CN111776905A - Battery car elevator entering warning method and system combining re-identification - Google Patents
Battery car elevator entering warning method and system combining re-identification Download PDFInfo
- Publication number
- CN111776905A CN111776905A CN202010814856.8A CN202010814856A CN111776905A CN 111776905 A CN111776905 A CN 111776905A CN 202010814856 A CN202010814856 A CN 202010814856A CN 111776905 A CN111776905 A CN 111776905A
- Authority
- CN
- China
- Prior art keywords
- battery car
- elevator
- image
- video data
- warning method
- 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
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
Landscapes
- Indicating And Signalling Devices For Elevators (AREA)
Abstract
The invention relates to a battery car elevator entering warning method and system combining heavy identification, wherein the method comprises the following steps: s1, collecting video data after an elevator door is opened; s2, detecting the battery car based on the video data, judging whether the battery car exists, if so, executing a step S3, and if not, executing a step S4; s3, acquiring an image containing the battery car, performing battery car weight identification on the battery car based on a registered car database, executing a step S4 if the vehicle is a registered vehicle, otherwise, giving an alarm and controlling the elevator to stop running; s4, the elevator is released, and the steps S1 to S3 are executed again. The invention can not only effectively prevent the battery car from entering the elevator; meanwhile, through the heavy identification technology, the toy car which is too similar to the battery car, the old mobility scooter and the like can be ensured to take the elevator smoothly.
Description
Technical Field
The invention relates to the field of elevators, in particular to a battery car elevator entering warning method combining heavy identification.
Background
In recent years, higher-level cells have been increasing. In order to facilitate charging, the battery car is pushed upstairs by an elevator by an owner. The storage battery car not only occupies the space of a fire fighting access, but also has serious potential safety hazard when going upstairs for charging. At present, most of high-rise communities go out of the elevator, but have the problem of high execution difficulty. Some methods of battery car detection based on video data have emerged to prevent battery cars from going upstairs. However, the method for preventing the user from taking the elevator based on the video image detection can effectively prevent the battery car from entering the elevator, but some false detection behaviors exist, so that the situation that the user cannot take the elevator, such as a toy car and an old mobility scooter, which have similar appearance characteristics with the battery car is caused, and a lot of inconvenience is brought to the life of the user.
Disclosure of Invention
The invention aims to provide a battery car ladder-entering warning method combined with heavy identification, and the method solves the inconvenience influence brought by the traditional battery car detection method.
In order to achieve the purpose, the invention provides a battery car ladder entry warning method combining re-identification, which comprises the following steps:
s1, collecting video data after an elevator door is opened;
s2, detecting the battery car based on the video data, judging whether the battery car exists, if so, executing a step S3, and if not, executing a step S4;
s3, acquiring an image containing the battery car, performing battery car weight identification on the battery car based on a registered car database, executing a step S4 if the vehicle is a registered vehicle, otherwise, giving an alarm and controlling the elevator to stop running;
s4, the elevator is released, and the steps S1 to S3 are executed again.
According to an aspect of the present invention, the step of detecting the battery car based on the video data and determining whether the battery car exists in step S2 includes:
s21, intercepting the video data according to the duration of a first preset interval, and decoding a plurality of images according to the duration of a second preset interval based on the video data;
and S22, if the number proportion of the images containing the battery car in the plurality of images exceeds a preset value, judging that the images exist.
According to an aspect of the invention, in step S21, the first preset interval is an integer multiple of the second preset interval.
According to an aspect of the present invention, the step of acquiring an image including the battery car and performing battery car weight recognition on the battery car based on the registered vehicle database in step S3 includes:
s31, taking an image containing the battery car as a candidate target image, and intercepting the battery car in the candidate target image as a candidate target;
s32, acquiring target characteristics of the candidate target by adopting a candidate target re-identification network;
and S33, calculating the characteristic distance between the target characteristic and the characteristic of the registered vehicle in the registered vehicle database, wherein if the characteristic distance is smaller than a preset threshold value, the candidate target corresponding to the target characteristic is an unregistered battery car.
