CN111144260A - Detection method, device and system of crossing gate - Google Patents
Detection method, device and system of crossing gate Download PDFInfo
- Publication number
- CN111144260A CN111144260A CN201911314957.2A CN201911314957A CN111144260A CN 111144260 A CN111144260 A CN 111144260A CN 201911314957 A CN201911314957 A CN 201911314957A CN 111144260 A CN111144260 A CN 111144260A
- Authority
- CN
- China
- Prior art keywords
- gate
- information
- crossing
- detected
- posture
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 16
- 230000008569 process Effects 0.000 claims description 14
- 230000007306 turnover Effects 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 16
- 210000003127 knee Anatomy 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 6
- 210000003423 ankle Anatomy 0.000 description 3
- 238000007635 classification algorithm Methods 0.000 description 2
- 210000000707 wrist Anatomy 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000002414 leg Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- 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
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Health & Medical Sciences (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention relates to the technical field of artificial intelligence and discloses a detection method, a device and a system of a crossing gate. The method comprises the following steps: acquiring a video image to be detected; determining the gate opening area to be detected according to the video image to be detected; processing the gateway region to be detected to obtain human skeleton posture information; judging whether a gate crossing behavior exists in the gate opening area to be detected according to the human body skeleton posture information; and if the gate-crossing behavior exists, sending a prompt message. By adopting the technical scheme of the invention, the cost of the detection equipment can be reduced, and the detection precision can be improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a detection method, a device and a system of a crossing gate.
Background
With the development of society and the progress of science and technology, the gate is generally found in places such as office buildings, subways, stations and the like. The occurrence of the gate standardizes the order and improves the efficiency of traffic and public security. But not lack the phenomenon of crossing the gate. And image processing is realized by taking continuous images as sample classification. The classification-based implementation has a high false alarm rate and a high false negative rate.
At present, products aiming at the detection of the gate crossing machine in the market are mainly based on an infrared sensor as data acquisition equipment, and only depend on the shielding of a certain sensor or a plurality of sensors to identify and judge the behavior of the gate crossing machine. Meanwhile, the alarm information generated by the gate sensor identification system cannot be correspondingly recorded in video monitoring, and only the instantaneous sound alarm signal occurs in an event, so that the cooperative control, evidence obtaining and playback of all parties in the later-stage processing of the emergency event bring difficulties; in addition, in the prior art, a surveillance video is analyzed, a gate video frame image matching rate sequence is used as a feature vector, and a traditional classification algorithm is used for judging whether a gate crossing behavior exists or not. The image matching rate is used as a feature, the description is simple, the application scene is simple, the method is easy to cause misjudgment in a complex scene (when more people exist), and the accuracy is low.
In the implementation process of the prior art, the inventor finds that the prior art has at least the following technical problems:
in the prior art, the cost is high by a traditional method for comprehensively judging the behavior of the gate crossing machine by depending on multi-sensor acquisition information; based on image matching, continuous frame matching rate is used as a feature vector, and a traditional classification algorithm classification method is used, so that the generalization performance is poor, and the precision is low.
Disclosure of Invention
The invention aims to provide a detection method, a device and a system of a crossing gate machine, which are used for overcoming the defects of high equipment cost and low detection precision in the prior art.
In order to solve the above technical problem, an embodiment of the present invention provides a detection method for a crossing gate, including:
acquiring a video image to be detected;
determining the gate opening area to be detected according to the video image to be detected;
processing the gateway region to be detected to obtain human skeleton posture information;
judging whether a gate crossing behavior exists in the gate opening area to be detected according to the human body skeleton posture information;
and if the gate-crossing behavior exists, sending a prompt message.
In order to solve the above technical problem, an embodiment of the present invention further provides a detection apparatus for a crossing gate, including:
the image acquisition unit is used for acquiring a video image to be detected;
the area determining unit is used for determining the area of the gate to be detected according to the video image to be detected;
the information acquisition unit is used for processing the gateway region to be detected to acquire human skeleton posture information;
the judging unit is used for judging whether the gate crossing behavior exists in the area of the gate opening to be detected according to the posture information of the human body skeleton;
and the information sending unit is used for sending prompt information if the behavior of crossing the gate exists.
In order to solve the above technical problem, an embodiment of the present invention further provides a detection system of a crossing gate, including: the detection device of the gate is crossed as described above.
