A target detection method, device, equipment and readable storage medium

By performing density detection and adaptive block cropping on ultra-large pixel images, combined with background modeling and an adapted target detector, the problem of low detection accuracy in ultra-large pixel images is solved, and efficient target detection and tracking are achieved.

CN115131707BActive Publication Date: 2026-05-26INSPUR SUZHOU INTELLIGENT TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
INSPUR SUZHOU INTELLIGENT TECH CO LTD
Filing Date
2022-06-30
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing object detection algorithms cannot effectively handle ultra-large pixel images, resulting in low detection accuracy. Furthermore, the existing sliding window image slicing and stitching method further reduces the accuracy of object detection.

Method used

Density detection technology is used to dynamically and adaptively segment ultra-large pixel images. Image blocks are cropped according to the density detection results, and a suitable target detector is selected for detection. Background modeling is combined to remove non-target areas, thus optimizing the image segmentation and detection process.

Benefits of technology

It improves the accuracy and speed of target detection, reduces hardware requirements, enhances the cost-effectiveness of the target detection system, and supports target tracking applications.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115131707B_ABST
    Figure CN115131707B_ABST
Patent Text Reader

Abstract

This application discloses a target detection method, apparatus, device, and readable storage medium. The method includes: acquiring a current frame image; performing density detection on targets in the current frame image to obtain density detection results; cropping the current frame image according to the density detection results to obtain image blocks; inputting each image block into a target detector corresponding to the target density in the image block for target detection; and stitching together the target detection results of each image block to obtain the target detection result of the current frame image. The above-disclosed technical solution dynamically and adaptively divides the current frame image into blocks based on the target density distribution, and selects a target detector adapted to the image block based on the target density distribution in different image blocks for target detection, thereby improving target detection capability and accuracy. Furthermore, density detection of the current frame image can remove non-target regions, thus improving target detection speed.
Need to check novelty before this filing date? Find Prior Art