CN110427873A - A kind of cleaning vehicle, the intelligent pedestrian antispray system and method applied to field of sanitation - Google Patents
A kind of cleaning vehicle, the intelligent pedestrian antispray system and method applied to field of sanitation Download PDFInfo
- Publication number
- CN110427873A CN110427873A CN201910703474.5A CN201910703474A CN110427873A CN 110427873 A CN110427873 A CN 110427873A CN 201910703474 A CN201910703474 A CN 201910703474A CN 110427873 A CN110427873 A CN 110427873A
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- intelligent
- module
- video
- antispray
- 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
Classifications
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01H—STREET CLEANING; CLEANING OF PERMANENT WAYS; CLEANING BEACHES; DISPERSING OR PREVENTING FOG IN GENERAL CLEANING STREET OR RAILWAY FURNITURE OR TUNNEL WALLS
- E01H3/00—Applying liquids to roads or like surfaces, e.g. for dust control; Stationary flushing devices
- E01H3/02—Mobile apparatus, e.g. watering-vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Multimedia (AREA)
- Civil Engineering (AREA)
- Architecture (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Structural Engineering (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of cleaning vehicle, applied to the intelligent pedestrian antispray system and method for field of sanitation, system includes: vision collecting module, is set in cleaning vehicle and for carrying out real time video collection to the road surface for needing to clean watering;Master board, the master board include the video processing module for being handled the video that video acquisition module acquires, and identify the intelligent algorithm module of the pedestrian target occurred in video, and send the electronic control module for stopping the control signal of water spray;The intelligent algorithm module uses YOLOV3 algorithm, core network darknet53.The present invention can realize the intelligent water sprinkling operation of cleaning vehicle with intelligent recognition cleaning vehicle job area pedestrian, avoid splash pedestrian, and can greatly reduce distraction of operating personnel during cleaning sprinkler operation, promote the safety of driving.
Description
Technical field
The invention belongs to intelligent science and technology fields, and in particular to a kind of cleaning vehicle, the intelligent row applied to field of sanitation
People's air defense spray system and method.
Background technique
In current urban road cleaning, mechanized cleaning vehicle, such as low pressure sprinkling truck, high-pressure washing vehicle are by widely
It uses.However, can not identify to vehicle periphery pedestrian in the existing cleaning vehicle course of work, operating personnel needs driving
Whether there is or not pedestrians in observation job area while vehicle, manually control cleaning sprinkler switch, attention is difficult to concentrate, and influences to drive a vehicle
Safety.And by manual control sprinkler switch, vehicle cannot independently evade the pedestrian in job area, bath spray often occur
The case where splashing pedestrian denounces by masses.
From the above, it would be highly desirable to which a kind of intelligent pedestrian antispray system applied to field of sanitation solves modern city
Road cleans the contradiction between the status of low intelligent, low hommization and intelligent, the humanized inexorable trend of urban development.
Summary of the invention
To solve the above-mentioned problems, the present invention provides a kind of intelligent pedestrian antispray system applied to field of sanitation,
When cleaning vehicle cleans road surface, the case where cleaning water projection be'ss to pedestrian generation is avoided.
The technical solution of the present invention is as follows: a kind of intelligent pedestrian antispray system applied to field of sanitation, comprising:
Vision collecting module is set in cleaning vehicle and for adopting to the road surface progress real-time video for needing cleaning watering
Collection;
Master board, the master board include at the video for being handled the video that video acquisition module acquires
Module is managed, identifies the intelligent algorithm module of the pedestrian target occurred in video, and sends the control signal for stopping water spray
Electronic control module;
The intelligent algorithm module uses YOLOV3 algorithm, core network darknet53.
Preferably, core network layer type includes convolutional layer and residual error network layer, convolutional layer information includes convolution kernel
Number and convolution kernel size, characteristic pattern size indicate the network layer Output Size.
Preferably, detection layer includes the convolved set for feature extraction, for being by the size up-sampling of characteristic pattern
The up-sampling layer of twice originally, and the splicing layer for the characteristic pattern under different scale to be spliced together, the convolution
Set is made of the convolution kernel of 1 × 1 and 3 × 3.