According to the detection method, the device and the system for the gate crossing machine, provided by the invention, the video image to be detected is obtained; determining the gate opening area to be detected according to the video image to be detected; processing the gateway region to be detected to obtain human skeleton posture information; judging whether a gate crossing behavior exists in the gate opening area to be detected according to the human body skeleton posture information; and if the gate-crossing behavior exists, sending a prompt message. By adopting the technical scheme of the invention, the cost of the detection equipment can be reduced, and the detection precision can be improved.
Drawings
Fig. 1 is a flowchart of a detection method of a crossing gate according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a detection device of a crossing gate according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that numerous technical details are set forth in order to provide a better understanding of the present application in various embodiments of the present invention. However, the technical solutions claimed in the claims of the present application can be implemented without these technical details and with various changes and modifications based on the following embodiments.
A first embodiment of the present invention relates to a detection method of a rollover gate. The specific flow is shown in figure 1. The method comprises the following steps:
101: acquiring a video image to be detected;
102: determining the gate opening area to be detected according to the video image to be detected;
103: processing the gateway region to be detected to obtain human skeleton posture information;
104: judging whether a gate crossing behavior exists in the gate opening area to be detected according to the human body skeleton posture information;
105: and if the gate-crossing behavior exists, sending a prompt message.
It should be noted that the step of processing the gateway region to be detected to obtain the human skeleton posture information includes:
presetting a regional picture scale;
performing image processing on the gate opening area to be detected according to the area picture scale to obtain a standard-scale gate opening area picture to be detected;
and acquiring the posture information of the human skeleton according to the standard dimension of the picture of the portal area to be detected.
It should be further noted that the step of determining whether a gate crossing behavior exists in the gate opening area to be detected according to the posture information of the human skeleton includes:
presetting a gate-crossing attitude threshold;
and judging whether the posture information of the human body skeleton is smaller than the posture threshold value of the crossing gate.
It should be further noted that the human skeleton posture information includes: position information and attributes of key points of a human body, and position information among preset key points; the step of judging whether the human body skeleton posture information is smaller than the turnover gate posture threshold value specifically comprises the following steps:
and judging whether the posture information of the human skeleton is smaller than the posture threshold value of the crossing gate according to the position information among the preset key points.
It should be further noted that the prompt information includes: and recording state information, corresponding crossing images and video information of the crossing process when the gate is crossed.
It should be further noted that the prompt information includes: recording state information when a gate crossing event occurs; the method further comprises the following steps:
receiving an instruction for acquiring the state information of the crossing gate;
according to the instruction for acquiring the state information of the crossing gate, sending event information of the crossing gate; the rollover gate event information includes: the image information and/or the process video information are flipped over when the gate event is flipped over.
A second embodiment of the present invention relates to a detection device of a rollover gate. As shown in particular in fig. 2.
The device includes:
an image acquisition unit 201, configured to acquire a video image to be detected;
the area determining unit 202 is configured to determine a gate area to be detected according to the video image to be detected;
the information acquisition unit 203 is used for processing the gateway region to be detected to acquire human skeleton posture information;
the judging unit 204 is configured to judge whether a gate crossing behavior exists in the gate opening area to be detected according to the human body skeleton posture information;
and an information sending unit 205, configured to send a prompt message if there is a gate flipping behavior.
It should be noted that the information obtaining unit is further configured to preset a region picture scale; performing image processing on the gate opening area to be detected according to the area picture scale to obtain a standard-scale gate opening area picture to be detected; acquiring human skeleton posture information according to the standard dimension of the picture of the portal area to be detected;
the judging unit is also used for presetting a gate-crossing attitude threshold; and judging whether the posture information of the human body skeleton is smaller than the posture threshold value of the crossing gate.
It should be further noted that the human skeleton posture information includes: position information and attributes of key points of a human body, and position information among preset key points; the judgment unit is further used for judging whether the human skeleton posture information is smaller than the turnover gate posture threshold value or not according to the position information among the preset key points;
the prompt message comprises: recording state information, corresponding crossing images and crossing process video information when crossing the gate event; or, the prompt message includes: recording state information when a gate crossing event occurs; the device also includes:
the instruction receiving unit is used for receiving an instruction for acquiring the state information of the crossing gate;
the information sending unit is further configured to send the gate crossing event information according to the instruction for obtaining the state information of the gate crossing; the rollover gate event information includes: the image information and/or the process video information are flipped over when the gate event is flipped over.
