an information processing module and an instruction execution module which are sequentially connected, wherein the obstacle detection module is used for detecting whether an obstacle exists in a set area or not, setting points are divided through pictures obtained by an infrared depth sensor, the set area is formed by the setting points, data returned by the infrared sensor outside the set area are filtered, and obstacle information is returned when the set area detects the obstacle.
Description
Technical Field
The invention relates to the technical field of computer application, in particular to a method and a system for identifying obstacles through electronic equipment.
Background
The obstacle recognition technology is a technology for calculating whether an obstacle exists in front of a camera in real time, transmitting obstacle information to a processing mechanism, and enabling the processing mechanism to carry out evasion, alarm or other processing through the obstacle information.
The infrared depth camera or the laser or the ultrasonic detects whether an obstacle exists in front of the vehicle, and the distance of the obstacle is obtained by the time difference of the infrared ray, the laser and the ultrasonic reaching the surface of the obstacle and returning, and the realization principle is mainly as follows:
(1) connecting a camera with a computer or other processing mechanisms in advance;
(2) acquiring the distance of an object through an infrared camera, laser and an ultrasonic sensor;
(3) and comparing the distance of the object with a set value, and if the distance is less than or equal to the set value, indicating that the object is too close.
The current obstacle detection technology has two major disadvantages:
1. the cost of the equipment is too high, the laser detection equipment on the market is generally higher in price at present, and the phenomenon that the product is expensive can be caused when the equipment is used for the product.
2. The infrared camera and the ultrasonic detection equipment are prone to error detection, various interferences can be caused in a normal detection flow, a barrier is suddenly detected, and the normal flow can be interrupted.
Disclosure of Invention
In order to solve the defects of the prior art and achieve the purposes of reducing the cost and simultaneously reducing the detection interference, the invention adopts the following technical scheme:
the robot obstacle detection method based on the infrared deep camera technology comprises the following steps:
s1, acquiring data of the infrared depth sensor;
s2, filtering data returned by the infrared sensors outside a set area, wherein the set area divides a picture obtained by the infrared depth sensor into set points, and the set points form the set area;
s3, when the set area detects an obstacle, the obstacle information is returned.
By the method, the obstacle which appears at the edge of the picture but is not in the detection area can not interfere with the obstacle identification of the normal flow, namely the obstacle can not be identified to cause flow interruption, so that the fault tolerance is increased, and the aim of normally performing the flow without interruption when the obstacle detection interference occurs to a certain degree is fulfilled.
Through the construction of the set region, the set region meets specific conditions, other region detection data are ignored, and the effects of reducing useless data quantity, reducing operation requirements and using under special conditions are achieved.
The similar function of the laser sensor with high cost can be realized through the infrared depth camera with low cost, the cost is reduced, the popularization difficulty of the product is reduced, and the competitiveness of the product is improved.
Further, in step S2, the shape of the set area and the depth acquired by the infrared depth sensor are matched to the shape of the robot provided with the infrared depth sensor. The problem that in a traditional detection mode, a rectangular area is used for wrapping the range of the whole robot to detect obstacles in the whole rectangular area is avoided, and when the obstacle passes through narrow areas, the detection range of the rectangular area is possibly too large, so that the robot can pass through the area and is judged to be incapable of passing through the area.
Furthermore, avoidance is performed according to the position and the number of the set points of the detected obstacles. Due to the fact that the corresponding relation exists between the set point and the robot, the robot can conduct adaptive evasion according to the position and the number of the whole set area where the set point is located and a local area formed by a plurality of set points. The problem that a robot in a traditional rectangular frame detection area cannot enter the area because the whole rectangular area becomes impassable due to the existence of obstacles is solved.
Further, in step S3, when an obstacle is detected at one or more set points of the set area, it is determined that an obstacle is present.
Further, in step S1, the infrared depth sensor performs distance sampling on the designated screen area to detect the obstacle, and when the infrared detection distance returned by the designated screen area is smaller than the distance threshold, it indicates that the obstacle is detected.