Preferably, feature extraction is carried out by darknet53, then by merging the characteristic pattern under three kinds of different scales,
The confidence level and bounding box (x, y, w, h) of pedestrian in prediction input picture, three kinds of different scales are respectively 13 × 13,26
× 26 and 52 × 52.
The present invention also provides a kind of intelligent pedestrian antispray methods applied to field of sanitation, comprising the following steps:
(1) vision collecting module is set on the car body of cleaning vehicle, watering is cleaned to needs by vision collecting module
Road surface carries out real time video collection;
(2) video that vision collecting module acquires is handled by video processing module, passes through intelligent algorithm module
The pedestrian target occurred in video is identified, if being normally carried out washing and cleaning operation without pedestrian in cleaning vehicle working range;If cleaning
Occurs pedestrian in vehicle working range, then electronic control module sends control signal, closes outlet valve, and wherein intelligent algorithm module uses
YOLOV3 algorithm, core network darknet53, the pedestrian detection frame of model output prediction is in current survey image region
The pixel of center point coordinate (x, y) and corresponding detection block is wide high (w, h), can reduce pedestrian's erroneous detection by the way that detection threshold value is arranged
Rate is calculated friendship and the ratio of detection block using non-maxima suppression algorithm, judges whether detection block is same target.
Preferably, core network layer type includes convolutional layer and residual error network layer, convolutional layer information includes convolution kernel
Number and convolution kernel size, characteristic pattern size indicate the network layer Output Size.
Preferably, detection layer includes the convolved set for feature extraction, for being by the size up-sampling of characteristic pattern
The up-sampling layer of twice originally, and the splicing layer for the characteristic pattern under different scale to be spliced together, the convolution
Set is made of the convolution kernel of 1 × 1 and 3 × 3.
Preferably, feature extraction is carried out by darknet53, then by merging the characteristic pattern under three kinds of different scales,
The confidence level and bounding box (x, y, w, h) of pedestrian in prediction input picture, three kinds of different scales are respectively 13 × 13,26
× 26 and 52 × 52.
Preferably, being spilt apart from cleaning vehicle when judging whether to have pedestrian in working range in the step (2) pedestrian
The distance of water valve is judged that judgment step includes: pedestrian's distance detection algorithm, outside by calibration for cameras (vision collecting module)
Ginseng, the pedestrian's centre coordinate predicted using algorithm of target detection and the detection high information of frame width, are mapped to camera for image coordinate
Coordinate system, calculates the relative distance and angle of pedestrian target Yu camera and sprinkler valve, and then calculates pedestrian for sprinkler valve
Relative level and vertical range.
If the relative level of pedestrian and sprinkler valve distance is greater than watering distance, the pedestrian detected will not trigger watering
Valve control shutdown signal, sprinkler valve are in normally open;When the relative level on pedestrian and sprinkling truck distance is less than watering distance
If, if the Relative vertical of pedestrian and sprinkler valve distance is less than safe distance, then controller issues shutdown signal, sprinkler valve
In normally off, the relative distance cut down to pedestrian and watering opens sprinkler valve greater than safe distance later.
The present invention also provides a kind of cleaning vehicles, the water injector including car body and for spraying water to road surface, the spray
Water installations include outlet valve, further include above-mentioned intelligent pedestrian antispray system, and the outlet valve is controlled by the electronic control module,
The video processing module handles the video that vision collecting module acquires, and is identified in video by intelligent algorithm module
The pedestrian target of appearance, if being normally carried out washing and cleaning operation without pedestrian in cleaning vehicle working range;If in cleaning vehicle working range
There is pedestrian, then electronic control module sends control signal, closes outlet valve.
When the present invention is run, after connecting power supply, power module converts the supply voltage of external world's input to certain voltage
Value gives entire intelligent pedestrian antispray system power supply, the letter on the vision collecting module acquisition road of the operation of system starting immediately
Breath, and real-time Transmission is to the video processing module in master board, video processing module from vision collecting module to acquiring
Video information is handled, and intelligent algorithm module quickly identifies the pedestrian position information in video.It can be preset in the present invention
Certain operation warning region, when pedestrian is in warning region, system output pause sprinkler operation signal to electronic control module.
Then, electronic control module acts, and closes outlet valve, until pedestrian passes through, realizes the intelligent pedestrian antispray of environmental sanitation cleaning vehicle.
