CN210271176U - Human behavior recognition device - Google Patents
Human behavior recognition device Download PDFInfo
- Publication number
- CN210271176U CN210271176U CN201920454004.5U CN201920454004U CN210271176U CN 210271176 U CN210271176 U CN 210271176U CN 201920454004 U CN201920454004 U CN 201920454004U CN 210271176 U CN210271176 U CN 210271176U
- Authority
- CN
- China
- Prior art keywords
- controller
- behavior
- alarm
- radar
- recognition device
- 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.)
- Expired - Fee Related
Links
- 238000004891 communication Methods 0.000 claims abstract description 21
- 238000001514 detection method Methods 0.000 claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 6
- 230000004044 response Effects 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 4
- 239000000428 dust Substances 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 238000005286 illumination Methods 0.000 abstract description 2
- 230000010365 information processing Effects 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 30
- 230000006870 function Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000013145 classification model Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Radar Systems Or Details Thereof (AREA)
Abstract
The utility model discloses a human behavior recognition device, which comprises a detection radar, a radar signal processor, a behavior recognizer, an alarm device, an image collector, a communication device and a controller; the radar signal processor is connected with the detection radar, the radar signal processor is respectively connected with the behavior recognizer and the controller, the image collector and the alarm device are respectively connected with the controller, and the controller is provided with a communication device. The system adopts a radar detection technology, can effectively solve the interference of environmental factors such as illumination, dust and the like on behavior detection, and has small information quantity and quick information processing response. Meanwhile, the device greatly improves the classification and identification accuracy of the behavior detection, thereby providing a high-feasibility method for the behavior detection of underground operators.
Description
[ technical field ]
The utility model relates to a human action recognition field, concretely relates to human action recognition device.
[ background art ]
During industrial operations, such as downhole operations, there are a large number of dangerous activities that cause death of tens of thousands of people each year. If the dangerous human behaviors can be comprehensively and accurately identified and timely alarmed, the occurrence rate of safety production accidents is greatly reduced, the life and property safety of enterprises and staff is guaranteed, and the production performance of the enterprises is improved.
The existing human behavior recognition technical scheme mainly has two types, one type is based on the monitoring operation of a visual camera, but the monitoring of a single camera has many defects: if the requirements of the camera on light and environment are high, the sight line of the camera is easily shielded by structures, equipment and the like, meanwhile, the characteristic quantity of human behavior recognition processing by adopting a camera scheme is large, the information quantity is large, the real-time performance is insufficient, and the cost of the high-definition camera is high; the other type is a wearable sensor scheme, the human behavior information is acquired by adopting an acceleration sensor, a gyroscope and the like, the false alarm is easily generated due to lack of accurate analysis and judgment, and a large number of devices are worn difficultly during operation.
[ contents of utility model ]
The utility model discloses mainly be in order to solve the human action recognition problem that exists among the prior art, different with the mode that adopts camera control and personnel to dress the sensor, provide a new human action recognition device.
In order to achieve the above object, the utility model provides a human action recognition device specifically adopts following technical scheme:
the human behavior recognition device comprises a detection radar, a radar signal processor, a behavior recognizer, an alarm device, an image collector, a communication device and a controller; the radar signal processor is connected with the detection radar, the radar signal processor is respectively connected with the behavior recognizer and the controller, the image collector and the alarm device are respectively connected with the controller, and the controller is provided with a communication device.
Further, the system also comprises a background management center, and the controller is in real-time communication with the background management center through a communication device.
Further, the detection radar is a doppler radar: the method comprises the steps of detecting a human body target in a range in real time by transmitting continuous wave signals, and receiving reflected echo signals of the human body target, wherein the echo signals carry behavior state information of the human body target.
Further, the radar signal processor: the radar echo signals are converted into digital signals which can be processed by a Digital Signal Processor (DSP) through an analog-to-digital signal converter (ADC), and the DSP converts the echo signals into time-frequency spectrum signals from time sequence signals through short-time Fourier transform.
Further, the behavior recognizer: and identifying the behavior, specifically an embedded processing system based on a GPU or an FPGA.
Further, the alarm device: and receiving the alarm signal of the controller, performing sound-light alarm on the site, and generating a subordinate alarm signal.
Further, the image collector: the controller is connected with the controller, controls the image collector to take a snapshot on site and identify a specific target state and an environment state from a close view, and stores image data locally.
Further, the communication device: the system is in signal connection with a background management center, the subordinate alarm signals and the image data are linked with a background alarm in a wired or wireless communication mode, and the background management center further confirms the field situation according to the alarm signals and the image data and then takes emergency response measures.
Further, the controller: and receiving the judgment result of the behavior recognizer, and controlling the alarm device, the image collector and the communication device to work if the falling behavior occurs.
