CN113591727A - Traffic signal recognition device of distribution robot - Google Patents
Traffic signal recognition device of distribution robot Download PDFInfo
- Publication number
- CN113591727A CN113591727A CN202110885318.2A CN202110885318A CN113591727A CN 113591727 A CN113591727 A CN 113591727A CN 202110885318 A CN202110885318 A CN 202110885318A CN 113591727 A CN113591727 A CN 113591727A
- Authority
- CN
- China
- Prior art keywords
- image
- filter
- traffic signal
- image acquisition
- image processor
- 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
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000000605 extraction Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009466 transformation 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
- G06T7/90—Determination of colour characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
-
- 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
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a traffic signal recognition device for a distribution robot, which comprises an image acquisition device, a signal processing device, a control module and a signal output device which are sequentially connected, wherein the control module is also connected with the image acquisition device, the image acquisition device comprises an image acquisition module and a light compensation module, and the image acquisition module is used for recognizing and acquiring traffic signals to obtain original images; the light compensation module can be automatically started to judge whether the current state needs to be subjected to light compensation for image acquisition; the signal processing device is used for processing the original image to obtain an identification result; the signal output device is used for outputting the identification result. The device can effectively improve the accuracy rate of the distribution robot for identifying the traffic signals and reduce the safety problem in the distribution process.
Description
Technical Field
The invention belongs to the technical field of intelligent robots, and particularly relates to a traffic signal recognition device of a distribution robot.
Background
In recent years, with the development of information technology, automatic control technology, communication technology and the like, robots are enabled to enter people's daily life, and it becomes possible to change people's life style, and the research on service robots gradually enters people's sight.
With article delivery in the current domestic logistics industry, the mode that adopts artifical delivery is mostly, along with electronic commerce's the rise, logistics company constantly increases, and logistics distribution personnel constantly increases, cost of labor greatly increased, and the equal delivery pressure of people is big, often appears delaying, send the wrong condition. In addition, for frequent cargo transportation distribution among factory warehouses, the robot distribution is more incomparable. However, the current logistics distribution robot has a single function, often runs according to a set program and a set route, cannot meet the distribution requirements of indoor and outdoor environments at the same time, does not have the logistics distribution capability of complex environments, runs in a single machine, is not supported by a network system, and has the problems of unretraceable distribution process and the like. The traffic signal identification technology is an important technical link of research in the field of distribution robots, so that how to improve the automatic identification accuracy of traffic signals is very important.
Disclosure of Invention
The invention aims to improve the identification accuracy of the robot to the traffic sign and reduce the safety problem in the distribution process.
In order to achieve the above object, the invention adopts the following technical scheme that the distribution robot traffic signal recognition device comprises an image acquisition device, a signal processing device, a control module and a signal output device which are connected in sequence, wherein the control module is also connected with the image acquisition device,
the image acquisition device comprises an image acquisition module and a light compensation module, wherein the image acquisition module is used for identifying and acquiring traffic signals to obtain an original image; the light compensation module can be automatically started to judge whether the current state needs to be subjected to light compensation for image acquisition;
the signal processing device is used for processing the original image to obtain an identification result;
the signal output device is used for outputting a recognition result;
the control module is used for controlling the operation of the identification device.
Preferably, the signal processing apparatus includes:
the primary image processor is used for preprocessing an original image;
a secondary image processor for recognizing color information of the traffic signal;
a three-level image processor for recognizing shape information of the traffic signal;
the control module is respectively connected with the primary image processor, the secondary image processor and the tertiary image processor.
Preferably, the first-stage image processor comprises a first filter, a second filter and a third filter which are connected in sequence, and the first filter performs binarization processing on the original image to obtain a first image;
the second filter carries out smoothing processing on the first image to obtain a second image;
and the third filter carries out edge extraction on the second image to obtain a weight image for distinguishing a background area from a target area.
Preferably, the evaluation of each pixel in the weighted image shows a luminance corresponding to the importance value, the weight of all pixels belonging to the target region is set to 1.0, the weight of all pixels belonging to the background region is set to 0.3, and the weight of all pixels tangent to a straight line between the target region and the background region is set to 0.1.
Preferably, the two-level image processor includes: a fourth filter that identifies color information of the traffic signal.
Preferably, the extraction colours are in particular: in the extracted target region, color information is extracted by comparison with the original image.
Preferably, the fourth filter comprises an HSB component: and the hue filter, the saturation filter and the brightness filter respectively correspond to three components of hue H, saturation S and brightness B in the color information, and the output image of the HSB component synthesizes the color information to obtain a color output image.
