A method and apparatus for detecting target object

Abstract

The invention discloses a method and device for detecting a target object, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: extracting a sample picture set from a historical video file recorded in a to-be-detected area; performing target object detection on the sample picture set based on a first confidence coefficient threshold value and a second confidence coefficient threshold value which are different in size to obtain sample data sets under different confidence coefficient thresholds; determining an invalid region by comparing the sample data set under the first confidence threshold value with the sample data set under the second confidence threshold value; and when the currently acquired image data is detected, excluding the target object in the invalid area. According to the embodiment, the detection accuracy of the target object can be improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for detecting a target object. Background technique [0002] "Object detection" is a technical means that uses computer vision technology to judge whether there is a target object in an image or video sequence and give it a location; among them, "pedestrian detection" is the most widely used, in artificial intelligence systems, vehicle assisted driving systems, intelligent robots, Intelligent video surveillance, human behavior analysis and intelligent transportation all play an important role. [0003] There are various existing object detection algorithms, but the methods for outputting results are basically the same: use the detection frame to locate the detected object, and calculate the probability that the object belongs to each of the preset multiple categories, Take the maximum value of the probability as the confidence that the object in the detecti...

AI Technical Summary

Problems solved by technology

[0004] In the process of realizing the present invention, the inventors have found that there are at least the following problems in the prior art: in the detection method of the prior art, the confidence threshold is difficult to determine; if the confidence threshold is too small, the detection result may falsely detect other Objects, resulting in inaccurate results; if the confidence threshold is too large, the number of detection results will be greatly reduced, and some real target objects will be missed, which also has the problem of inaccurate results

Images