Unlock instant, AI-driven research and patent intelligence for your innovation.
A method and system for pedestrian detection and identification based on rgbd
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
An identity recognition and pedestrian detection technology, applied in the field of image processing, can solve the problems of limited application scenarios, easy confusion, and inability to use valid facial information, and achieve the effect of wide application scenarios, high robustness and accuracy
Active Publication Date: 2020-06-09
杭州艾芯智能科技有限公司
View PDF0 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0003] The first method has poor anti-interference ability and low robustness in rainy, snowy, windy, shaking leaves, flickering lights, etc.
The second method has the following problems: due to the different postures and clothing of pedestrians, the performance of the classifier is greatly affected by the training samples, and the application scenarios covered are limited
However, this method can only use the appearance features of pedestrians for identification, but cannot use effective information of the face; in addition, due to changes in scale, illumination and angle, the appearance features of the same pedestrian will change to a certain extent in different pictures , the appearance characteristics of different pedestrians may be more similar than the appearance characteristics of the same person, thus affecting the accuracy of the recognition process and easily confusing
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0046] figure 1 A schematicflowchart of the RGBD-based pedestrian detection and identification method provided by Embodiment 1 of the present invention is shown. Such as figure 1 As shown, the method includes:
[0047] Step S1, input an RGBD image, and preprocess the RGBD image;
[0048] Step S2, constructing the multi-channel feature and scale list of the RGBD image;
[0049] Step S3, according to the multi-channel feature and the scale list, train a detection classifier;
[0050] Step S4, using the detection classifier to detect and identify pedestrians.
[0051] The concrete technical scheme of the example one of the present invention is:
[0052] Step S1, input an RGBD image, and perform preprocessing on the RGBD image.
[0053] The RGBD images include two categories: color images and depth images, where the color images are also called RGB images or color images. For RGB images, in the preprocessing step, use appropriate filtering to remove its noise according to ...
Embodiment 2
[0099] Corresponding to the embodiments of the present invention, figure 2 A schematic structural diagram of an RGBD-based pedestrian detection and identification system provided by an embodiment of the present invention is shown. Such as figure 2 As shown, the system includes: an input module 101 , a feature construction module 102 , a training module 103 , and a detection and recognition module 104 . Wherein, the input module 101 is connected with the feature construction module 102 , the feature construction module 102 is connected with the training module 103 , and the training module 103 is connected with the detection and identification module 104 .
[0100] The input module 101 is configured to input an RGBD image and perform preprocessing on the RGBD image. Specifically used for: For RGB images, use appropriate filtering to remove noise according to the actual situation; for depth images, set the pixel value of the area without depth value to 0, regard 0 as missing...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
PUM
Login to View More
Abstract
The invention discloses a pedestrian detection and identification method and system based on RGBD, the method includes: inputting an RGBD image, and preprocessing the RGBD image; constructing a multi-channel feature and scale list of the RGBD image; according to The multi-channel features are trained to obtain a detection classifier; the detection classifier is used to detect and identify pedestrians according to the scale list. The invention is based on the fusion of RGBD multi-channel features, so that the detection of pedestrians and the identification of identities have higher robustness and accuracy and wider application scenarios.
Description
technical field [0001] The invention relates to the technical field of image processing, in particular to a pedestrian detection and identity recognition method and system. Background technique [0002] Pedestrian detection refers to the detection of the specific location of pedestrians contained in video or static images through algorithms such as image processing and pattern recognition. As an important direction of target detection, pedestrian detection technology has broad application prospects in home service robots, intelligent monitoring, intelligent transportation, and assisted driving. Compared with ordinary object detection, the characteristics of pedestrians such as non-rigid body and diversity greatly increase the difficulty of effectively detecting pedestrians. At present, pedestrian detection can be divided into two categories: 1) methods based on background modeling: segment the foreground, extract moving objects, and then further extract features, classify a...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More