Preferably, the three-stage image processor includes a fifth filter for recognizing shape information of the traffic signal,
the fifth filter comprises a sixth filter, a seventh filter and an eighth filter which are respectively used for extracting the circular, humanoid and regular arrow traffic signal signs.
The invention has the technical effects that: according to the invention, the light compensation module is arranged to provide light compensation for the image acquisition module, so that images with higher quality can be shot even in an environment with poor light, and then the images are automatically and effectively identified, so that the identification accuracy of traffic signals is improved, a guarantee is provided for realizing autonomous distribution, the potential safety hazard of manual distribution is effectively solved, and the distribution efficiency is improved.
Drawings
Fig. 1 is a schematic structural diagram of an embodiment of the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
As shown in fig. 1, a traffic signal recognition device for a distribution robot comprises an image acquisition device, a signal processing device, a control module and a signal output device, which are connected in sequence, wherein the control module is further connected with the image acquisition device,
the image acquisition device comprises an image acquisition module and a light compensation module, wherein the image acquisition module is used for identifying and acquiring traffic signals to obtain an original image; the light compensation module can be automatically started to judge whether the current state needs to be subjected to light compensation for image acquisition;
the signal processing device is used for processing the original image to obtain an identification result;
the signal output device is used for outputting a recognition result;
the control module is used for controlling the operation of the identification device;
the control module is used for controlling the operation of the identification device.
In a further preferred embodiment, the signal processing apparatus includes:
the primary image processor is used for preprocessing an original image;
a secondary image processor for recognizing color information of the traffic signal;
a three-level image processor for recognizing shape information of the traffic signal;
the control module is respectively connected with the primary image processor, the secondary image processor and the tertiary image processor.
According to a further optimization scheme, the primary image processor comprises a first filter, a second filter and a third filter which are sequentially connected, and the first filter is used for carrying out binarization processing on an original image to obtain a first image;
the second filter carries out smoothing processing on the first image to obtain a second image;
and the third filter carries out edge extraction on the second image to obtain a weight image for distinguishing a background area from a target area.
Further optimization, the evaluation of each pixel in the weighted image shows a luminance corresponding to the importance value, the weight of all pixels belonging to the target area is set to 1.0, the weight of all pixels belonging to the background area is set to 0.3, and the weight of all pixels tangent to a straight line between the target area and the background area is set to 0.1 in consideration of the fluctuation range.
In a further refinement, the secondary image processor comprises: a fourth filter that identifies color information of the traffic signal.
Further optimizing the scheme, the extracted color is specifically as follows: in the extracted target region, color information is extracted by comparison with the original image.
In a further optimization, the fourth filter includes an HSB component: the hue filter, saturation filter, and luminance filter correspond to three components of hue H, saturation S, and luminance B in the color information, respectively, and a genetic algorithm is applied to three independent groups, corresponding to three different images divided into three HSB components, and the output images of the HSB components synthesize the color information to obtain a color output image. In this embodiment, the hue filter, the saturation filter, and the luminance filter are applied to the HSB component into which the color input image is divided, and the color information is synthesized by using the output image of the HSB component, thereby obtaining a color output image.
In a further optimized scheme, the three-level image processor comprises a fifth filter used for identifying the shape information of the traffic signal,
the fifth filter comprises a sixth filter, a seventh filter and an eighth filter which are respectively used for extracting the circular, humanoid and regular arrow traffic signal signs.
In this embodiment, the traffic sign is displayed as a regular perfect circle in the circular traffic sign, three line segments of the formed arrow in the arrow-shaped traffic sign intersect at the vertex, and the human-shaped traffic sign is compared with the human-shaped database to find the corresponding sign. The traffic signal signs of all kinds of humanoid forms are stored in the humanoid database.
Taking a circular traffic sign as an example, in an image obtained after masking, an area where the circular traffic sign is performed is black, and a background area is white.
In the Hough transform, a circle in an image space can be mapped to one point in a three-dimensional parameter space, and since the circle in the image space can be expressed as three parameters of center coordinates and radius coordinates, the circle in the image space can be detected by obtaining a specific point in the parameter space.
In this filter, pixels larger than 127 in the input image are defined as feature points; moreover, the Hough transformation takes the characteristic points as targets; all pixels belonging to the inner region have the highest value and all pixels belonging to other regions have the lowest value in each circle detected by the Hough transform.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. A distribution robot traffic signal recognition device is characterized by comprising an image acquisition device, a signal processing device, a control module and a signal output device which are sequentially connected, wherein the control module is also connected with the image acquisition device,
the image acquisition device comprises an image acquisition module and a light compensation module, wherein the image acquisition module is used for identifying and acquiring traffic signals to obtain an original image; the light compensation module can be automatically started to judge whether the current state needs to be subjected to light compensation for image acquisition;
the signal processing device is used for processing the original image to obtain an identification result;
the signal output device is used for outputting a recognition result;
the control module is used for controlling the operation of the identification device.