It should be understood that this embodiment is an example of the apparatus corresponding to the first embodiment, and may be implemented in cooperation with the first embodiment. The related technical details mentioned in the first embodiment are still valid in this embodiment, and are not described herein again in order to reduce repetition. Accordingly, the related-art details mentioned in the present embodiment can also be applied to the first embodiment.
It should be noted that each module referred to in this embodiment is a logical module, and in practical applications, one logical unit may be one physical unit, may be a part of one physical unit, and may be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, elements that are not so closely related to solving the technical problems proposed by the present invention are not introduced in the present embodiment, but this does not indicate that other elements are not present in the present embodiment.
A third embodiment of the present invention relates to a detection system for a rollover gate. The system comprises: the detection device of the gate is crossed as described above.
Based on the above embodiment, the invention sets the video acquisition device as a camera, the erection height of the camera can be set within the range of 2.5m-3.5m according to the actual site requirement, the inclination angle is 45 degrees, and the shooting direction is to shoot the front of the pedestrian just opposite to the gate opening; setting a specific gate port area at the front end of a system (web); presetting the screen capture of a single gate port to be scaled to a fixed scale (namely, the area picture scale) to be 192x 256; and acquiring a monitoring image from an actual monitoring camera, detecting each gate bank in the image by using a gate detector, and pairing every two adjacent gate banks according to a detection result to obtain each entrance area of the gate area. And performing area verification at fixed time intervals to ensure the accuracy of the area position. According to the detected gate port area, each gate inlet is separately subjected to screenshot independent analysis; the screenshot of a single gate opening is zoomed in to a fixed scale (192x256), a human body key point probability graph is obtained through model analysis, 17 key points in the screenshot are obtained according to the probability maximum principle, the 17 key points are scattered and distributed when no pedestrian exists, and the key points correspond to all parts of a human body one by one when the pedestrian exists. According to the key point information of the human body, the snap shot is performed when the posture characteristics are crossed, and the related information such as time, place and the like is recorded. And capturing images when the posture meets the crossing posture rule, and sending a crossing gate event alarm.
The technical scheme of the invention is implemented as follows:
s1, monitoring the shot video image as a data source, and determining the position area of the gate through system setting;
s2, the gate dealer detector adopts the CenterNet network structure model, so the position returning is more accurate.
S3, the gate banker detector respectively analyzes the human skeleton gesture of each gate mouth region picture; the method specifically comprises the following steps: the image scaling is performed on each gate opening area picture to a uniform scale (i.e. the area picture scale in the above implementation), and the width and the height are respectively: 192x 256.
The human body skeleton posture analysis returns 17 key points of a nose, a left eye, a right eye, a left shoulder, a right shoulder, a left elbow, a right elbow, a left wrist, a right wrist, a left hip, a right hip, a left knee, a right knee, a left ankle, a right ankle and the like of a human body through a deep learning method. The key point of the scale ensures the accuracy of the posture estimation. And the body state authentication is that the distribution of 17 key points is consistent with the real distribution of the human body. (the determination is made by the order of the upper, lower, left and right of each key point). The human skeleton posture regression model uses a ResNet50 network as a feature learning and extracting structure.
S4, presetting a gate-crossing attitude threshold; for example: pedestrian crossing gate behavior rules: bipedal lift, leg flexion, knee elevation, as the relative distance from knee and ankle keypoints to the hip (relative distance is the ratio of the distance between the shoulders) becomes shorter than the rollover gate attitude threshold, i.e.: the average vertical distance from knees to hips s1, distance between shoulders s2, algorithm determines that the pedestrian has cross-gate behavior when s1/s2< R (cross-gate attitude threshold). The value range of the attitude threshold of the crossing gate is 0.4-0.6, and the most preferable value is 0.5, so that the detection precision of the crossing gate is higher.
And S5, displaying prompt information on the client, and marking the instant image of the pedestrian crossing the gate with a rectangular frame in the snapshot image, wherein the instant image is accompanied by information such as time, place, equipment number and the like.
