Video semantic segmentation method based on optical flow feature fusion

Abstract

The invention discloses a video semantic segmentation method based on optical flow feature fusion. The method comprises the following steps: the step 1, judging whether a current video frame image ofa video sequence is a key frame image or a non-key frame image; if the image is a key frame image, executing the step 2, and if the image is a non-key frame image, executing the step 3; the step 2, extracting a high-level semantic feature map of fusion position dependent information and channel dependent information of the current video frame image; the step 3, calculating an optical flow field toobtain a high-level semantic feature map of the current video frame image; and the step 4, performing up-sampling on the high-level semantic feature maps obtained in the step 2 and the step 3 to obtain a semantic segmentation map. According to the method, the thought of an optical flow field and an attention mechanism is fused, so that the rate and accuracy of video semantic segmentation can be improved.

Description

technical field [0001] The invention relates to the technical field of video processing, in particular to a video semantic segmentation method based on optical flow feature fusion. Background technique [0002] With the increasing market demand for automotive active safety and intelligence, more and more companies and research institutions have begun to devote themselves to the research and development of autonomous driving systems. The environment perception technology in the automatic driving system acts as the eyes and ears of the automatic driving vehicle, and provides support for the behavioral decision-making system of the automatic driving. In the autonomous driving environment perception technology, fast and accurate semantic segmentation of the real-time video data collected by the vehicle camera is a crucial technology. [0003] Self-driving cars perform semantic segmentation of real driving scenes. The core issue is to extract road semantic information, improve t...

AI Technical Summary

Problems solved by technology

[0004] First, in the field of autonomous driving applications, there are many and complex instances in video data, resulting in low semantic segmentation accuracy of video semantic segmentation algorithms

[0005] Second, compared with the image semantic segmentation task, the video semantic segmentation task processes a larger amount of data, resulting in a larger amount of calculation for the video semantic segmentation algorithm and high segmentation delay.

Images