Target detection method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a target detection method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a current frame of a video imageas a to-be-detected image; performing feature extraction on the to-be-detected image to obtain a corresponding feature map; dividing the image to be detected into at least two grids based on the feature map; and if the center of a first target object falls into a certain grid, predicting the first target object according to a preset anchor point of the grid to obtain a first detection box of the first target object and a second detection box of a target area of the first target object. According to the embodiment of the invention, the performance of target detection can be ensured, and the real-time performance of target detection can be improved.

Description

technical field [0001] The present application relates to the technical field of video image processing, and in particular to a target detection method, device, electronic equipment and storage medium. Background technique [0002] Computer vision is a science that studies how to make machines "see". It uses image acquisition equipment and computers instead of human eyes to identify, track and measure targets, covering various technologies such as image semantic understanding, image recognition, and video image processing. , and in the field of video image processing, target detection plays a particularly important role. In general, target detection methods are divided into methods based on artificially designed features and methods based on deep learning. Among them, the method based on artificially designed features first extracts features from the candidate area, and then uses a classifier to classify the candidate area to determine whether it contains detection target, ...

AI Technical Summary

Problems solved by technology

In general, target detection methods are divided into methods based on artificially designed features and methods based on deep learning. Among them, the method based on artificially designed features first extracts features from the candidate area, and then uses a classifier to classify the candidate area to determine whether it contains detection target, but the detection performance of methods based on artificially designed features is poor

In comparison, the method based on deep learning has superior detection performance, and the learned features have stronger hierarchical expression ability and robustness, which can be directly applied to target detection. However, the method based on deep learning has complex algorithms and computational complexity. The amount is large, and the real-time performance of detection still cannot meet the actual needs

Images