It should be further noted that, the step S5 may send only the prompt message to the client; the prompt message comprises: and recording state information, corresponding crossing images and video information of the crossing process when the gate is crossed. Alternatively, the step S5 may also be to send the prompt message first; the prompt message comprises: recording state information when a gate crossing event occurs; subsequently, receiving an instruction for acquiring the state information of the gate crossing machine according to the requirements of the client user; according to the instruction for acquiring the state information of the crossing gate, sending event information of the crossing gate; the rollover gate event information includes: the image information and/or the process video information are flipped over when the gate event is flipped over.
According to the method, the device and the system for snapping the pedestrian crossing gate, provided by the technical scheme of the invention, the interaction end is provided, the specific gate opening area is set, the resource consumption of searching the gate area in full-image matching is avoided, and the condition that false alarm is possibly caused in a complex scene is avoided. The human skeleton posture regression to single floodgate machine mouth is carried out under relatively less resolution ratio to this application, can effectively save the computational resource. By adopting the ResNet50 network structure to learn and extract features, the accuracy of the skeleton key regression is effectively improved, and the detection accuracy of the crossing event in the real crossing event test reaches more than 95%.
It should also be noted that the human skeleton regression model feature extraction structure has a replaceable network structure. For example: based on the embodiment, the centret network structure model full-image detection gate dealer, the gate passing area and the snapping gate opening area are further determined, the regression model based on the ResNet50 structure is used for regressing the human skeleton, and the resolution ratio of the input image of the model is 192 × 256; the specific implementation process is as follows:
s11: acquiring an image to be detected in real time: in particular to a method for acquiring a monitoring video from a gate monitoring camera.
S12: and extracting images from the video frames to detect the gate bank, and determining the gate area.
S13: according to the gate areas, two adjacent unit positions are divided into the relative coordinates of the outer frames of the gate areas, and the areas for human body key point regression analysis are determined accordingly. The method comprises the steps of obtaining an input image of a human body key point regression model according to a gate entrance area, regressing each key point of a human body, judging the body state characteristics of the human body by utilizing the key point design rules, and identifying a gate crossing event at one time.
S14: obtaining the size of an input image of a human body key point regression model: specifically, the previous segmentation resulted in an image of the gate opening area, which was scaled to a fixed size (192 × 256) and sent to the model.
S15: performing human body key point regression on the image (namely the fixed size 192 × 256) with the image resolution adjusted to obtain human body state features;
s16: if the posture of the person in the image is consistent with the rules of a gate-flipping machine, (i.e., the average vertical distance from the knees to the hips s1, the distance between the shoulders s2, when s1/s2< R (gate-flipping attitude threshold), a prompt is issued.
When the gate crossing event is identified, the system can snap the current video frame image and mark the object, and alarm by adding information such as location, time and the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
For convenience of description, the above devices are described separately in terms of functional division into various units/modules. Of course, the functionality of the units/modules may be implemented in one or more software and/or hardware implementations of the invention.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A detection method of a gate overturning machine is characterized by comprising the following steps:
acquiring a video image to be detected;
determining the gate opening area to be detected according to the video image to be detected;
processing the gateway region to be detected to obtain human skeleton posture information;
judging whether a gate crossing behavior exists in the gate opening area to be detected according to the human body skeleton posture information;
and if the gate-crossing behavior exists, sending a prompt message.
2. The method for detecting the gate crossing machine according to claim 1, wherein the step of processing the region of the gate to be detected to obtain the posture information of the human skeleton comprises the following steps:
presetting a regional picture scale;
performing image processing on the gate opening area to be detected according to the area picture scale to obtain a standard-scale gate opening area picture to be detected;
and acquiring the posture information of the human skeleton according to the standard dimension of the picture of the portal area to be detected.
3. The method for detecting the gate crossing machine according to claim 2, wherein the step of judging whether the gate crossing area to be detected has the gate crossing behavior according to the human body skeleton posture information comprises the following steps:
presetting a gate-crossing attitude threshold;
and judging whether the posture information of the human body skeleton is smaller than the posture threshold value of the crossing gate.
4. The method for detecting a rollover gate according to claim 3, wherein the human skeleton posture information comprises: position information and attributes of key points of a human body, and position information among preset key points; the step of judging whether the human body skeleton posture information is smaller than the turnover gate posture threshold value specifically comprises the following steps:
and judging whether the posture information of the human skeleton is smaller than the posture threshold value of the crossing gate according to the position information among the preset key points.
