Remote sensing image target detection method based on smooth frame regression function

Abstract

The invention discloses a remote sensing image target detection method based on a smooth frame regression function, and the method comprises the steps: carrying out the necessary preprocessing of a training image, and setting the hyper-parameters of network training; inputting the picture into a target detection convolutional neural network to obtain a feature map; inputting the feature map into aregion suggestion network to obtain a candidate box; sending the candidate boxes and the feature map into a region-of-interest pooling layer to obtain region-of-interest features, and classifying theregion-of-interest features in a classifier; sending the obtained features of the region of interest into a full connection layer to obtain predicted offset, sending the predicted offset into a smooth frame regression function to obtain actual offset, and correcting a candidate frame to a new position; repeating the steps until the training process is finished; and preprocessing the to-be-detected image and then inputting the preprocessed to-be-detected image into the trained network to obtain a target detection result. High-precision frame regression can be effectively realized, and higher-precision target detection can be realized under the condition of a high IOU threshold.

Description

technical field [0001] The invention belongs to the field of image processing and machine learning, and relates to a remote sensing image target detection method based on a smooth frame regression function. Background technique [0002] With the rapid development of remote sensing technology, the amount of remote sensing data is increasing rapidly. In the face of increasingly large and complex remote sensing information, how to quickly and efficiently process the original remote sensing images and make them information that users can understand and use has become an important issue. research topics. Target detection in remote sensing images is one of the core tasks in remote sensing image understanding. Its main purpose is to quickly find and accurately locate targets of interest in remote sensing images. Target detection itself is an important task and the basis of many tasks. Such as instance segmentation, image understanding, etc. However, the detection accuracy of the ...

AI Technical Summary

Problems solved by technology

With the progress of the training process, the quality of the candidate frame is gradually improved, getting closer and closer to the real frame. At this time, the gap will become smaller, and the volatility will be greater, the more difficult it is to stabilize the regression, especially at the zero point Nearby, the regression will fail due to continuous shocks, resulting in low regression accuracy

Images