According to one aspect of the invention, in the step of giving an alarm and controlling the elevator to stop running in the step of S3, the alarm is stopped if the battery car does not exist in the next video data.
According to one aspect of the invention, the registered vehicle database is obtained by the steps comprising:
s031, obtain the side images of at least three directions of the vehicle that can take the elevator, and adopt the heavy recognition network of said candidate target to carry on the feature extraction and obtain n 1 x 512 feature data to the said image, wherein, n represents the direction quantity to obtain the said side image;
s032, carrying out normalization processing on the feature data, and taking the processing result as the feature of the registered vehicle.
According to one aspect of the invention, in the step S22, in the step of detecting the battery car based on the video data and determining whether the battery car exists, an image including the battery car is output by using a target detection network, and a confidence of the battery car in the image is greater than a preset threshold.
According to an aspect of the present invention, in step S32, the target feature of the candidate target is feature data with a length of 512;
in step S33, the characteristic distance is an L2 distance or a cosine distance.
According to one aspect of the invention, the target detection network employs yolov3 detection network;
the candidate target re-identifies the network as a Resnet34 network.
In order to achieve the above object, the present invention provides an electric vehicle entering ladder warning system for the electric vehicle entering ladder warning method, comprising:
the image acquisition module is used for acquiring video data after the elevator is opened;
the front-end equipment is used for receiving the video data and carrying out decoding processing to obtain a plurality of images;
the cloud server receives the image uploaded by the front-end equipment, judges whether the battery car exists in the image, and if the battery car exists in the image, performs battery car weight recognition on the battery car and outputs a judgment result;
and the alarm unit is used for receiving the processing result of the cloud server and determining whether to send out an alarm or not.
According to the scheme of the invention, the battery car can be effectively prevented from entering the elevator; meanwhile, through the heavy identification technology, the toy car which is too similar to the battery car, the old mobility scooter and the like can be ensured to take the elevator smoothly.
According to one scheme of the invention, video data of passengers entering an elevator are acquired through a camera, a candidate battery car is detected by using a battery car detection algorithm, a re-identification algorithm is further used for identifying the screenshot of the detected candidate battery car on the basis of detecting the candidate battery car, and if the battery car is not in the registered data of the available vehicles of the current elevator, an alarm operation is performed.
According to the scheme, the storage battery car detection is carried out after continuous video data at one end is intercepted and converted into a plurality of images, so that the data volume in the storage battery car detection process is effectively reduced, and the efficiency of the whole detection process is greatly improved. In addition, the mode of judging whether there is the storage battery car in the video data through the mode that adopts the default ratio effectively has avoided the detection error that brings when having storage battery car to pass the elevator gate among the video data, very big improvement the detection accuracy of this scheme, favorable to guaranteeing the stable normal operating of elevator.
Drawings
Fig. 1 is a block diagram schematically illustrating the steps of an incoming alarm method for a battery car according to an embodiment of the present invention;
fig. 2 is a flowchart schematically illustrating an incoming alarm method for a battery car according to an embodiment of the present invention;
FIG. 3 is a diagram schematically illustrating an object detection network in accordance with one embodiment of the present invention;
FIG. 4 is a flow chart schematically illustrating battery car re-identification according to an embodiment of the present invention;
fig. 5 is a block diagram schematically illustrating an incoming call warning system for a battery car according to an embodiment of the present invention;
fig. 6 is a flow chart schematically showing the operation of the battery car entering alarm system according to one embodiment of the 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 used in the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
In describing embodiments of the present invention, the terms "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like are used in an orientation or positional relationship that is based on the orientation or positional relationship shown in the associated drawings, which is for convenience and simplicity of description only, and does not indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and thus, the above-described terms should not be construed as limiting the present invention.