Further, the step S2 is determined to be an obstacle when the detected obstacle is detected by the set point in the set area.
The robot obstacle detection system based on the infrared depth camera technology comprises an obstacle detection module, a sensor information uploading module, an information processing module and an instruction execution module which are sequentially connected, wherein the obstacle detection module is used for detecting whether an obstacle exists in a set area, a set point is divided through a picture obtained by an infrared depth sensor, the set area is formed by the set point, data returned by the infrared sensor outside the set area are filtered, obstacle information is returned when the set area detects the obstacle, the sensor information uploading module integrates and uploads information detected by the obstacle detection module to the information processing module, the information processing module judges whether the obstacle exists, and the instruction execution module executes operation for the obstacle when the information processing module judges that the obstacle exists.
Through the system, the obstacle which appears at the edge of the picture but is not in the detection area can not interfere with the obstacle identification of the normal flow, namely the obstacle can not be identified to cause flow interruption, the fault tolerance is increased, and the aim of normally carrying out the flow without interruption when the obstacle detection interference of a certain degree occurs is fulfilled.
Through the construction of the set region, the set region meets specific conditions, other region detection data are ignored, and the effects of reducing useless data quantity, reducing operation requirements and using under special conditions are achieved.
The similar function of the laser sensor with high cost can be realized through the infrared depth camera with low cost, the cost is reduced, the popularization difficulty of the product is reduced, and the competitiveness of the product is improved.
Further, the obstacle detection module comprises a setting module, wherein the setting module is used for constructing a set point and a set area formed by the set point, and matching the shape of the set area and the depth acquired by the infrared depth sensor with the shape of the robot provided with the infrared depth sensor. The traditional detection system is avoided, the whole robot range is wrapped by one rectangular area, the obstacles in the whole rectangular area are detected, and when the robot passes through some narrow areas, the detection range of the rectangular area is possibly too large, so that the robot can pass through the area, and the robot is judged to be unable to pass through the area.
Further, the information processing module calculates an avoidance maneuver according to the position and the number of the set points of the detected obstacles, and executes avoidance operation through instructions. Due to the fact that the corresponding relation exists between the set point and the robot, the robot can conduct adaptive evasion according to the position and the number of the whole set area where the set point is located and a local area formed by a plurality of set points. The problem that a robot in a traditional rectangular frame detection area cannot enter the area because the whole rectangular area becomes impassable due to the existence of obstacles is solved.
The invention has the advantages and beneficial effects that:
through regarding infrared degree of depth camera as barrier detection device to can set for detection range and reduce the interference, strengthen the ability of barrier detection environment, reduce product manufacturing cost, and all can use on special scene, detector form, widen the use scene, improve the competitiveness.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a schematic diagram of the system architecture of the present invention.
Fig. 3 is a schematic diagram of the robot in the invention.
Fig. 4 is a schematic view of a simulated robot detection perspective in the present invention.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present invention, are given by way of illustration and explanation only, not limitation.
The method comprises the steps that a picture of the whole infrared depth camera is divided into a plurality of detection points, only key obstacle regions are set as detection regions by the detection points, the infrared camera performs distance sampling on a designated picture region to detect an obstacle, when the infrared detection distance returned by the designated picture region of the camera is smaller than a designated distance, the obstacle is detected, and when the obstacle is detected by the detection points in the detection regions, the obstacle is determined to be the obstacle. Therefore, the obstacles which appear at the edge of the screen but are not in the detection area can not interfere with the obstacle recognition of the normal flow, namely the obstacles can not be recognized as the obstacles to cause flow interruption. The number, position and the like of the detection points can be set according to actual requirements.
By setting the detection area, the detection area accords with the specific condition, and other area detection data are ignored, so that the effects of reducing the amount of useless data, reducing the operation requirement and using under the special condition are achieved. For example, a detection area with a T-shaped pattern is suitable for obstacle avoidance of a robot with a wider top when the robot travels, and only the passing condition meets the T-shaped pattern, and the detection condition of the whole picture in the traditional detection is not needed.
