Method and device for counting the number of objects in an area

Abstract

The present invention provides a method and device for counting the number of targets in an area, wherein the method includes: collecting images in the area; extracting multiple frames of images in the image as key frame images; screening multiple key frame images, and The target object in the key frame image is calibrated with a calibration frame; according to the calibration of the target object in the key frame image, the preliminary detection result of the number of target objects is obtained through calculation; the first tracking inspection is carried out on the preliminary result; the second is carried out on the preliminary result Tracking inspection: update the quantity of objects according to the result of the first tracking inspection and the result of the second tracking inspection, and obtain the final detection result of the quantity of objects. The method for counting the number of targets in the area provided by the present invention performs two data tracking on the data, cooperates with each other through the results of the two tracking checks, and updates the number of targets to accurately obtain the number of targets. The resulting mutation degradation caused by overlapping has been greatly improved.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method for counting the number of objects in an area and a device for counting the number of objects in the area. Background technique [0002] The description of the background technology in the present invention belongs to the related art related to the present invention, and is only used to illustrate and facilitate the understanding of the invention content of the present invention, and should not be construed as the applicant's explicit belief or presumption that the applicant believes that the present invention is the first application of the present invention. the prior art of the filing date. [0003] At present, most breeding enterprises rely on manual inventory and calculation, not only the working environment is harsh, but also the counting of real-time moving animals will inevitably produce errors. At the same time, the low labor efficiency further reduces the timel...

AI Technical Summary

Problems solved by technology

[0003] At present, most breeding enterprises rely on manual inventory and calculation, not only the working environment is harsh, but also the counting of real-time moving animals will inevitably produce errors

At the same time, the low labor efficiency further reduces the timeliness of data and further reduces the value of data

Among the emerging solutions, a large number of neural network methods are limited to the training and modification of detectors, and for a large-scale and large-scale farming scene, a single camera cannot cover all areas, and a single target detection algorithm counts The time series and the spatial mobility of livestock will also be ignored in the process, and the results will be greatly deviated

In the early research work, the matching problem of detection is the most important core problem of tracking problem. Therefore, based on the traditional Hungarian algorithm, the effect of Kalman filter algorithm combined with cascade matching will be affected by sudden changes in detector performance and overlapping objects. leading to strong degradation in tracking results

Images