A 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, which includes the following steps: Step 1: Determine whether a current video frame image of a video sequence is a key frame image or a non-key frame image; if it is a key frame image, execute Step 2, if it is a non-key frame image, perform step 3; Step 2, extract the high-level semantic feature map of the fusion position-dependent information and channel-dependent information of the current video frame image; Step 3, obtain the current video frame by calculating the optical flow field. The high-level semantic feature map of the image; step 4, up-sampling the high-level semantic feature map obtained in steps 2 and 3 to obtain a semantic segmentation map. The method of the present invention integrates the idea of ​​optical flow field and attention mechanism, which can improve the speed and accuracy of video semantic segmentation.

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 focus on the research and development of autonomous driving systems. The environment perception technology in the automatic driving system, as the eyes and ears of the automatic driving vehicle, provides support for the behavioral decision-making system of the automatic driving. In autonomous driving environment perception technology, fast and accurate semantic segmentation of real-time video data collected by vehicle cameras is a crucial technology. [0003] The core problem of autonomous vehicle semantic segmentation of real driving scenes is to extract road semantic information, and to improve the segmentation speed of th...

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