Cross-scale adaptive mapping light field imaging method

Abstract

The embodiment of the invention discloses a cross-scale adaptive mapping light field imaging method, and the method comprises the steps: obtaining a light field image collected by a light field camera and a gray-scale map collected by an event camera, according to the light field image and the grey-scale map, determining a current area distribution image containing at least one dynamic object and a movement speed corresponding to each dynamic object; determining a motion saliency index according to the light field image, the current area distribution image and the motion speed corresponding to each dynamic object; screening each dynamic object according to the motion saliency index to obtain a target motion object; and determining a target image according to the target moving object. According to the invention, the problem of frequent and mass acquisition and processing of images caused by tiny change when the images of the monitoring area are acquired is solved, dynamic objects which do not need to be concerned or do not expect to be concerned in the images can be effectively filtered, the data processing amount is reduced, the data analysis speed is improved, a target moving object is visually observed through the target image, and subsequent data processing is facilitated.

Description

technical field [0001] Embodiments of the present invention relate to image processing technologies, and in particular to a light field imaging method for cross-scale adaptive mapping. Background technique [0002] With the improvement of social informatization, big data collection, analysis, and storage have gradually become the bottleneck restricting its further development. In the field of video surveillance, performance indicators such as camera resolution and frame rate are gradually improving. However, high-definition video sequences put forward higher requirements for storage and subsequent analysis in terms of hardware computing power and efficient algorithms. In many surveillance scenarios, the monitored object or environment is static and stable most of the time, but the high-definition surveillance camera equipment is still shooting continuously, generating a large amount of data to be saved in real time. Although the volume of these data is huge, the amount of e...

AI Technical Summary

Problems solved by technology

[0003] Although the motion-triggered monitoring system can avoid continuous invalid collection when the picture is still for a long time, and alleviate the huge pressure of data storage to a certain extent, in order to ensure that information is not missed and collected, the sensitivity of motion-triggered is generally relatively high, for example, when It is hoped that the monitoring system will trigger the collection when pedestrians pass by, but due to its high sensitivity, it will start to collect when birds fly by. After the data collection is completed, when the follow-up data analysis is performed, due to the high resolution of the image and the single source of information, etc. problems, causing defects such as slow analysis and loss of information

Images