The present invention is described in detail below with reference to the drawings and the specific embodiments, which are not repeated herein, but the embodiments of the present invention are not limited to the following embodiments.
Referring to fig. 1 and 2, according to an embodiment of the present invention, a battery car entrance warning method with re-identification according to the present invention includes:
s1, collecting video data after an elevator door is opened;
s2, detecting the battery car based on the video data, judging whether the battery car exists, if so, executing a step S3, and if not, executing a step S4;
s3, acquiring an image containing the battery car, performing battery car weight identification on the battery car based on the registered car database, executing a step S4 if the car is the registered car, otherwise, giving an alarm and controlling the elevator to stop running;
s4, the elevator is released, and the steps S1 to S3 are executed again.
According to one embodiment of the invention, video data acquisition is carried out on the position of the elevator entrance through the image acquisition module, and meanwhile, the acquired video data are transmitted to the front-end equipment for processing.
According to an embodiment of the present invention, the step of detecting the battery car based on the video data and determining whether the battery car exists in step S2 includes:
s21 captures the video data according to the duration of the first preset interval, and decodes the multiple images according to the duration of the second preset interval based on the video data. In this embodiment, the front-end device receives video data collected by the image collection module. And intercepting the uploaded video data according to the preset duration of a first preset interval. In the present embodiment, video data after the elevator door is opened is mainly captured. And then, decoding the intercepted video data according to the duration of a second preset interval to obtain a plurality of images. For example, if the duration of the first preset interval is set to 3s, the front-end device intercepts 3s of video data after the elevator door is opened from the received video data, and uses the video data for further decoding processing. The duration of the second preset interval is set to 0.5s, and then, the video data of the above 3s may be converted into 6 images along the time sequence.
And S22, if the quantity proportion of the images containing the battery car in the plurality of images exceeds a preset value, judging that the images exist. In the embodiment, the acquired images are detected one by one, the number of the images including the battery car is acquired, and if the ratio of the number of the images including the battery car to the total number of the acquired images exceeds a preset value, it is determined that the battery car exists in the video data. For example, if the preset value is set to 2/3, in 6 images acquired in the foregoing step, if more than four images contain a battery car, the output result is that the battery car exists in the video data.
Through the setting, in this scheme, carry out the detection of storage battery car after intercepting the continuous video data of one end and converting into many images, the effectual data volume that has reduced in the storage battery car testing process, very big improvement whole testing process's efficiency. In addition, the mode of judging whether there is the storage battery car in the video data through the mode that adopts the default ratio effectively has avoided the detection error that brings when having storage battery car to pass the elevator gate among the video data, very big improvement the detection accuracy of this scheme, favorable to guaranteeing the stable normal operating of elevator.
According to one embodiment of the present invention, in step S21, the first preset interval is an integer multiple of the second preset interval. Through the arrangement, the image data of the head and tail positions of the video data can be effectively decoded, so that the method is favorable for more accurately and widely detecting whether the image of the battery car is contained in the video data, and is beneficial to improving the detection accuracy and effectively utilizing the video data.
As shown in fig. 3, according to an embodiment of the present invention, in the step S22, performing storage battery car detection based on the video data, and determining whether the storage battery car exists, an image including the storage battery car is output by using a target detection network, and a confidence of the storage battery car in the image is greater than a preset threshold. In this embodiment, the destination detection network is a yolov3 detection network, and the network may output a bounding box (a position in an input image, referred to as a Bbox for short) of the battery car detected by the current image and a confidence that a destination surrounded by the bounding box is the battery car, that is, the confidence, where if the confidence is greater than a preset threshold, the destination is a candidate battery car destination, and otherwise, the destination is directly returned. In the present embodiment, the preset threshold may be set to 0.6.
Through the arrangement, the accuracy of the detected images containing the storage battery car is ensured, so that the judgment accuracy of the elevator detection device is ensured, and the elevator can stably run for a long time.
