A camera image motion detection area conversion method

CN114245106BActive Publication Date: 2024-11-29HANGZHOU VISION INSIGHT TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202111543526.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-17
Publication Date
2024-11-29
Estimated Expiration
2041-12-17

AI Technical Summary

Technical Problem

The movement detection area of ​​existing network cameras cannot be selected carefully, which cannot be ruled out movement events in invalid areas in the picture, and is easily triggered at the edge, resulting in a high false alarm rate.

Method used

By circled a polygon in the picture, obtain the intersection coordinates and number of edges of each edge, and then convert it into a coordinate set that infinitely approaches the smallest pixel block of the circled picture to be detected. The minimum pixel block can be set independently to balance the equipment performance and detection area accuracy.

Benefits of technology

It realizes the setting of the mobile detection area more finely in the actual use environment, reduces the false alarm rate and improves the accuracy of detection events.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114245106B_ABST
    Figure CN114245106B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of network cameras. The present invention discloses a method for converting a camera image motion detection area. First, the intersection coordinates and the number of edges are obtained. Then, the entire image is serialized into a set of point coordinates by setting the minimum pixel. Then, a specific method is used to determine whether the serialized coordinate points are within the detection area. If they are within the area, they are recorded. Finally, all the coordinate points within the area are obtained. Then, the coordinate points are restored to the corresponding area. Finally, a detection area composed of quadrilaterals with the minimum detection pixel as the unit is obtained. The present invention can make the area setting of motion detection more in line with the actual use environment, can be set according to the actual use scenario, is more humane, and greatly reduces the false alarm rate of motion detection.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • 3D light field conversion method and device

    CN113645462A

  • Video screening method based on face recognition

    CN113779309A