Neural network training and construction method and device, and object detection method and device

Abstract

The embodiment of the invention provides a neural network training and construction method and device for object detection, and an object detection method and device based on a neural network. The neural network training and construction method for object detection comprises the steps: inputting a training image comprising a training object into the neural network, so as to obtain a prediction boundary frame of the training object; obtaining a first loss function according to the ratio of the intersection area and union area of the prediction boundary frame and a real boundary frame, wherein the real boundary frame is the boundary frame of the training object marked in the training image in advance; and adjusting the parameters of the neural network at least through the first loss function, so as to carry out the training of the neural network. According to the invention, the first loss function is employed for the regression of a target boundary frame into an integrated unit, and the object detection precision of the neural network is remarkably improved. Moreover, the training and detection efficiency of the neural network can be effectively improved through two branch structures of the neural network.

Description

technical field [0001] Embodiments of the present disclosure relate to image processing, and in particular to a method and device for training and constructing a neural network for object detection, and a method and device for object detection based on a neural network. Background technique [0002] Object detection is a basic research topic in the field of computer vision, and it has broad application prospects in many aspects such as face recognition, security monitoring, and dynamic tracking. Target detection refers to detecting and identifying a specific target (such as a face) in any given image, and returning the position and size information of the target, such as outputting a bounding box surrounding the target. Target detection is a complex and challenging pattern detection problem. There are two main difficulties. On the one hand, it is caused by internal changes such as target detail changes and occlusions. On the other hand, it is caused by imaging angles and lig...

AI Technical Summary

Problems solved by technology

However, the target detection results obtained by the current CNN-based target detection method still have technical problems such as being affected by the inherent changes of the target, inaccurate target recognition, and low detection efficiency.

Images