An indoor personnel detection method based on video image

Abstract

The invention relates to an indoor personnel detection method under monitoring conditions, comprising the following steps: establishing a sample set; Input sample pretreatment: input samples are labeled one by one, the upper part of the human body is labeled, and the labeled samples obtained above are pretreated by using the idea of region suggestion as the data input of the whole network model; Target feature extraction; Deformable treatment: According to the characteristics that most of the indoor personnel are visible in the upper body under the condition of monitoring, The corresponding component model is designed based on the algorithm idea of deformable component, and the feature map is obtained after the feature extraction of the human body object in the image. After the deformableprocessing layer, the corresponding component feature map is obtained by convolution operation with the corresponding component filter, and the mapping score of the component is calculated. Complete classification and discrimination; Network model training.

Description

technical field [0001] The invention relates to the human body target detection task in the field of computer vision, and especially has good effect on indoor human body target detection under monitoring conditions. Background technique [0002] In today's rapidly developing society, there are more and more unstable factors in all walks of life, and people pay more and more attention to safety issues, especially in the field of security protection. For some important national security departments, if the on-duty personnel leave their posts without authorization, it is likely to cause immeasurable losses. In order to deal with this situation, most enterprises and departments adopt the method of manual inspection. With the continuous development of video surveillance technology, intelligent video surveillance emerges as the times require, and the method of manual check-in is gradually replaced by the means of video surveillance. Through the effective detection of indoor pers...

AI Technical Summary

Problems solved by technology

For indoor personnel detection tasks, most of the human targets in the video images are at a certain inclination angle to the camera, and the range of image acquisition is small, and only part of the human targets are often shown, which are not completely visible. In addition to the common front and rear perspectives, more It is a side view, and the postures are various, and there are often deformations of different degrees. It is blocked by plants, tables and chairs and other surrounding environments, and interfered by complex backgrounds. Most of the existing research methods are not suitable for this application scenario.

Images