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

Abstract

Embodiments of the present invention provide a neural network training and construction method and device for target detection and a neural network-based target detection method and device. The neural network training method for target detection includes: inputting the training image containing the training target to the neural network to obtain the predicted bounding box of the training target; according to the intersection area of ​​the predicted bounding box and the real bounding box and the ratio of the area of ​​the union to obtain a first loss function, the true bounding box is the bounding box of the training target pre-marked in the training image; and at least use the first loss function to adjust the neural network parameters to train the neural network. The neural network training and construction method and device and the target detection method and device of the embodiments of the present invention use the first loss function to regress the target bounding box into a whole unit, which significantly increases the target detection accuracy of the neural network, and can pass the neural network. The two-branch structure effectively improves the training and detection efficiency 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