2. The delivery robot traffic signal recognition device of claim 1, wherein the signal processing device comprises:
the primary image processor is used for preprocessing an original image;
a secondary image processor for recognizing color information of the traffic signal;
a three-level image processor for recognizing shape information of the traffic signal;
the control module is respectively connected with the primary image processor, the secondary image processor and the tertiary image processor.
3. The distribution robot traffic signal recognition device of claim 2, wherein the primary image processor comprises a first filter, a second filter and a third filter which are connected in sequence, the first filter performs binarization processing on an original image to obtain a first image;
the second filter carries out smoothing processing on the first image to obtain a second image;
and the third filter carries out edge extraction on the second image to obtain a weight image for distinguishing a background area from a target area.
4. The delivery robot traffic signal recognition apparatus according to claim 3, wherein the evaluation of each pixel in the weight image shows a brightness corresponding to the importance value, the weight of all pixels belonging to the target area is set to 1.0, the weight of all pixels belonging to the background area is set to 0.3, and the weight of all pixels tangent to a straight line between the target area and the background area is set to 0.1.
5. The distribution robot traffic signal recognition device of claim 2, wherein the secondary image processor comprises: a fourth filter that identifies color information of the traffic signal.
6. The distribution robot traffic signal recognition apparatus of claim 5, wherein the extracted colors are specifically: in the extracted target region, color information is extracted by comparison with the original image.
7. The dispensing robot traffic signal identifying device of claim 5, wherein the fourth filter comprises an HSB component: and the hue filter, the saturation filter and the brightness filter respectively correspond to three components of hue H, saturation S and brightness B in the color information, and the output image of the HSB component synthesizes the color information to obtain a color output image.
8. The dispensing robot traffic signal recognition device of claim 2, wherein the three-stage image processor includes a fifth filter for recognizing shape information of the traffic signal,
the fifth filter comprises a sixth filter, a seventh filter and an eighth filter which are respectively used for extracting the circular, humanoid and regular arrow traffic signal signs.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110885318.2A CN113591727A (en) | 2021-08-03 | 2021-08-03 | Traffic signal recognition device of distribution robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110885318.2A CN113591727A (en) | 2021-08-03 | 2021-08-03 | Traffic signal recognition device of distribution robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113591727A true CN113591727A (en) | 2021-11-02 |
Family
ID=78254280
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110885318.2A Pending CN113591727A (en) | 2021-08-03 | 2021-08-03 | Traffic signal recognition device of distribution robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113591727A (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103500341A (en) * | 2013-09-16 | 2014-01-08 | 安徽工程大学 | Recognition device used for road signboard |
CN105930819A (en) * | 2016-05-06 | 2016-09-07 | 西安交通大学 | System for real-time identifying urban traffic lights based on single eye vision and GPS integrated navigation system |
CN105930791A (en) * | 2016-04-19 | 2016-09-07 | 重庆邮电大学 | Road traffic sign identification method with multiple-camera integration based on DS evidence theory |
CN205992299U (en) * | 2016-08-25 | 2017-03-01 | 泉州理工职业学院 | A kind of automatic identification system of road traffic sign |
CN107506760A (en) * | 2017-08-04 | 2017-12-22 | 西南大学 | Traffic signals detection method and system based on GPS location and visual pattern processing |
CN208511466U (en) * | 2017-12-26 | 2019-02-19 | 广东数相智能科技有限公司 | A kind of guide blind walking stick |
CN208781399U (en) * | 2018-09-29 | 2019-04-23 | 深圳市拓必达科技有限公司 | One kind being based on intelligent transportation pattern recognition device |
CN111144218A (en) * | 2019-11-29 | 2020-05-12 | 中科曙光(南京)计算技术有限公司 | Traffic sign identification method and device in vehicle driving process |
CN112329556A (en) * | 2020-10-20 | 2021-02-05 | 北京理工大学珠海学院 | Traffic sign detection method and device, electronic equipment and storage medium |
US20210042886A1 (en) * | 2018-03-19 | 2021-02-11 | Sony Corporation | Image processing apparatus, image processing method, and program |
CN113191255A (en) * | 2021-04-28 | 2021-07-30 | 浙江大学 | Traffic sign identification method based on mobile robot |
