Remote sensing image vehicle target detection method based on anchor-point-free accurate sampling

Abstract

The invention discloses a remote sensing image vehicle target detection method based on anchor-point-free accurate sampling, and the method comprises the following steps: S1, carrying out the featureextraction of an original image through a multilayer convolution neural network, and forming a top-down feature pyramid according to feature maps with different scales; S2, for each layer of featuresof the feature pyramid, generating category prediction of all pixel points on the feature map; S3, for each layer of features of the feature pyramid, generating target box prediction of all pixel points on the feature map; S4, determining a feature map to which the current vehicle target belongs according to the real frame area information in the input picture; S5, determining a positive sample pixel point of the target in the layer of features by means of target instance segmentation information in the real box, and calculating a difference value from the pixel point to four edges of the realbox; and S6, calculating category loss of all positive sample pixel points and regression loss about a real box.

Description

technical field [0001] The invention belongs to the technical field of image processing based on deep learning, and in particular relates to a vehicle target detection method based on accurate sampling of remote sensing images without anchor points. Background technique [0002] In recent years, with the development of satellite remote sensing technology, it is more and more convenient to obtain ground pictures from the air. At the same time, with the economic development of the society, the number of vehicles is also increasing year by year. People's requirements for urban transportation capacity are also increasing, and the acquisition of traffic conditions in large-scale areas is becoming more and more important. Obtaining vehicle information in remote sensing images through a satellite platform has great advantages and convenience. Among them, vehicle target detection in remote sensing images is the basic and important task of intelligent transportation, urban traffic a...

AI Technical Summary

Problems solved by technology

In this way, although the quality of the results close to the center of the target is higher, it reduces the number of sampling points. After the vehicle target is processed by the deep network, the number of retained pixels is relatively small, and the non-real instance in the target frame The target pixels interfere with the detection results

The second is that in the inclined vehicle target frame, there is too much background information, and the sampling in the central area cannot represent the entire vehicle target.

Third, for objects with special shapes, only sampling the central area of ​​the target frame will lose most or even all feature information of the object, making the model less versatile

Images