The obstacle identification method is improved, the fault tolerance is increased, and the aim of normally performing the process without interruption when a certain degree of obstacle detection interference occurs is fulfilled. Similar functions of a high-cost laser sensor can be realized through the low-cost infrared depth camera, the popularization difficulty of products is reduced, and the competitiveness of the products is improved.
As shown in fig. 1, the robot obstacle detection method based on the infrared depth camera technology includes the following steps:
s1, receiving data of the infrared depth sensor;
s2, filtering data returned by the infrared sensor except the set point;
s3, when the set point detects the obstacle, the set point returns the obstacle information;
s4, when the plurality of set points all detect the obstacle, judging that the obstacle exists, and performing other operations such as avoiding or warning;
as shown in fig. 2, the robot obstacle detection system based on the infrared depth camera technology includes an obstacle detection module, a sensor information uploading module, an information processing module and an instruction execution module, which are connected in sequence, wherein the obstacle detection module is used for detecting whether an obstacle exists in the front, the sensor information uploading module integrates and uploads information detected by the obstacle detection module to the information processing module, the information processing module judges whether an obstacle exists, and the instruction execution module executes operations such as avoiding or warning of the information processing module when the information processing module judges that an obstacle exists.
As shown in fig. 3, the whole robot is shaped like an hourglass with large upper and lower parts and small waist, so that the detection points corresponding to the robot can be set in the line marking area, and the detection range is set to the shape of the robot. And the traditional detection mode uses a rectangular area to wrap the whole robot range to detect the obstacles in the whole rectangular area. When a narrow area is passed, the detection range using the rectangular area may be too large to determine that the area where the robot can pass through cannot pass through.
As shown in fig. 4, the detection view of the robot is simulated, only the lower left corner in the figure may be an obstacle, and the robot can avoid the obstacle to enter the area by only turning right, that is, when the obstacle is detected at some detection points, the robot can adaptively avoid the obstacle according to the position and number of the whole detection area where the detection points are located and a local area formed by a plurality of set points because the detection points and the robot have a corresponding relationship. In the case of a rectangular detection area, the entire rectangular area becomes impassable due to the presence of an obstacle, so that the area cannot enter.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A robot obstacle detection method based on an infrared deep camera technology is characterized by comprising the following steps:
s1, acquiring data of the infrared depth sensor;
s2, filtering data returned by the infrared sensors outside a set area, wherein the set area divides a picture obtained by the infrared depth sensor into set points, and the set points form the set area;
s3, when the set area detects an obstacle, the obstacle information is returned.
2. The method for detecting robot obstacle based on infrared depth camera technology as claimed in claim 1, wherein in said step S2, the shape of the set area and the depth acquired by the infrared depth sensor are matched with the shape of the robot provided with said infrared depth sensor.
3. The method of claim 2, wherein avoidance is performed according to the position and number of the set points where the obstacle is detected.
4. The method for detecting obstacles on a robot based on infrared deep camera technology as claimed in claim 1, wherein in step S3, when an obstacle is detected at one or more set points of the set area, it is determined that an obstacle is present.
5. The method for detecting robot obstacle according to claim 1, wherein in step S1, the infrared depth sensor performs distance sampling on the designated screen area, and when the infrared detection distance returned by the designated screen area is less than the distance threshold, it indicates that the obstacle is detected.
6. The method for detecting obstacles of a robot based on infrared depth camera technology as claimed in claim 5, wherein said step S2 is performed when the detected obstacle is detected by the set point in the set area and is recognized as an obstacle.