Compared with prior art, the beneficial effects of the present invention are embodied in:
The present invention can be realized the intelligent water sprinkling operation of cleaning vehicle, be avoided spraying with intelligent recognition cleaning vehicle job area pedestrian
Pedestrian is splashed, and can greatly reduce distraction of operating personnel during cleaning sprinkler operation, promotes the safety of driving
Property.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of cleaning vehicle in the present invention.
Fig. 2 is intelligent pedestrian antispray system and device schematic diagram in the present invention.
Fig. 3 is the schematic illustration that YOLOV3 algorithm is used in the present invention.
1, vision collecting module;2, car body;3, driving direction;4, master control borad;5, power module;6, data transmission interface;
7, system casing.
Specific embodiment
As depicted in figs. 1 and 2, the present invention includes car body 2 and the water injector for spraying water to road surface, the water spray dress
It sets including outlet valve, further includes intelligent pedestrian antispray system, wherein intelligent pedestrian antispray system, comprising:
Vision collecting module 1 is set in cleaning vehicle and for adopting to the road surface progress real-time video for needing cleaning watering
Collection;
Master board 4, the master board include the video for being handled the video that video acquisition module acquires
Processing module identifies the intelligent algorithm module of the pedestrian target occurred in video, and sends the control signal for stopping water spray
Electronic control module.
Outlet valve is controlled by the electronic control module, and the video that the video processing module acquires vision collecting module carries out
Processing, identifies the pedestrian target occurred in video by intelligent algorithm module, if without pedestrian in cleaning vehicle working range, just
Often carry out washing and cleaning operation;If occurring pedestrian in cleaning vehicle working range, electronic control module sends control signal, closes outlet valve.
Wherein, as shown in figure 3, intelligent algorithm module uses YOLOV3 algorithm in the present invention, core network is
darknet53.Wherein, core network layer type includes Convolutional (convolutional layer), Residual (residual error network
Layer), convolutional layer information includes convolution kernel number and convolution kernel size, and characteristic pattern size indicates the network layer Output Size, left side
1 × 1 indicate that such calculating process has been used once.Detecting layer mainly includes Convolutional Set (convolved set), Up
Sample (up-sampling layer), Concatenate (splicing layer).Wherein Convolutional Set by 1 × 1,3 × 3 convolution kernel
Composition, major function are characterized extraction;The size up-sampling of feature map is original two by Up sample major function
Times;Feature map under different scale is mainly spliced together by Concatenate.Pedestrian detect network mainly by
Darknet53 carries out feature extraction, then by under three kinds of fusions, three kinds of different scales (13 × 13,26 × 26,52 × 52)
Characteristic pattern, prediction input the confidence level and bounding box (x, y, w, h) of pedestrian in picture.
The principle of the present invention are as follows:
When the present invention is run, after connecting power supply, power module 5 converts the supply voltage of external world's input to certain voltage
Value gives entire intelligent pedestrian antispray system power supply, the letter on the vision collecting module acquisition road of the operation of system starting immediately
Breath, and real-time Transmission is to the video processing module in master board, video processing module from vision collecting module to acquiring
Video information is handled, and intelligent algorithm module quickly identifies the pedestrian position information in video.It can be preset in the present invention
Certain operation warning region, when pedestrian is in warning region, system output pause sprinkler operation signal to electronic control module.
Then, electronic control module acts, and closes outlet valve, until pedestrian passes through, realizes the intelligent pedestrian antispray of environmental sanitation cleaning vehicle.
When judging whether to have pedestrian in working range, the distance of the sprinkler valve to pedestrian apart from cleaning vehicle judges, sentences
Disconnected step includes: pedestrian's distance detection algorithm, is joined outside by calibration for cameras (vision collecting module), pre- using algorithm of target detection
The pedestrian's centre coordinate and the detection high information of frame width measured, are mapped to camera coordinates system for image coordinate, calculate pedestrian target
With the relative distance and angle of camera and sprinkler valve, and then pedestrian is calculated for the relative level and vertical range of sprinkler valve.
If the relative level of pedestrian and sprinkler valve distance is greater than watering distance, the pedestrian detected will not trigger watering
Valve control shutdown signal, sprinkler valve are in normally open;When the relative level on pedestrian and sprinkling truck distance is less than watering distance
If, if the Relative vertical of pedestrian and sprinkler valve distance is less than safe distance, then controller issues shutdown signal, sprinkler valve
In normally off, the relative distance cut down to pedestrian and watering opens sprinkler valve greater than safe distance later.