As shown in fig. 4, in step S3, the step of acquiring an image containing a battery car and performing battery car weight recognition on the battery car based on the registered vehicle database includes:
and S31, taking the image containing the battery car as a candidate target image, and intercepting the battery car in the candidate target image as a candidate target. In the embodiment, the detected image containing the battery car is taken as a candidate target image, and the battery car image is taken as a candidate target, namely, a screenshot of the battery car image is obtained in an input image according to the Bbox of the battery car.
S32, acquiring target characteristics of the candidate target by adopting a candidate target re-identification network; in this embodiment, the candidate target re-identification network is a Resnet34 network, which is capable of outputting target features of a fixed dimension. In the present embodiment, the target feature of the candidate target is feature data having a length of 512.
And S33, calculating the characteristic distance between the target characteristic and the characteristic of the registered vehicle in the registered vehicle database, wherein if the characteristic distance is smaller than a preset threshold value, the candidate target corresponding to the target characteristic is the unregistered battery car. In the present embodiment, the feature distance is calculated by calculating the distance between the target feature of the candidate target and all the registered vehicle features, and in the present embodiment, the feature distance is calculated by using the L2 distance metric or the cosine distance. If the characteristic distance of the most similar object (the characteristic distance is smallest) to the candidate object in the registered vehicles is less than a given threshold, it indicates that the candidate object is an unregistered object, that is, it is possible to confirm that the candidate object is an unregistered electric vehicle. In this embodiment, the threshold value may be selected to be 0.6.
According to one embodiment of the invention, in the step of giving an alarm and controlling the elevator to stop running in the step of S3, if the battery car does not exist in the next video data, the alarm is stopped. In the embodiment, as described above, when the battery car is detected, the video data of the next continuous time period (e.g. 3s) is acquired to detect the electric vehicle, and when the battery car is not detected, the alarm is ended.
According to one embodiment of the invention, the registered vehicle database is obtained by the steps comprising:
s031, obtain the side image of the vehicle of the passable elevator at least three directions, and adopt the heavy identification network of candidate target to carry out feature extraction and obtain n 1 × 512's feature data to the image, wherein, n represents the direction quantity of obtaining the side image. In the embodiment, vehicles capable of taking an elevator, such as toy vehicles, geriatric vehicles and the like, are determined in advance, and three side images of the front and the left and right sides of the vehicle in three directions are photographed by using the image acquisition module. Of course, other directions of the side images may be taken as a supplement. And obtaining the feature data of 3 vehicles with 1 x 512 through the candidate target re-identification network. The registered vehicle database is constructed by adopting the candidate target re-identification network, so that the data universality in the subsequent re-identification process is facilitated, and the accuracy of the whole detection process is ensured.
S032, normalization processing is carried out on the feature data, and the processed result is used as the feature of the registered vehicle.
Referring to fig. 5 and 6, according to an embodiment of the present invention, an entry warning system for a battery car includes: the system comprises an image acquisition module for acquiring video data after the elevator is opened, front-end equipment for receiving the video data, decoding the video data to acquire a plurality of images, a cloud server connected with the front-end equipment and an alarm unit. In the embodiment, the cloud server receives the image uploaded by the front-end equipment, judges whether the battery car exists in the image, and if the battery car exists in the image, the battery car is identified again and a judgment result is output, and the alarm unit receives a processing result of the cloud server and determines whether to give an alarm. In the present embodiment, the image capturing module may be a monitoring camera, a depth camera, or the like, which is installed inside the elevator car to be inclined toward the elevator doorway to acquire image data. In the embodiment, the image acquisition module, the front-end device and the cloud server are connected by a network cable, and data transmission is realized based on a TCP/IP protocol. The alarm unit is electrically connected with the front-end equipment, and the cloud server outputs the output judgment result to the front-end equipment and transmits the output judgment result to the alarm unit through the front-end equipment.
The foregoing is merely exemplary of particular aspects of the present invention and devices and structures not specifically described herein are understood to be those of ordinary skill in the art and are intended to be implemented in such conventional ways.
