Face detection method and face detection device, storage medium
A face detection and face area technology, applied in the field of face detection, can solve problems such as unfavorable rapid realization of face detection effect, complex structure of deep neural network, increased time-consuming for classification and judgment, etc. The detection process is quick and the effect of enhancing the practical effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0060] Please refer to figure 1 , the present application discloses a face detection device 1, which includes an image acquisition unit 11, a judgment unit 12, a face recognition processing unit 13, a face tracking unit 14 and an output unit 15, which will be described separately below.
[0061] The image acquisition unit 11 is used to acquire an image to be detected in an image sequence. In one embodiment, the image acquisition unit 11 acquires a frame of image from a video stream, and uses the frame of image as the image to be detected. Here, the video stream here The video can be taken by surveillance probes in public places, or by mobile phones, cameras and other electronic devices, and the captured videos include real-time captured videos and past archived videos.
[0062] The judging unit 12 is used to select a processing method for the image to be detected according to the previous face detection result in the image sequence. In one embodiment, the face recognition dev...
Embodiment 2
[0111] Please refer to Image 6 , the present application also discloses another embodiment of the face detection device 2, which includes the face detection device 1 in the first embodiment, and also includes a frame number judgment unit 16 and an ROI area calculation unit 17, which will be described separately below.
[0112] Described frame number judging unit 16 is positioned between detection judging unit 12 and human face tracking processing unit 14, is used for starting when detecting human face area in image sequence, each frame image that detects is counted, when counting result exceeds expected When the number of frames is set (the preset number of frames can be represented by the symbol T, preferably using a value in the range of 48-128), the ROI area calculation is performed on the image to be detected, otherwise, the face tracking is performed on the image to be detected Process and clear the counting results for the next round of counting.
[0113] The ROI area ...
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