A self-adaptive city people searching method based on edge computing
An edge computing and adaptive technology, applied in computing, computer components, instruments, etc., can solve the problems of large amount of calculation, high energy consumption, long response time, etc., to reduce the response time, reduce the amount of calculation, reduce the amount of calculation and the effect of calculating energy consumption
Active Publication Date: 2019-06-21
SUN YAT SEN UNIV
View PDF10 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In order to overcome the defects of large amount of calculation, high energy consumption and long response time in the centralized calculation of pedestrian detection and pedestrian re-identification in the above-mentioned prior art, the present invention provides an adaptive urban person-finding method based on edge computing
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 1
[0046] Such as figure 1 Shown, a kind of edge computing-based self-adaptive urban person-finding method, described method comprises the following steps:
[0047] S1: Convert the surveillance video into video frames through the edge node, and select the video frame to be uploaded to the edge server as the fth o frame, set the similarity threshold between video frames, and set the fth o The video frames following the frame are respectively related to the fth o Calculate the similarity of the frame, find the first video frame whose similarity is less than the similarity threshold, and put the found video frame into the queue to be uploaded Trigger_frame Upload the video frame to the edge server in the order of the queue, and at the same time upload the found video frame Frame as the last uploaded video frame, continue to search for the current video frame to be uploaded; the present invention can filter out redundant video frames by setting the similarity threshold between vide...
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 self-adaptive city people searching method based on edge calculation. The method comprises the following steps: a monitoring video is converted into a video frame, an uploaded video frame is selected, redundant video frames are filtered, a to-be-uploaded video frame is searched, and the searched video frame is uploaded to an edge server; Pedestrian detection is carried out on the uploaded video frame pedestrians, pedestrian re-identification is carried out on the detected pedestrians in a certain proportion, and pedestrian characteristics are output; The edge server uploads K identified pedestrians with the highest similarity with the searched target to the cloud server at regular time; A pedestrian re-identification module on the cloud server is used for re-identifying the pedestrians of the remaining proportion, the identification results of the cloud server and the edge server are combined, and K identified pedestrians with the highest similarity with the searched target are returned to the terminal at regular time to be processed. According to the method, the defects of large centralized calculation amount, high energy consumption and long response time are overcome, the calculation amount is reduced by filtering redundant video frames, and meanwhile, the calculation energy consumption and the response time are reduced.
Description
technical field [0001] The present invention relates to the field of edge computing, and more specifically, to an adaptive urban person-finding method based on edge computing. Background technique [0002] With the development of transportation and the increase of floating population, the number of lost people in cities is on the rise. Lost people are often unable to be quickly retrieved or even never heard from due to low efficiency of tracing. So how to use new technologies to quickly and effectively find people? People urgently need to be resolved. Before the rise of Internet technology, posting missing person notices was the main way. This traditional method has been gradually eliminated due to its shortcomings such as low efficiency and low success rate. With the development of Internet technology, urban person tracing has gradually transformed into online person tracing. Major Internet companies, such as Alibaba, Sina, and Toutiao, have successively launched their own...
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 IPC IPC(8): G06K9/00H04L29/08H04N7/18
Inventor 刘芳马东辉黎燊梁家越
Owner SUN YAT SEN UNIV