Claims (10)
1. a kind of intelligent pedestrian antispray system applied to field of sanitation characterized by comprising
Vision collecting module is set in cleaning vehicle and for carrying out real time video collection to the road surface for needing to clean watering;
Master board, the master board include the video processing mould for being handled the video that video acquisition module acquires
Block identifies the intelligent algorithm module of the pedestrian target occurred in video, and sends the automatically controlled of the control signal for stopping water spray
Module;
The intelligent algorithm module uses YOLOV3 algorithm, core network darknet53.
2. being applied to the intelligent pedestrian antispray system of field of sanitation as described in claim 1, which is characterized in that core network
Layer type includes convolutional layer and residual error network layer, and convolutional layer information includes that convolution kernel number and convolution kernel size, characteristic pattern are big
Small expression network layer Output Size.
3. being applied to the intelligent pedestrian antispray system of field of sanitation as claimed in claim 2, which is characterized in that detection layer packet
It is twice original of up-sampling layer for up-sampling the size of characteristic pattern containing the convolved set for feature extraction, and
Splicing layer for the characteristic pattern under different scale to be spliced together, the convolved set by 1 × 1 and 3 × 3 convolution kernel group
At.
4. being applied to the intelligent pedestrian antispray system of field of sanitation as claimed in claim 3, which is characterized in that by
Darknet53 carries out feature extraction, and then by the characteristic pattern under three kinds of different scales of fusion, prediction inputs pedestrian in picture
Confidence level and bounding box (x, y, w, h), three kinds of different scales are respectively 13 × 13,26 × 26 and 52 × 52.
5. a kind of intelligent pedestrian antispray method applied to field of sanitation, which comprises the following steps:
(1) vision collecting module is set on the car body of cleaning vehicle, by vision collecting module to the road surface for needing to clean watering
Carry out real time video collection;
(2) video that vision collecting module acquires is handled by video processing module, is identified by intelligent algorithm module
The pedestrian target occurred in video out, if being normally carried out washing and cleaning operation without pedestrian in cleaning vehicle working range;If cleaning turner
Make occur pedestrian in range, then electronic control module sends control signal, closes outlet valve, and wherein intelligent algorithm module uses YOLOV3
Algorithm, core network darknet53.
6. being applied to the intelligent pedestrian antispray method of field of sanitation as claimed in claim 5, which is characterized in that core network
Layer type includes convolutional layer and residual error network layer, and convolutional layer information includes that convolution kernel number and convolution kernel size, characteristic pattern are big
Small expression network layer Output Size.
7. being applied to the intelligent pedestrian antispray method of field of sanitation as claimed in claim 6, which is characterized in that detection layer packet
It is twice original of up-sampling layer for up-sampling the size of characteristic pattern containing the convolved set for feature extraction, and
Splicing layer for the characteristic pattern under different scale to be spliced together, the convolved set by 1 × 1 and 3 × 3 convolution kernel group
At.
8. the use as claimed in claim 7 in the intelligent pedestrian antispray method of field of sanitation, which is characterized in that by
Darknet53 carries out feature extraction, and then by the characteristic pattern under three kinds of different scales of fusion, prediction inputs pedestrian in picture
Confidence level and bounding box (x, y, w, h), three kinds of different scales are respectively 13 × 13,26 × 26 and 52 × 52.
9. the use as claimed in claim 7 in the intelligent pedestrian antispray method of field of sanitation, which is characterized in that the step
(2) when judging whether to have pedestrian in working range in, the distance of the sprinkler valve to pedestrian apart from cleaning vehicle judges, judges to walk
It suddenly include: the pedestrian's centre coordinate and detection block predicted using algorithm of target detection by joining outside calibration vision collecting module
Image coordinate is mapped to vision collecting module coordinate system by the high information of width, calculates pedestrian target and vision collecting module and clearly
The relative distance and angle of the sprinkler valve of carwash, so calculate pedestrian for sprinkler valve relative level distance and vertically away from
From;
When the relative level of pedestrian and sprinkler valve distance be greater than watering apart from when, the pedestrian detected will not trigger sprinkler valve control
Device shutdown signal, sprinkler valve are in normally open;When the relative level on pedestrian and sprinkling truck distance be less than watering distance, and when row
If the Relative vertical of people and sprinkler valve distance is less than safe distance, then electronic control module issues shutdown signal, and sprinkler valve is in normal
Closed state, the relative distance cut down to pedestrian and watering open sprinkler valve greater than safe distance later.