-
2021
- 2021-08-03 CN CN202110885318.2A patent/CN113591727A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103500341A (en) * | 2013-09-16 | 2014-01-08 | 安徽工程大学 | Recognition device used for road signboard |
CN105930791A (en) * | 2016-04-19 | 2016-09-07 | 重庆邮电大学 | Road traffic sign identification method with multiple-camera integration based on DS evidence theory |
CN105930819A (en) * | 2016-05-06 | 2016-09-07 | 西安交通大学 | System for real-time identifying urban traffic lights based on single eye vision and GPS integrated navigation system |
CN205992299U (en) * | 2016-08-25 | 2017-03-01 | 泉州理工职业学院 | A kind of automatic identification system of road traffic sign |
CN107506760A (en) * | 2017-08-04 | 2017-12-22 | 西南大学 | Traffic signals detection method and system based on GPS location and visual pattern processing |
CN208511466U (en) * | 2017-12-26 | 2019-02-19 | 广东数相智能科技有限公司 | A kind of guide blind walking stick |
US20210042886A1 (en) * | 2018-03-19 | 2021-02-11 | Sony Corporation | Image processing apparatus, image processing method, and program |
CN208781399U (en) * | 2018-09-29 | 2019-04-23 | 深圳市拓必达科技有限公司 | One kind being based on intelligent transportation pattern recognition device |
CN111144218A (en) * | 2019-11-29 | 2020-05-12 | 中科曙光(南京)计算技术有限公司 | Traffic sign identification method and device in vehicle driving process |
CN112329556A (en) * | 2020-10-20 | 2021-02-05 | 北京理工大学珠海学院 | Traffic sign detection method and device, electronic equipment and storage medium |
CN113191255A (en) * | 2021-04-28 | 2021-07-30 | 浙江大学 | Traffic sign identification method based on mobile robot |
Non-Patent Citations (3)
Title |
---|
JESMIN F. KHAN等: "Image Segmentation and Shape Analysis for Road-Sign Detection", 《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》, vol. 12, no. 1, 31 March 2011 (2011-03-31), pages 83 - 96, XP011348835, DOI: 10.1109/TITS.2010.2073466 * |
吕凯凯等: "基于HSB 颜色空间的交通标志识别研究", 《赤峰学院学报(自然科学版)》, vol. 35, no. 5, 31 May 2019 (2019-05-31), pages 36 - 38 * |
徐华青等: "道路交通标志检测分类方法的研究", 《微型机与应用》, vol. 31, no. 15, 31 December 2012 (2012-12-31), pages 37 - 38 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108108761B (en) | Rapid traffic signal lamp detection method based on deep feature learning | |
CN102142084B (en) | Method for gesture recognition | |
CN102012939B (en) | Method for automatically tagging animation scenes for matching through comprehensively utilizing overall color feature and local invariant features | |
CN110414559B (en) | Construction method of intelligent retail cabinet commodity target detection unified framework and commodity identification method | |
CN102819728A (en) | Traffic sign detection method based on classification template matching | |
CN109460715A (en) | A kind of traffic lights automatic identification implementation method based on machine learning | |
CN112733914B (en) | Underwater target visual identification classification method based on support vector machine | |
CN108197521A (en) | A kind of leggy Quick Response Code obtains identification device and method | |
CN112847321B (en) | Industrial robot visual image recognition system based on artificial intelligence | |
WO2022257807A1 (en) | Positioning apparatus based on passive infrared tag | |
CN113034624A (en) | Temperature early warning image identification method, system, equipment and storage medium based on temperature sensing color-changing adhesive tape | |
CN110633635A (en) | ROI-based traffic sign board real-time detection method and system | |
CN111712021A (en) | Intelligent adjusting method, device and system for lamplight of art gallery | |
CN105976407A (en) | Method for identifying plate shapes under shielding condition | |
CN111242057A (en) | Product sorting system, method, computer device and storage medium | |
CN113902641A (en) | Data center hot area distinguishing method and system based on infrared image | |
CN104574377A (en) | Method for correcting yellow cast of red lamp of electronic police | |
CN112818853A (en) | Traffic element identification method, device, equipment and storage medium | |
CN108427954B (en) | Label information acquisition and recognition system | |
CN113591727A (en) | Traffic signal recognition device of distribution robot | |
CN113408409A (en) | Traffic signal lamp identification method and equipment, cloud control platform and vehicle-road cooperative system | |
Jia et al. | Design of Traffic Sign Detection and Recognition Algorithm Based on Template Matching | |
CN116311132A (en) | Deceleration strip identification method, deceleration strip identification device, deceleration strip identification equipment and storage medium | |
CN111340897A (en) | Color identification method based on fuzzy mathematical similarity | |
Mukhopadhyay et al. | Comparing shape descriptor methods for different color space and lighting conditions |
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 |