Target detection method and device, electronic equipment and computer readable medium

Abstract

The embodiment of the invention discloses a target detection method and device, electronic equipment and a computer readable medium. A specific embodiment of the method comprises the following steps: segmenting an acquired image into image sub-images to obtain an image sub-image set; performing binary division processing on each image sub-image in the image sub-image set to generate a binary image, and obtaining a binary image set; selecting a binary image containing a salient region from the binary image set as a target binary image to obtain a target binary image set; selecting an image sub-image corresponding to the target binary image from the image sub-image set as a target sub-image to obtain a target sub-image set; carrying out fine-grained target detection on each target sub-image in the target sub-image set to generate a target image, and obtaining a target image set, wherein the target image in the target image set comprises target positioning information and target classification information. According to the embodiment, the image processing time is shortened, and the consumption of memory resources in the processing process is reduced.

Description

technical field [0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular, to a target detection method, apparatus, electronic device, and computer-readable medium. Background technique [0002] Object detection is an image segmentation based on the geometric and statistical features of objects. Traditional target detection methods mainly use steps such as foreground and background separation, hand-designed features, and training classifiers to locate and identify targets. The algorithm has poor robustness and flexibility, and low accuracy. The target detection algorithm based on deep learning uses massive remote sensing image data, and after deep extraction of features, the classification and regression are slow. [0003] However, when the above method is used for target detection, there are often the following technical problems: [0004] First, the target detection algorithm using deep learning takes a long time and consu...

AI Technical Summary

Problems solved by technology

[0004] First, the target detection algorithm using deep learning takes a long time and consumes a lot of memory resources;

[0005] Second, without overlapping filtering processing, the same target is marked multiple times on the obtained image, which cannot be put into actual production use

Images