Prisoner-oriented active transformation behavior evaluation method

Abstract

The invention relates to a prisoner-oriented active reconstruction behavior evaluation method, which is realized by using computer vision and image processing technologies, and is implemented by detecting and analyzing whether a face image of a prisoner in an acquired video appears in a detection area (face detection), a head deflection condition, an eye closing condition and a sight deviation condition. After comprehensive consideration, the distraction value of the prisoner in the video is calculated, and 80% of the distraction value is set as a distraction threshold value, so that whether the detector focuses on attention or not is effectively judged, and whether the prisoner actively cooperates with transformation or not is evaluated on the basis of the distraction value. The video data of the prisoners in the interrogation process are collected in a non-contact mode through the computer vision technology, the attention state of the prisoners is analyzed through the image processing technology, whether the prisoners actively cooperate with transformation or not is evaluated, and therefore the purposes of being free of interference and easy to implement are achieved.

Description

technical field [0001] The invention belongs to the field of computer vision and pattern recognition, and in particular relates to an evaluation method for the active reformation behavior of inmates. Background technique [0002] As an important part of the state apparatus, prisons are responsible for the important mission of detaining and reforming criminals, with the ultimate goal of transforming prisoners into qualified law-abiding citizens. This is of great significance for maintaining the long-term stability of the country and building a safe China. As an important link in the implementation of the overall national security concept, the education and reform of prisoners still faces many challenges and difficulties. It is manifested in problems such as inaccurate reform evaluation system, imperfect reform strategy system, and imperfect re-offending risk early warning and prediction system. Among them, the reform performance of prisoners during their sentence is the ext...

AI Technical Summary

Problems solved by technology

[0004] To sum up, these methods are more or less subjective, especially for the special group of prisoners, which are highly concealed and highly vigilant. It is difficult to make an objective and accurate judgment on the reform situation with the above methods

With the development of human-computer interaction technology, the assessment of the transformation of inmates will use brain waves, heart rate and other physiological characteristics of inmates. However, although these methods are more objective than traditional questionnaires, they mostly use Kinect sensors and infrared cameras. And other equipment, more importantly, sensors need to be placed on the detector. If it is used in a supervision place, this will seriously interfere with the inmates, making them vigilant or alert, and it is difficult to guarantee the accuracy of the results.

Images