A Pedestrian Detection Method Based on Thermal Imaging Background Filtering

Abstract

The invention discloses a pedestrian detection method based on thermal imaging background filtering, which comprises the following steps: firstly, the original thermal imaging picture obtained by a thermal imaging infrared camera is subjected to histogram mean value processing, and then threshold value segmentation is performed by setting a suitable threshold Obtain the preliminary candidate area for pedestrian detection, and at the same time, based on the Gaussian mixture model, separate the foreground and background from the relationship between the front and rear frames of the image, obtain the background subtraction image, and send the composite image obtained after the two are connected to the subsequent improved Faster R‑ The CNN framework completes the work of pedestrian detection. The present invention solves the problem of temperature drift in thermal imaging camera imaging results through normalization, uses threshold segmentation and background subtraction for background filtering, fully utilizes the characteristics of thermal imaging pictures, and improves pedestrian detection in low-light and no-light environments precision.

Description

technical field [0001] The invention relates to a pedestrian detection method based on thermal imaging background filtering, which belongs to the field of target detection of image processing. Background technique [0002] Vision is the most direct and main method for organisms to obtain environmental information. At the same time, the amount of information obtained through vision is also very rich, so the processing of visual information plays a vital role in environmental information processing. Vision-based object detection is currently a research hotspot in the field of computer vision. [0003] In recent years, with the development of artificial intelligence, deep learning and other fields, vision-based object detection has made great progress. Different from the traditional object detection method based on feature extraction, the object detection method based on deep learning extracts the deep information of the image through the deep neural network, and uses massive ...

AI Technical Summary

Problems solved by technology

However, visible light images are very susceptible to environmental influences

Images