Frame level feature aggregation method for video target detection

Abstract

The invention provides a frame level feature aggregation method for video target detection, and relates to the technical field of computer vision. The invention provides a frame-level feature aggregation method for video target detection. The method comprises the following steps: firstly, extracting deep features from a single-frame image through a feature network; extracting an inter-frame optical flow by using an optical flow network FlowNet; aligning the frame-level features of the adjacent frames to the current frame based on the optical flow to realize frame-level feature propagation; finally, calculating the scaling cosine similarity weight through the mapping network and the weight scaling network, and using the scaling cosine similarity weight to aggregate the multi-frame featuresto generate the aggregated features. According to the frame-level feature aggregation method for video target detection provided by the invention, the weight distribution is more reasonable, and the aggregated features are input into the video target detection network, so that video detection in complex scenes such as motion blur, low pixels, lens zooming and shielding can have a better detectioneffect and robustness.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a frame-level feature aggregation method for video target detection. Background technique [0002] In recent years, with the rise of deep learning, video object detection has gradually developed rapidly. Since target detection in video has more temporal context information and motion information than target detection in a single image, many studies have used this information to improve the performance of video target detection. The video target detection method automatically analyzes and processes the video sequences collected by the camera, and then realizes the detection, classification, recognition and tracking of moving targets in the monitoring scene. Most existing feature-level video object detection methods use frame-level feature aggregation methods. The purpose of frame-level feature aggregation is to use the time and motion information between video frames to ...

AI Technical Summary

Problems solved by technology

In complex scenes such as motion blur, low pixels, lens zoom, occlusion, etc., the above methods cannot accurately detect moving objects, resulting in a high false detection rate and missed detection rate of video object data detection.

Images