7. The robot obstacle detection system based on the infrared depth camera technology comprises an obstacle detection module, a sensor information uploading module, an information processing module and an instruction execution module which are sequentially connected, and is characterized in that the obstacle detection module is used for detecting whether an obstacle exists in a set area or not, a set point is marked out through a picture obtained by an infrared depth sensor, the set area is formed by the set point, data returned by an infrared sensor outside the set area are filtered, obstacle information is returned when the set area detects the obstacle, the sensor information uploading module integrates and uploads information detected by the obstacle detection module to the information processing module, the information processing module judges whether the obstacle exists or not, and the instruction execution module executes operation for the obstacle when the information processing module judges that the obstacle exists.
8. A robotic obstacle detection system as claimed in claim 7, in which said obstacle detection module includes a setting module for constructing a set point and a set zone formed thereby, and matching the shape of the set zone and the depth acquired by the infrared depth sensor to the shape of the robot on which the infrared depth sensor is provided.
9. The system of claim 8, wherein the information processing module calculates an avoidance maneuver according to the position and number of the set points of the detected obstacles, and performs an avoidance operation by an instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011526620.0A CN112605999B (en) | 2020-12-22 | 2020-12-22 | Robot obstacle detection method and system based on infrared deep camera technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011526620.0A CN112605999B (en) | 2020-12-22 | 2020-12-22 | Robot obstacle detection method and system based on infrared deep camera technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112605999A true CN112605999A (en) | 2021-04-06 |
| CN112605999B CN112605999B (en) | 2022-01-18 |
Family
ID=75244021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011526620.0A Active CN112605999B (en) | 2020-12-22 | 2020-12-22 | Robot obstacle detection method and system based on infrared deep camera technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112605999B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113370212A (en) * | 2021-06-25 | 2021-09-10 | 三一建筑机器人(西安)研究院有限公司 | Safe operation method, device and control system for truss manipulator |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105522592A (en) * | 2014-10-17 | 2016-04-27 | 发那科株式会社 | Apparatus for setting interference region of robot |
| CN105934774A (en) * | 2014-03-24 | 2016-09-07 | 株式会社日立制作所 | Object detection apparatus, object detection method, and mobile robot |
| CN106502267A (en) * | 2016-12-06 | 2017-03-15 | 上海师范大学 | A kind of unmanned plane avoidance system |
| CN108177162A (en) * | 2016-12-08 | 2018-06-19 | 发那科株式会社 | The interference region setting device of mobile robot |
| WO2018129648A1 (en) * | 2017-01-10 | 2018-07-19 | 深圳市极思维智能科技有限公司 | Robot and method thereof for establishing map by using deep camera and obstacle avoidance system |
| CN109551472A (en) * | 2017-09-27 | 2019-04-02 | 精工爱普生株式会社 | Robot system |
| CN109591008A (en) * | 2017-11-18 | 2019-04-09 | 广州科语机器人有限公司 | The area of safety operaton of mobile robot determines method |
| CN109940620A (en) * | 2019-04-15 | 2019-06-28 | 于傲泽 | A kind of Intelligent exploration robot and its control method |
| CN110135278A (en) * | 2019-04-23 | 2019-08-16 | 腾讯科技（上海）有限公司 | A kind of obstacle detection method, device and electronic equipment |
| CN110207702A (en) * | 2019-04-22 | 2019-09-06 | 北京云迹科技有限公司 | The method and device of target positioning |
| US20190377355A1 (en) * | 2019-07-26 | 2019-12-12 | Lg Electronics Inc. | Robot for detecting human head and control method thereof |
| KR20200023707A (en) * | 2018-08-23 | 2020-03-06 | 엘지전자 주식회사 | Moving robot |
-
2020
- 2020-12-22 CN CN202011526620.0A patent/CN112605999B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105934774A (en) * | 2014-03-24 | 2016-09-07 | 株式会社日立制作所 | Object detection apparatus, object detection method, and mobile robot |
