Pedestrian detection method based on on-board infrared camera

Abstract

The invention relates to a pedestrian detection method based on an on-board infrared camera. A traditional method is time consuming. According to the pedestrian detection method based on the on-board infrared camera, at first, the infrared camera is horizontally erected at the position of the car head and calibrated. Secondly, the pre-installed camera detects distance range to determine the upper and the lower boundary. And then a bounding box is selected, histograms of oriented gradients (HOG) feature of the remained candidate boxes is extracted, and a pre-trained SVM classifier is used for judging whether a bounding box is a pedestrian or not. Finally, the bounding box is judged as the pedestrian according to scale and distance clustering step 5 and the camera slides smoothly to obtain the final detection and tracking of the pedestrian. The pedestrian detection method based on the on-board infrared camera is low in time consumption and error detection, and convenient to embedded in real-time application.

Description

technical field [0001] The invention belongs to the field of intelligent video monitoring, and in particular relates to a pedestrian detection method based on a vehicle-mounted infrared camera. Background technique [0002] For pedestrian detection with on-board cameras, the current methods are either the background difference method based on the motion camera [1], or the pattern recognition method based on the full image search [2], which are relatively time-consuming methods. Although the method based on dual (multi) camera [3] can use the depth information to extract the region of interest and then detect it, obtaining the depth information itself is a time-consuming process. [0003] Some methods [4] reduce time-consuming by extracting certain features of people, such as the head, for preliminary positioning and then detection, but often cause problems such as a decrease in detection rate. [0004] Related literature and patents: [0005] [1]Online Moving Camera Backgr...

AI Technical Summary

Problems solved by technology

[0002] For pedestrian detection under the vehicle camera, the current method is either the background difference method based on the motion camera [1], or the pattern recognition method based on the full image search [2], which are relatively time-consuming methods

The method based on dual (multi) camera[3] can use the depth information to extract the region of interest and then detect it, but obtaining the depth information itself is a time-consuming process

[0003] Some methods [4] reduce time-consuming by extracting certain features of people, such as the head, for preliminary positioning and then detection, but often cause problems such as a decrease in detection rate

Images