5. The method for detecting a rollover gate according to claim 4, wherein the prompt message includes: and recording state information, corresponding crossing images and video information of the crossing process when the gate is crossed.
6. The method for detecting a rollover gate according to claim 4, wherein the prompt message includes: recording state information when a gate crossing event occurs; the method further comprises the following steps:
receiving an instruction for acquiring the state information of the crossing gate;
according to the instruction for acquiring the state information of the crossing gate, sending event information of the crossing gate; the rollover gate event information includes: the image information and/or the process video information are flipped over when the gate event is flipped over.
7. A detection apparatus for a gate rollover, comprising:
the image acquisition unit is used for acquiring a video image to be detected;
the area determining unit is used for determining the area of the gate to be detected according to the video image to be detected;
the information acquisition unit is used for processing the gateway region to be detected to acquire human skeleton posture information;
the judging unit is used for judging whether the gate crossing behavior exists in the area of the gate opening to be detected according to the posture information of the human body skeleton;
and the information sending unit is used for sending prompt information if the behavior of crossing the gate exists.
8. The apparatus according to claim 7, wherein the information acquiring unit is further configured to preset a region picture scale; performing image processing on the gate opening area to be detected according to the area picture scale to obtain a standard-scale gate opening area picture to be detected; acquiring human skeleton posture information according to the standard dimension of the picture of the portal area to be detected;
the judging unit is also used for presetting a gate-crossing attitude threshold; and judging whether the posture information of the human body skeleton is smaller than the posture threshold value of the crossing gate.
9. The detection apparatus of the rollover gate according to claim 8, wherein the human skeletal pose information comprises: position information and attributes of key points of a human body, and position information among preset key points; the judgment unit is further used for judging whether the human skeleton posture information is smaller than the turnover gate posture threshold value or not according to the position information among the preset key points;
the prompt message comprises: recording state information, corresponding crossing images and crossing process video information when crossing the gate event; or, the prompt message includes: recording state information when a gate crossing event occurs; the device also includes:
the instruction receiving unit is used for receiving an instruction for acquiring the state information of the crossing gate;
the information sending unit is further configured to send the gate crossing event information according to the instruction for obtaining the state information of the gate crossing; the rollover gate event information includes: the image information and/or the process video information are flipped over when the gate event is flipped over.
10. A detection system for a rollover gate, comprising: detection device of a turndown gate according to any of claims 7-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911314957.2A CN111144260A (en) | 2019-12-19 | 2019-12-19 | Detection method, device and system of crossing gate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911314957.2A CN111144260A (en) | 2019-12-19 | 2019-12-19 | Detection method, device and system of crossing gate |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111144260A true CN111144260A (en) | 2020-05-12 |
Family
ID=70518910
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911314957.2A Pending CN111144260A (en) | 2019-12-19 | 2019-12-19 | Detection method, device and system of crossing gate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111144260A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112200828A (en) * | 2020-09-03 | 2021-01-08 | 浙江大华技术股份有限公司 | Detection method and device for ticket evasion behavior and readable storage medium |
| CN113014870A (en) * | 2021-02-20 | 2021-06-22 | 同济大学 | Subway gate passage ticket evasion identification method based on passenger posture rapid estimation |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140373647A1 (en) * | 2013-06-20 | 2014-12-25 | Target Brands, Inc. | Lifting motion evaluation |
| CN206411817U (en) * | 2016-12-06 | 2017-08-15 | 山东康威通信技术股份有限公司 | A kind of prison circumference makes an inspection tour warning robot system |