10. a kind of cleaning vehicle, the water injector including car body and for spraying water to road surface, the water injector include water outlet
Valve, which is characterized in that further include the intelligent pedestrian antispray system as described in Claims 1 to 4 is any, the outlet valve is controlled
In the electronic control module, the video processing module handles the video that vision collecting module acquires, and passes through intelligent algorithm
Module identifies the pedestrian target occurred in video, if being normally carried out washing and cleaning operation without pedestrian in cleaning vehicle working range;If
Occurs pedestrian in cleaning vehicle working range, then electronic control module sends control signal, closes outlet valve.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910703474.5A CN110427873B (en) | 2019-07-31 | 2019-07-31 | Cleaning vehicle, intelligent pedestrian anti-splashing system and method applied to sanitation field |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910703474.5A CN110427873B (en) | 2019-07-31 | 2019-07-31 | Cleaning vehicle, intelligent pedestrian anti-splashing system and method applied to sanitation field |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110427873A true CN110427873A (en) | 2019-11-08 |
CN110427873B CN110427873B (en) | 2023-06-30 |
Family
ID=68413483
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910703474.5A Active CN110427873B (en) | 2019-07-31 | 2019-07-31 | Cleaning vehicle, intelligent pedestrian anti-splashing system and method applied to sanitation field |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110427873B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111091110A (en) * | 2019-12-24 | 2020-05-01 | 山东仁功智能科技有限公司 | Wearing identification method of reflective vest based on artificial intelligence |
CN111178223A (en) * | 2019-12-24 | 2020-05-19 | 苏州奥创智能科技有限公司 | Watering method of watering cart, automatic watering control system, main control box and watering cart |
CN111218911A (en) * | 2019-12-17 | 2020-06-02 | 苏州奥创智能科技有限公司 | Energy-saving system and energy-saving method applied to road sweeping cleaning vehicle |
CN111485524A (en) * | 2020-04-16 | 2020-08-04 | 新石器慧通(北京)科技有限公司 | Spraying control method, spraying vehicle and storage medium |
CN112000102A (en) * | 2020-08-27 | 2020-11-27 | 江苏徐工信息技术股份有限公司 | Sprinkler mis-spraying prevention system and method based on video detection and GPS |
CN112092732A (en) * | 2020-09-22 | 2020-12-18 | 福建龙马环卫装备股份有限公司 | Image recognition-based road sanitation vehicle operation device control system and method |
CN112214016A (en) * | 2020-09-08 | 2021-01-12 | 上海汽车集团股份有限公司 | Road operation vehicle intelligent operation system and operation method based on vision |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008191815A (en) * | 2007-02-02 | 2008-08-21 | Mazda Motor Corp | Vehicular safety support device |
CN109614957A (en) * | 2019-01-04 | 2019-04-12 | 王卫星 | A kind of railway shunting signals security early warning system |
-
2019
- 2019-07-31 CN CN201910703474.5A patent/CN110427873B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008191815A (en) * | 2007-02-02 | 2008-08-21 | Mazda Motor Corp | Vehicular safety support device |
CN109614957A (en) * | 2019-01-04 | 2019-04-12 | 王卫星 | A kind of railway shunting signals security early warning system |
Non-Patent Citations (1)
Title |
---|
林付春等: "基于深度学习的智能辅助驾驶系统设计", 《贵州大学学报(自然科学版)》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111218911A (en) * | 2019-12-17 | 2020-06-02 | 苏州奥创智能科技有限公司 | Energy-saving system and energy-saving method applied to road sweeping cleaning vehicle |
CN111218911B (en) * | 2019-12-17 | 2021-11-12 | 苏州奥创智能科技有限公司 | Energy-saving system and energy-saving method applied to road sweeping cleaning vehicle |
CN111091110A (en) * | 2019-12-24 | 2020-05-01 | 山东仁功智能科技有限公司 | Wearing identification method of reflective vest based on artificial intelligence |
CN111178223A (en) * | 2019-12-24 | 2020-05-19 | 苏州奥创智能科技有限公司 | Watering method of watering cart, automatic watering control system, main control box and watering cart |