The above description is only one embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A battery car elevator entering warning method combining re-identification comprises the following steps:
s1, collecting video data after an elevator door is opened;
s2, detecting the battery car based on the video data, judging whether the battery car exists, if so, executing a step S3, and if not, executing a step S4;
s3, acquiring an image containing the battery car, performing battery car weight identification on the battery car based on a registered car database, executing a step S4 if the vehicle is a registered vehicle, otherwise, giving an alarm and controlling the elevator to stop running;
s4, the elevator is released, and the steps S1 to S3 are executed again.
2. The battery car elevator entering warning method according to claim 1, wherein in the step S2, the step of detecting the battery car based on the video data and determining whether the battery car exists comprises:
s21, intercepting the video data according to the duration of a first preset interval, and decoding a plurality of images according to the duration of a second preset interval based on the video data;
and S22, if the number proportion of the images containing the battery car in the plurality of images exceeds a preset value, judging that the images exist.
3. The battery car ladder entry warning method as claimed in claim 2, wherein in step S21, the first preset interval is an integer multiple of the second preset interval.
4. The battery car boarding warning method according to claim 2 or 3, wherein the step of acquiring an image containing the battery car and performing battery car weight recognition on the battery car based on a registered vehicle database in step S3 includes:
s31, taking an image containing the battery car as a candidate target image, and intercepting the battery car in the candidate target image as a candidate target;
s32, acquiring target characteristics of the candidate target by adopting a candidate target re-identification network;
and S33, calculating the characteristic distance between the target characteristic and the characteristic of the registered vehicle in the registered vehicle database, wherein if the characteristic distance is smaller than a preset threshold value, the candidate target corresponding to the target characteristic is an unregistered battery car.
5. The battery car elevator entering warning method according to claim 4, wherein in the step of sending an alarm and controlling the elevator to stop running in step S3, the alarm is stopped if the battery car does not exist in the next video data.
6. The battery car boarding warning method according to claim 4, wherein the registered vehicle database is obtained by the steps comprising:
s031, obtain the side images of at least three directions of the vehicle that can take the elevator, and adopt the heavy recognition network of said candidate target to carry on the feature extraction and obtain n 1 x 512 feature data to the said image, wherein, n represents the direction quantity to obtain the said side image;
s032, carrying out normalization processing on the feature data, and taking the processing result as the feature of the registered vehicle.
7. The battery car ladder entry warning method according to claim 4, wherein in the step S22, battery car detection is performed based on the video data, and whether a battery car exists is judged, wherein in the step S22, an image including the battery car is output by using a target detection network, and the confidence of the battery car in the image is greater than a preset threshold.
8. The battery car boarding warning method according to claim 4, wherein in step S32, the target feature of the candidate target is feature data with a length of 512;
in step S33, the characteristic distance is an L2 distance or a cosine distance.
9. The battery car ladder entry warning method as claimed in claim 7, wherein the target detection network is a yolov3 detection network;
the candidate target re-identifies the network as a Resnet34 network.