| CN107221175A (en) * | 2017-05-31 | 2017-09-29 | 深圳市鸿逸达科技有限公司 | A kind of pedestrian is intended to detection method and system |
| CN107812343A (en) * | 2017-08-29 | 2018-03-20 | 浙江理工大学 | A kind of vault sports training method |
| CN108280435A (en) * | 2018-01-25 | 2018-07-13 | 盛视科技股份有限公司 | Passenger abnormal behavior recognition method based on human body posture estimation |
| CN108958478A (en) * | 2018-06-14 | 2018-12-07 | 吉林大学 | Action recognition and appraisal procedure are ridden in a kind of operation of Virtual assemble |
-
2019
- 2019-12-19 CN CN201911314957.2A patent/CN111144260A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140373647A1 (en) * | 2013-06-20 | 2014-12-25 | Target Brands, Inc. | Lifting motion evaluation |
| CN206411817U (en) * | 2016-12-06 | 2017-08-15 | 山东康威通信技术股份有限公司 | A kind of prison circumference makes an inspection tour warning robot system |
| CN107221175A (en) * | 2017-05-31 | 2017-09-29 | 深圳市鸿逸达科技有限公司 | A kind of pedestrian is intended to detection method and system |
| CN107812343A (en) * | 2017-08-29 | 2018-03-20 | 浙江理工大学 | A kind of vault sports training method |
| CN108280435A (en) * | 2018-01-25 | 2018-07-13 | 盛视科技股份有限公司 | Passenger abnormal behavior recognition method based on human body posture estimation |
| CN108958478A (en) * | 2018-06-14 | 2018-12-07 | 吉林大学 | Action recognition and appraisal procedure are ridden in a kind of operation of Virtual assemble |
Non-Patent Citations (3)
| Title |
|---|
| KUANGYOU B.CHENG: "The Relationship between Joint Strength and Standing Vertical Jump Performance", 《JOURNAL OF APPLIED BIOMECHANICS》, vol. 24, no. 3, pages 224 - 233 * |
| 汪亚明 等: "基于改进ELM的撑杆跳起跳过杆轨迹模型研究", 《浙江理工大学学报（自然科学版）》, vol. 39, no. 1, pages 75 - 81 * |
| 范嘉义: "基于骨架信息的人体动作识别", 《中国优秀硕士学位论文全文数据库信息科技辑》, pages 138 - 1725 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112200828A (en) * | 2020-09-03 | 2021-01-08 | 浙江大华技术股份有限公司 | Detection method and device for ticket evasion behavior and readable storage medium |
| CN113014870A (en) * | 2021-02-20 | 2021-06-22 | 同济大学 | Subway gate passage ticket evasion identification method based on passenger posture rapid estimation |
| CN113014870B (en) * | 2021-02-20 | 2022-09-20 | 同济大学 | Subway gate passage ticket evasion identification method based on passenger posture rapid estimation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ahmed et al. | Vision based hand gesture recognition using dynamic time warping for Indian sign language | |
| CN103824070B (en) | A kind of rapid pedestrian detection method based on computer vision | |
| CN105205455B (en) | The in-vivo detection method and system of recognition of face on a kind of mobile platform | |
| US20220180534A1 (en) | Pedestrian tracking method, computing device, pedestrian tracking system and storage medium | |
| US20070098222A1 (en) | Scene analysis | |
| WO2021082112A1 (en) | Neural network training method, skeleton diagram construction method, and abnormal behavior monitoring method and system | |
| TWI439951B (en) | Facial gender identification system and method and computer program products thereof | |
| CN107657244B (en) | Human body falling behavior detection system based on multiple cameras and detection method thereof | |
| CN111241913A (en) | Method, device and system for detecting falling of personnel | |
| KR102580434B1 (en) | Dangerous situation detection device and dangerous situation detection method | |
| JP2017059945A (en) | Device and method for image analysis | |
| CN111753587B (en) | Ground falling detection method and device | |
| CN114140745A (en) | Method, system, device and medium for detecting personnel attributes of construction site | |
| CN207233038U (en) | Face is called the roll and number system | |
| CN111144260A (en) | Detection method, device and system of crossing gate | |
| Raheja et al. | Cross border intruder detection in hilly terrain in dark environment | |
| CN114511592B (en) | Personnel track tracking method and system based on RGBD camera and BIM system | |
| CN106056080B (en) | A kind of visual biometric information acquisition device and method | |
| CN109215150A (en) | Face is called the roll and method of counting and its system | |
| CN110580708B (en) | Rapid movement detection method and device and electronic equipment | |
| Shivthare et al. | Suspicious activity detection network for video surveillance using machine learning | |
| CN114639168B (en) | Method and system for recognizing running gesture | |
| CN113554682B (en) | Target tracking-based safety helmet detection method | |
| CN112818929B (en) | Method and device for detecting people fighting, electronic equipment and storage medium | |
| CN113239772B (en) | Personnel gathering early warning method and system in self-service bank or ATM environment |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200512 |