A low-power image recognition module
An image recognition, low-power technology, applied in image communication, character and pattern recognition, television and other directions, can solve the problems of huge data transmission pressure, data processing pressure, complexity, high power consumption, etc., to reduce communication requirements and reduce power Consumption, the effect of saving power consumption
Active Publication Date: 2018-07-06
成都芯软科技股份公司
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Although the image recognition algorithm in the prior art is already very complete, it is generally complex, and the image transmission operation also consumes a lot of power, and this operation also brings huge data to the monitoring end of the central monitoring room. Transmission pressure and data processing pressure
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
[0031] like figure 1 As shown, the low-power image recognition module includes: the image acquisition unit, an image preprocessing unit, and an image recognition unit.
[0032] Wherein, the image acquisition unit includes:
[0033] The image optical acquisition unit is used to obtain the optical signal of the image. According to an embodiment of the present invention, the image acquisition unit adopts an optical lens group, such as a plurality of convex lenses bonded together.
[0034] The sound collection unit is used for collecting sound information. The unit can use audio input devices such as recording pens and microphones.
[0035] According to a preferred embodiment of the present invention, the preprocessing unit includes: a photoelectric conversion unit, a judgment unit, and an image transmission unit. in:
[0036] The photoelectric conversion unit is used to obtain corresponding electrical signals representing image information according to optical signals at dif...
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
In order to reduce the power consumed by the monitoring terminal in the central monitoring room to identify the image or video information of the monitoring point, and at the same time reduce the network data transmission pressure in the security monitoring system, the present invention provides a low-power image recognition module, including: A collection unit, which collects monitoring images; an image preprocessing unit, which preprocesses the image information collected by the image collection unit; an image recognition unit, which performs image recognition based on the output of the image preprocessing unit. The invention can control the image acquisition equipment such as the camera of the monitoring point to send image information to the monitoring end when necessary, which reduces the transmission of unnecessary image frames, further reduces the communication demand, saves the power consumption related to communication, and can The pattern can further accurately determine the identity of personnel or abnormal information, and improve the safety of security monitoring.
Description
technical field [0001] The present invention relates to the technical field of image information processing, and more specifically, to a low-power image recognition module. Background technique [0002] With the continuous development of computer and network technology, the video surveillance system is transitioning from the analog era to the digital, network and intelligent direction. Intelligent video surveillance technology includes the analysis of video signals and the recognition and understanding of moving target patterns. The analysis of video signals, such as dynamic target detection and tracking, is the basis for building an intelligent video surveillance system; the core content of intelligent monitoring is the understanding of moving target patterns, especially the recognition and classification of moving targets, such as human figure recognition, abnormal Behavior detection and identification, scene understanding, etc. This is especially indispensable for secur...
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 Patents(China)
IPC IPC(8): H04N7/18H04N5/225G06K9/00
CPCH04N7/18H04N23/54H04N23/55G06F2218/12
Inventor 葛辉
Owner 成都芯软科技股份公司