10. An electric vehicle entry warning system for the electric vehicle entry warning method according to any one of claims 1 to 9, comprising:
the image acquisition module is used for acquiring video data after the elevator is opened;
the front-end equipment is used for receiving the video data and carrying out decoding processing to obtain a plurality of images;
the cloud server receives the image uploaded by the front-end equipment, judges whether the battery car exists in the image, and if the battery car exists in the image, performs battery car weight recognition on the battery car and outputs a judgment result;
and the alarm unit is used for receiving the processing result of the cloud server and determining whether to send out an alarm or not.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010814856.8A CN111776905B (en) | 2020-08-13 | 2020-08-13 | Battery car elevator entering warning method and system combining re-identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010814856.8A CN111776905B (en) | 2020-08-13 | 2020-08-13 | Battery car elevator entering warning method and system combining re-identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111776905A true CN111776905A (en) | 2020-10-16 |
| CN111776905B CN111776905B (en) | 2021-11-23 |
Family
ID=72762005
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010814856.8A Active CN111776905B (en) | 2020-08-13 | 2020-08-13 | Battery car elevator entering warning method and system combining re-identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111776905B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112261380A (en) * | 2020-10-26 | 2021-01-22 | 杭州海康威视数字技术股份有限公司 | Elevator control method and device |
| CN112347873A (en) * | 2020-10-26 | 2021-02-09 | 浙江新再灵科技股份有限公司 | Ladder control method |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08133619A (en) * | 1994-11-15 | 1996-05-28 | Hitachi Building Syst Eng & Service Co Ltd | Safety device for elevator |
| JP2010037057A (en) * | 2008-08-05 | 2010-02-18 | Mitsubishi Electric Building Techno Service Co Ltd | Elevator for automobile |
| CN105173931A (en) * | 2015-09-11 | 2015-12-23 | 浙江南奥电梯有限公司 | Automatic car identifying and door-opening system for car elevator |
| CN107679531A (en) * | 2017-06-23 | 2018-02-09 | 平安科技（深圳）有限公司 | Licence plate recognition method, device, equipment and storage medium based on deep learning |
| CN109165620A (en) * | 2018-09-04 | 2019-01-08 | 张晓飞 | A kind of detection method of electric vehicle, system and terminal device |
| CN109740479A (en) * | 2018-12-25 | 2019-05-10 | 苏州科达科技股份有限公司 | A kind of vehicle recognition methods, device, equipment and readable storage medium storing program for executing again |
| CN110002315A (en) * | 2018-11-30 | 2019-07-12 | 浙江新再灵科技股份有限公司 | Vertical ladder electric vehicle detection method and warning system based on deep learning |
| CN110222659A (en) * | 2019-06-12 | 2019-09-10 | 江苏鼎航电子科技有限公司 | Electric vehicle recognition methods, device and system |
| CN209493186U (en) * | 2018-11-09 | 2019-10-15 | 中海物业管理有限公司苏州分公司 | Electric vehicle image recognition managing and control system in a kind of elevator |
| CN110436294A (en) * | 2019-08-08 | 2019-11-12 | 杭州吉时语科技有限公司 | A kind of battery truck enters elevator detection method |
| CN111439644A (en) * | 2020-02-28 | 2020-07-24 | 浙江大华技术股份有限公司 | Alarming method of storage battery car in elevator and related device |
| CN112079213A (en) * | 2020-08-24 | 2020-12-15 | 浙江新再灵科技股份有限公司 | Elevator entry control method and elevator entry control system |
-
2020
- 2020-08-13 CN CN202010814856.8A patent/CN111776905B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08133619A (en) * | 1994-11-15 | 1996-05-28 | Hitachi Building Syst Eng & Service Co Ltd | Safety device for elevator |
| JP2010037057A (en) * | 2008-08-05 | 2010-02-18 | Mitsubishi Electric Building Techno Service Co Ltd | Elevator for automobile |
| CN105173931A (en) * | 2015-09-11 | 2015-12-23 | 浙江南奥电梯有限公司 | Automatic car identifying and door-opening system for car elevator |
| CN107679531A (en) * | 2017-06-23 | 2018-02-09 | 平安科技（深圳）有限公司 | Licence plate recognition method, device, equipment and storage medium based on deep learning |