CN111091110B (en) * | 2019-12-24 | 2023-11-17 | 山东仁功智能科技有限公司 | Reflection vest wearing recognition method based on artificial intelligence |
CN111485524A (en) * | 2020-04-16 | 2020-08-04 | 新石器慧通(北京)科技有限公司 | Spraying control method, spraying vehicle and storage medium |
CN112000102A (en) * | 2020-08-27 | 2020-11-27 | 江苏徐工信息技术股份有限公司 | Sprinkler mis-spraying prevention system and method based on video detection and GPS |
CN112214016A (en) * | 2020-09-08 | 2021-01-12 | 上海汽车集团股份有限公司 | Road operation vehicle intelligent operation system and operation method based on vision |
CN112092732A (en) * | 2020-09-22 | 2020-12-18 | 福建龙马环卫装备股份有限公司 | Image recognition-based road sanitation vehicle operation device control system and method |
Also Published As
Publication number | Publication date |
---|---|
CN110427873B (en) | 2023-06-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110427873A (en) | A kind of cleaning vehicle, the intelligent pedestrian antispray system and method applied to field of sanitation | |
CN109664301B (en) | Inspection method, inspection device, inspection equipment and computer readable storage medium | |
CN109565536B (en) | Vehicle-mounted device | |
CN110688992A (en) | Traffic signal identification method and device, vehicle navigation equipment and unmanned vehicle | |
CN109344687B (en) | Vision-based obstacle detection method and device and mobile device | |
WO2019026785A1 (en) | Attached object detection device, and vehicle system provided with same | |
CN102673609B (en) | Pre-warning system and method for operation safety of railway maintenance | |
CN103533231A (en) | Diagnostic equipment decontamination vehicle camera devices, diagnostics and vehicle systems | |
KR101454855B1 (en) | Ship hull inspection and analysys system, and method thereof | |
CN110228484A (en) | A kind of low time delay intelligent remote control loop driving function with auxiliary | |
TW201310403A (en) | Pre-warning method for rear coming vehicle which switches lane and system thereof | |
JP2015156212A (en) | Method for detecting static element in video source and image source, system, image-capturing device, movable device, and program product | |
CN107344696A (en) | Tire crane anti-collision based on real time video image identification hits early warning system and its method | |
CN103413395A (en) | Intelligent smoke detecting and early warning method and device | |
CN110126734A (en) | A kind of collision early warning system being directed to Vehicular visual blind area, device and method | |
CN108447305A (en) | A kind of new friendship rule are lower to give precedence to pedestrian's method for early warning and early warning system | |
CN113240881A (en) | Fire identification system based on multi-feature fusion | |
CN207226848U (en) | Tyre crane Intelligent anti-collision early warning system based on real time video image identification | |
CN112489125A (en) | Automatic detection method and device for storage yard pedestrians | |
CN106527485A (en) | Unmanned aerial vehicle (UAV) fixed-point flight control system based on photo-electro-mechanical integrated visual positioning | |
CN111105135A (en) | Intelligent city sweeper operation monitoring method and device | |
Wu et al. | A vision-based collision warning system by surrounding vehicles detection | |
CN107858981A (en) | Function vehicle operation apparatus control method and system | |
CN114360267A (en) | Vehicle condition detection method and device based on cloud detection system and cloud detection system | |
CN202703632U (en) | Railway maintenance operation safety pre-warning system |
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 | ||
TR01 | Transfer of patent right |
Effective date of registration: 20230731 Address after: 1111, 10th Floor, Building 5, Yard 2, Boxing 9th Road, Beijing Economic Development Zone, Daxing District, Beijing, 100176 Patentee after: Beijing Jinkai new energy and Environmental Technology Co.,Ltd. Address before: 215300 Room 101, room 9, No. 1699, Zuchongzhi South Road, Yushan Town, Kunshan City, Suzhou City, Jiangsu Province Patentee before: Suzhou Aocheng Intelligent Technology Co.,Ltd. |
|
TR01 | Transfer of patent right |