The system can be applied to industrial line operators such as underground operation and the like, or people with dangerous behavior monitoring requirements such as prisoners and the like. The device adopts a radar detection technology, can effectively solve the interference of environmental factors such as illumination, dust and the like on behavior detection, and has small information quantity and rapid information processing response. Meanwhile, the device greatly improves the classification and identification accuracy of the behavior detection, thereby providing a high-feasibility method for the behavior detection of underground operators.
[ description of the drawings ]
Fig. 1 is a block diagram of the human body recognition system of the present invention.
[ detailed description of the invention ]
The terms "connected" and "connected" are to be construed broadly, e.g., as meaning a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; may be directly connected or indirectly connected through an intermediate. To those of ordinary skill in the art, the specific meaning of the above terms in the present invention can be understood in combination with the specific situation. The present invention will be further described with reference to the following examples.
As shown in fig. 1, the human behavior recognition device includes a detection radar, a radar signal processor, a behavior recognizer, an alarm device, an image collector, a communication device and a controller; the radar signal processor is connected with the detection radar, the radar signal processor is respectively connected with the behavior recognizer and the controller, the image collector and the alarm device are respectively connected with the controller, and the controller is provided with a communication device.
The composition and connection relationship of each component are respectively as follows:
the detection radar is a Doppler radar: the method comprises the steps of detecting a human body target in a range in real time by transmitting continuous wave signals, and receiving reflected echo signals of the human body target, wherein the echo signals carry behavior state information of the human body target.
The radar signal processor: the radar echo signal is converted into a digital signal that can be processed by a Digital Signal Processor (DSP) through an analog-to-digital signal converter (ADC). The DSP performs short-time Fourier transform by selecting a Hamming window and determining the length of the corresponding window through short-time Fourier transform, and transforms the echo signal into a time-frequency spectrum signal from a time sequence signal. Subsequently, 4 features were defined by time-frequency analysis: maximum doppler positive frequency, minimum doppler negative frequency, maximum doppler shift, signal power corresponding to maximum doppler shift. The 4 characteristic signals are extracted from each group of collected signals.
The behavior recognizer is: and identifying the behavior, specifically an embedded processing system based on a GPU or an FPGA. And analyzing and judging the characteristic signals by adopting an optimized SVM classification algorithm, and identifying four behaviors of standing up, squatting, sitting down and falling down. Specifically, a support vector machine is used for learning and classifying, an SVM is trained to obtain a classification model, and a radial basis function is selected as a kernel function to classify data. And simultaneously, optimizing the penalty parameter C and the kernel function parameter g of the vector machine by utilizing a particle swarm optimization algorithm. And when the falling behavior is identified, sending out a field alarm signal.
The alarm device is characterized in that: and receiving the alarm signal of the controller, performing sound-light alarm on the site, and generating a subordinate alarm signal.
The image collector comprises: the controller is connected with the controller, controls the image collector to take a snapshot on site and identify a specific target state and an environment state from a close view, and stores image data locally.
The communication device comprises: the system is in signal connection with a background management center, the subordinate alarm signals and the image data are linked with a background alarm in a wired or wireless communication mode, and the background management center further confirms the field situation according to the alarm signals and the image data and then takes emergency response measures.
The controller: and receiving the judgment result of the behavior recognizer, and controlling the alarm device, the image collector and the communication device to work if the falling behavior occurs.
When the detection radar transmits continuous wave signals to detect a human body target in real time, receives echo signals carrying human body behavior information, then performs time-frequency analysis on the echo signals, converts the echo signals into easily-identified time-frequency spectrum signals, extracts characteristic parameters of the signals, and then identifies four behavior states of sitting, standing, squatting and falling through an SVM classification model, so that whether falling behaviors occur or not is judged, and a judgment result is sent to the controller. If the controller receives the fall judgment result, the controller controls the alarm to give an alarm on site, controls the image collector to automatically track the current target in a linkage manner, takes a snapshot and identifies a close scene, and then the controller further reports the alarm information and the image data to a background management center through a communication device to confirm again, and the background makes an emergency measure.
Each part of the utility model can be realized by the combination of hardware and firmware, and can also be realized independently. In the above embodiments, the various components may be implemented in firmware stored in the memory of the component itself and executed by a suitable instruction execution system. For example, in hardware, any one or a combination of the following techniques, which are well known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
The above is only the embodiment of the present invention, not the limitation of the technical solution described in the present invention, and all modifications or equivalent replacements made according to the content of the specification should be covered in the protection scope of the present invention.
Claims (8)
1. A human behavior recognition device is characterized by comprising a detection radar, a radar signal processor, a behavior recognizer, an alarm device, an image collector, a communication device and a controller; the radar signal processor is connected with the detection radar, the radar signal processor is respectively connected with the behavior recognizer and the controller, the image collector and the alarm device are respectively connected with the controller, and the controller is provided with a communication device.
