Prisoner-oriented active transformation behavior evaluation method
An active technology for inmates, applied in the field of computer vision and pattern recognition, can solve the problems of high vigilance, interference by inmates, difficulty in ensuring the accuracy of results, etc., and achieve the effect of simple implementation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0092] An evaluation method for the active reformation behavior of inmates, such as figure 1 shown, including the following steps:
[0093] A. Collect human face video images every fixed time T, and perform grayscale conversion and video frame division to obtain each frame of human face images, and perform steps B-E sequentially for each frame of human face images; for each frame After performing steps B-E in sequence on the face image, enter step F;
[0094] B. Face detection: search the current frame face image to determine whether there is a face, if so, return the position of the face in the current frame face image, the length and width of the face, and enter step C. Otherwise, mark the frame of face image as no one frame;
[0095] C. Head deflection detection: Find the attitude angle of the head of the current frame face image. The attitude angle of the head includes the three Euler angles of the pitch angle pitch, the yaw angle yaw and the roll angle roll, which refe...
Embodiment 2
[0101] According to a method for assessing the active reformation behavior of inmates described in Example 1, the difference lies in:
[0102] Step A, collecting video images, including:
[0103] a. Collect face video images through the camera;
[0104] B, utilize OpenCV visual storehouse to carry out gray-scale conversion to the face video image that step a collects;
[0105] c. Carry out video framing on the human face video image processed in step b. Framing is to process the video to obtain a sequence of video frames.
[0106] The face image acquisition device used in the present invention is a notebook camera with a resolution of about 300,000 pixels. The original image data captured by the camera is preprocessed by using the computer vision library OpenCV to complete grayscale conversion.
[0107] Step B, carry out face detection to the face video image processed in step A, including:
[0108] Use the Dlib vision library for face detection: search for each image obt...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com