| CN105522592A (en) * | 2014-10-17 | 2016-04-27 | 发那科株式会社 | Apparatus for setting interference region of robot |
| CN106502267A (en) * | 2016-12-06 | 2017-03-15 | 上海师范大学 | A kind of unmanned plane avoidance system |
| CN108177162A (en) * | 2016-12-08 | 2018-06-19 | 发那科株式会社 | The interference region setting device of mobile robot |
| WO2018129648A1 (en) * | 2017-01-10 | 2018-07-19 | 深圳市极思维智能科技有限公司 | Robot and method thereof for establishing map by using deep camera and obstacle avoidance system |
| CN109551472A (en) * | 2017-09-27 | 2019-04-02 | 精工爱普生株式会社 | Robot system |
| CN109591008A (en) * | 2017-11-18 | 2019-04-09 | 广州科语机器人有限公司 | The area of safety operaton of mobile robot determines method |
| KR20200023707A (en) * | 2018-08-23 | 2020-03-06 | 엘지전자 주식회사 | Moving robot |
| CN109940620A (en) * | 2019-04-15 | 2019-06-28 | 于傲泽 | A kind of Intelligent exploration robot and its control method |
| CN110207702A (en) * | 2019-04-22 | 2019-09-06 | 北京云迹科技有限公司 | The method and device of target positioning |
| CN110135278A (en) * | 2019-04-23 | 2019-08-16 | 腾讯科技（上海）有限公司 | A kind of obstacle detection method, device and electronic equipment |
| US20190377355A1 (en) * | 2019-07-26 | 2019-12-12 | Lg Electronics Inc. | Robot for detecting human head and control method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 朱涛等: "基于Kinect深度技术的障碍物在线快速检测算法", 《电子设计工程》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113370212A (en) * | 2021-06-25 | 2021-09-10 | 三一建筑机器人(西安)研究院有限公司 | Safe operation method, device and control system for truss manipulator |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112605999B (en) | 2022-01-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ge et al. | Fruit localization and environment perception for strawberry harvesting robots | |
| Kluge | Extracting road curvature and orientation from image edge points without perceptual grouping into features | |
| US20200209880A1 (en) | Obstacle detection method and apparatus and robot using the same | |
| US20160104047A1 (en) | Image recognition system for a vehicle and corresponding method | |
| CN112070838A (en) | Object identification and positioning method and device based on two-dimensional-three-dimensional fusion characteristics | |
| CN112605999B (en) | Robot obstacle detection method and system based on infrared deep camera technology | |
| Talele et al. | Detection of real time objects using TensorFlow and OpenCV | |
| CN112102409A (en) | Target detection method, device, equipment and storage medium | |
| CN110147748B (en) | Mobile robot obstacle identification method based on road edge detection | |
| CN104933392A (en) | Probabilistic people tracking using multi-view integration | |
| CN104933436A (en) | Vision-based multi-camera factory monitoring including dynamic integrity grading | |
| CN110378937B (en) | Kinect camera-based industrial mechanical arm man-machine safety distance detection method | |
| Raviteja et al. | Advanced driver assitance system (ADAS) | |
| CN116310679A (en) | Multi-sensor fusion target detection method, system, medium, equipment and terminal | |
| CN110491060A (en) | A kind of robot and its method for safety monitoring, device and storage medium | |
| CN115993597A (en) | Visual radar perception fusion method and terminal equipment | |
| CN110703760A (en) | Newly-increased suspicious object detection method for security inspection robot | |
| CN113435278A (en) | Crane safety detection method and system based on YOLO | |
| Fu et al. | Camera-based semantic enhanced vehicle segmentation for planar lidar | |
| US20150063630A1 (en) | Apparatus and method for detecting obstacle | |
| CN114332732A (en) | Railway crisis monitoring method based on radar vision fusion | |
| KR20200068045A (en) | Around view monitoring system and method for detecting parking line with deep learning | |
| CN117787690A (en) | Hoisting operation safety risk identification method and identification device | |
| JP2022064388A (en) | Object recognition device | |
| CN111144415A (en) | Method for detecting micro pedestrian target |
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 |