Charging operation behavior specification monitoring method
A behavioral and standardized technology, which is applied in image data processing, instruments, biological neural network models, etc., can solve problems such as endangering the safety of operators, difficulty in ensuring standard charging operation behavior, and affecting blasting effects, so as to improve safety and reduce The cost of manual care and the effect of improving care efficiency
Pending Publication Date: 2021-04-16
鞍钢矿业爆破有限公司
View PDF3 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The charging operation is an important link in the construction process of the blasting site. At present, because there is no effective method to monitor the standardization of the workers' charging operation, it is difficult to guarantee the standard behavior of the charging operation, which may affect the blasting effect and endanger the safety of the operators.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0036] The present invention will be further elaborated below in conjunction with the accompanying drawings of the description.
[0037] The invention provides a method for monitoring the charging operation behavior specification, comprising the following steps:
[0038] 1) image data acquisition, the image data is obtained through the camera, transmitted through the router and stored in the image data unit;
[0039] 2) Target detection: use the YOLO model to detect the operation behavior of the operator in the image in real time;
[0040] 3) Target tracking: Based on the deepsort target tracking algorithm, the current target position is preliminarily predicted and judged, and the target to be tracked is locked;
[0041] 4) Action recognition: use a three-dimensional convolutional neural network to model the two-dimensional direction of the target image, extract time-series features, and obtain accurate action recognition results;
[0042] 5) According to the real-time detec...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a charging operation behavior specification monitoring method, which comprises the following steps of: acquiring image data, namely acquiring the image data through a camera, transmitting the image data through a router and storing the image data into an image data unit; target detection: adopting a YOLO model to detect an operation behavior of an operator in the image in real time; target tracking: performing preliminary prediction and judgment on the position of the current target based on a depsort target tracking algorithm, and locking the target to be tracked; action recognition: modeling the two-dimensional direction of the target image by using a three-dimensional convolutional neural network, and extracting features in a time sequence, thereby obtaining an accurate action recognition result; and according to a character action recognition result detected in real time, marking an action category in a monitoring video displayed in a monitoring room, and responding to non-standard actions. Potential safety hazards caused by improper operation are effectively avoided, the safety of a charging operation site is improved, the manual guarding cost is reduced, and the guarding efficiency is improved.
Description
technical field [0001] The invention relates to a behavior specification evaluation technology in the field of blasting, in particular to a monitoring method for charge operation behavior specifications. Background technique [0002] Blasting technology is an engineering technology that uses the energy of explosive explosion to destroy the original structure of a certain object, and realizes the arrangement of charges and detonation methods adopted for different engineering purposes. As an engineering blasting energy source, explosives contain huge energy. Industrial explosives must be detonated with a detonator, which is relatively safe. Modern detonation methods include electric and non-electric methods. The former detonates the explosive by electrothermally igniting the hot bridge wire in the electric detonator; the latter detonates the detonator by the flame of the fuse or the shock wave transmitted by the detonating cord and nonel tube, thereby Primer pack. The two de...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06T7/277G06K9/62G06N3/04
Inventor 张耿城廖耀福田思雨肖成勇白镕宇张日强刘万义耿图禹
Owner 鞍钢矿业爆破有限公司