2. The human behavior recognition device according to claim 1, further comprising a background management center, wherein the controller communicates with the background management center in real time through a communication device.
3. The human behavior recognition device according to claim 1, wherein the detection radar is a doppler radar: the method comprises the steps of detecting a human body target in a range in real time by transmitting continuous wave signals, and receiving reflected echo signals of the human body target, wherein the echo signals carry behavior state information of the human body target.
4. The human behavior recognition device according to claim 1, wherein the behavior recognizer: and identifying the behavior, specifically an embedded processing system based on a GPU or an FPGA.
5. The human behavior recognition device according to claim 1, wherein the alarm device: and receiving the alarm signal of the controller, performing sound-light alarm on the site, and generating a subordinate alarm signal.
6. The human behavior recognition device of claim 1, wherein the image collector: the controller is connected with the controller, controls the image collector to take a snapshot on site and identify a specific target state and an environment state from a close view, and stores image data locally.
7. The human behavior recognition device according to claim 1, wherein the communication device: the system is in signal connection with a background management center, the subordinate alarm signals and the image data are linked with a background alarm in a wired or wireless communication mode, and the background management center further confirms the field situation according to the alarm signals and the image data and then takes emergency response measures.
8. The human behavior recognition device according to claim 1, wherein the controller: and receiving the judgment result of the behavior recognizer, and controlling the alarm device, the image collector and the communication device to work if the falling behavior occurs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920454004.5U CN210271176U (en) | 2019-04-04 | 2019-04-04 | Human behavior recognition device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920454004.5U CN210271176U (en) | 2019-04-04 | 2019-04-04 | Human behavior recognition device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN210271176U true CN210271176U (en) | 2020-04-07 |
Family
ID=70021627
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201920454004.5U Expired - Fee Related CN210271176U (en) | 2019-04-04 | 2019-04-04 | Human behavior recognition device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN210271176U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113903147A (en) * | 2021-09-30 | 2022-01-07 | 湖南时变通讯科技有限公司 | Radar-based human body posture distinguishing method, device, equipment and medium |
-
2019
- 2019-04-04 CN CN201920454004.5U patent/CN210271176U/en not_active Expired - Fee Related
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113903147A (en) * | 2021-09-30 | 2022-01-07 | 湖南时变通讯科技有限公司 | Radar-based human body posture distinguishing method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3680206B1 (en) | System and method for detecting elevator maintenance behaviors in elevator hoistway | |
| CN104787084B (en) | A kind of railway foreign body intrusion detecting system and detection method | |
| CN110263686A (en) | A kind of construction site safety of image cap detection method based on deep learning | |
| CN104994334A (en) | Automatic substation monitoring method based on real-time video | |
| US20230012038A1 (en) | Systems and methods for automated detection of switch capacitor operation | |
| CN111965246B (en) | Scraper machine fault detection method and system based on multi-information fusion | |
| CN106291539B (en) | A kind of phased-array radar target identification system and method based on positioning filtering algorithm | |
| CN102164270A (en) | Intelligent video monitoring method and system capable of exploring abnormal events | |
| CN107526329A (en) | Robot management system based on artificial intelligence design | |
| CN103812577A (en) | Method for automatically identifying and learning abnormal radio signal type | |
| CN105427518A (en) | Digitalized risk decision system and method | |
| CN103983881A (en) | Fault diagnosis method and device for nuclear detector | |
| CN210271176U (en) | Human behavior recognition device | |
| CN109345787A (en) | A kind of anti-outer damage monitoring and alarming system of the transmission line of electricity based on intelligent image identification technology | |
| CN114988305A (en) | Early warning method for preventing suspension arm vehicle from electric shock during operation | |
| CN106153363B (en) | A kind of mechanical equipment fault automatic identifying method based on acoustic image monitoring | |
| CN107860691B (en) | Laser mine coal dust telemetry method based on machine vision technology | |
| CN202904792U (en) | Intelligent visualized alarm system | |
| US20220404784A1 (en) | Method and device for performing an operation based on sensor signal data | |
| CN207992777U (en) | A kind of garden potholing fertilizer applicator operating parameter harvester of high reliability | |
| CN112418604A (en) | Intelligent monitoring method for large-scale travelling crane wheel | |
| CN116488343B (en) | Intelligent power equipment safety monitoring system and method based on Internet of things | |
| CN116523321B (en) | Intelligent helmet security control system based on cloud platform | |
| CN102999988B (en) | Intelligent visualization alarm system and method for alarming by using system | |
| US20230308198A1 (en) | Radio wave abnormality detection system, radio wave abnormality detection method, and radio wave abnormality detection program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200407 |