| CN109165620A (en) * | 2018-09-04 | 2019-01-08 | 张晓飞 | A kind of detection method of electric vehicle, system and terminal device |
| CN209493186U (en) * | 2018-11-09 | 2019-10-15 | 中海物业管理有限公司苏州分公司 | Electric vehicle image recognition managing and control system in a kind of elevator |
| CN110002315A (en) * | 2018-11-30 | 2019-07-12 | 浙江新再灵科技股份有限公司 | Vertical ladder electric vehicle detection method and warning system based on deep learning |
| CN109740479A (en) * | 2018-12-25 | 2019-05-10 | 苏州科达科技股份有限公司 | A kind of vehicle recognition methods, device, equipment and readable storage medium storing program for executing again |
| CN110222659A (en) * | 2019-06-12 | 2019-09-10 | 江苏鼎航电子科技有限公司 | Electric vehicle recognition methods, device and system |
| CN110436294A (en) * | 2019-08-08 | 2019-11-12 | 杭州吉时语科技有限公司 | A kind of battery truck enters elevator detection method |
| CN111439644A (en) * | 2020-02-28 | 2020-07-24 | 浙江大华技术股份有限公司 | Alarming method of storage battery car in elevator and related device |
| CN112079213A (en) * | 2020-08-24 | 2020-12-15 | 浙江新再灵科技股份有限公司 | Elevator entry control method and elevator entry control system |
Non-Patent Citations (4)
| Title |
|---|
| HTTP://KODIO.TPY888.CN/NEWS/ITEMID-179724.SHTML: "《科缔欧电动车监测系统助力苏州小区管控电动车入电梯报警》", 17 September 2018 * |
| 李璐: "电梯智慧监管中的问题及对策研究――以杭州市萧山区为例", 《中国市场监管研究》 * |
| 郑凌秀: "AI在智慧社区的应用研究", 《中国公共安全》 * |
| 韩冰: "《数字音视频处理》", 31 October 2018, 西安电子科技大学出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112261380A (en) * | 2020-10-26 | 2021-01-22 | 杭州海康威视数字技术股份有限公司 | Elevator control method and device |
| CN112347873A (en) * | 2020-10-26 | 2021-02-09 | 浙江新再灵科技股份有限公司 | Ladder control method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111776905B (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111776905B (en) | Battery car elevator entering warning method and system combining re-identification | |
| CN112079213B (en) | Elevator entry control method and elevator entry control system | |
| CN112381066B (en) | Abnormal behavior identification method for elevator riding, monitoring system, computer equipment and storage medium | |
| CN110950208A (en) | Semantic segmentation-based method for prohibiting electric vehicle from entering elevator and going upwards in linkage manner | |
| CN109447090B (en) | Shield door obstacle detection method and system | |
| CN112623919B (en) | Escalator intelligent monitoring management system based on computer vision | |
| CN109867186B (en) | Elevator trapping detection method and system based on intelligent video analysis technology | |
| CN112419686B (en) | Multistage judgment alarm and event recording system for bridge impact detection | |
| CN114694054A (en) | Bus stop passenger flow statistical method and device, electronic equipment and storage medium | |
| CN112132863A (en) | High-altitude parabolic detection process and analysis method | |
| US11030465B1 (en) | Method for analyzing number of people and system thereof | |
| CN112818871A (en) | Target detection method of full-fusion neural network based on half-packet convolution | |
| CN114436087B (en) | Deep learning-based elevator passenger door-pulling detection method and system | |
| CN110407052B (en) | Method and system for detecting violent movement behaviors in elevator | |
| CN108305460A (en) | A kind of method and terminal of identification overloaded vehicle | |
| CN114701934B (en) | Security control method, device and system for elevator, cloud platform and storage medium | |
| CN112261380B (en) | Elevator control method and device | |
| CN114314243A (en) | Elevator overload alarm system and method based on video identification technology | |
| CN114283360A (en) | Method, apparatus, device and medium for detecting electric vehicle in elevator | |
| CN112699746A (en) | Object detection method, device, equipment and storage medium | |
| CN205862521U (en) | Pantograph dynamic monitor | |
| CN117007101B (en) | Vehicle monitoring method, device, electronic equipment and storage medium | |
| CN112158695A (en) | Elevator control method | |
| CN111918028A (en) | Building information processing device based on artificial intelligence | |
| CN114655804A (en) | Elevator monitoring method, device and 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 |