Training method and device of multi-task detection model and terminal equipment

Abstract

The invention is suitable for the technical field of image processing, and provides a multi-task detection model training method and device, terminal equipment and a computer readable storage medium, applied to a preset multi-task detection model, the multi-task detection model comprises a feature extraction network and a multi-task detection network, the method comprises the following steps: acquiring global feature information and local feature information of a training image through the feature extraction network; inputting the global feature information into the multi-task detection network to obtain a multi-task detection result; obtaining a semantic segmentation result of the training image according to the global feature information and the local feature information; and training the multi-task detection model according to the multi-task detection result and the semantic segmentation result. By means of the method, the calculation amount of multi-task detection can be reduced, and meanwhile the accuracy of multi-task detection is improved.

Description

technical field [0001] The present application belongs to the technical field of image processing, and in particular relates to a training method, device, terminal equipment and computer-readable storage medium of a multi-task detection model. Background technique [0002] With the continuous development of artificial intelligence in recent years, deep neural networks have been widely used in the field of computer vision. For example, in the application field of automatic driving, the target detection task based on deep neural network can be used to detect objects such as obstacles and signs during driving, and the lane line detection task based on deep neural network can be used to detect lane lines on the road . [0003] As mentioned in the above example, multiple detection tasks need to be performed in the same application scenario. In the prior art, a multi-task detection network can be used to perform multiple detection tasks, and an image to be detected can be input ...

AI Technical Summary

Problems solved by technology

However, each detection task in the existing multi-task detection network is executed independently, the amount of calculation is large, and the correlation features between different detection targets cannot be used, resulting in low detection accuracy

Images