Fuzzy target detection method of improved Fast-RCNN model
A technology of fuzzy targets and detection methods, applied in the field of intelligent recognition, can solve problems such as automatic driving safety accidents, and achieve the effect of improving accuracy
Pending Publication Date: 2020-11-24
REDNOVA INNOVATIONS INC
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In the case of blurred targets, existing target detection algorithms cannot detect accurately, which may lead to safety accidents in autonomous driving
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0044] Such as figure 1 Shown, the present invention is a kind of fuzzy target detection method of improving Faster-RCNN model, and this method specifically comprises the following steps:
[0045] Step 1: Obtain a data set for generating a repair network, and preprocess the data set, and divide the data set into a training set and a test set;
[0046] Step 2: Build a GAN model;
[0047] Step 3: Use the training set in step 1 to conduct confrontational training on the GAN model;
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 fuzzy target detection method based on an improved Faster-RCNN model, relating to the field of intelligent identification. Through constructing GAN model, the GAN model is trained to generate a repair network; the restoration network is introduced into the Faster-RCNN model, the Faster-RCNN model is improved, the blurred picture to be detected firstly enters the restoration network of the improved Faster-RCNN model, and then target detection is carried out, so that the accuracy of blurred target detection is greatly improved.
Description
technical field [0001] The invention relates to the field of intelligent recognition, in particular to an improved Faster-RCNN model fuzzy target detection method. Background technique [0002] Target detection is to find all the objects of interest in the image, including two sub-tasks of object positioning and object classification, and at the same time determine the category and location of the object. Object detection is a popular research direction of computer vision, which is widely used in many fields such as automatic driving, intelligent industrial detection, and intelligent monitoring. By using computer vision, it can automatically process pictures and reduce human labor, which has strong practical significance. [0003] Therefore, target detection algorithms have become a research hotspot in recent years. Recently, there are two types of popular target detection algorithms. One is the One-Stage target detection algorithm, mainly including YOLO algorithm and SSD 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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V2201/07G06N3/045G06F18/214G06F18/2431
Inventor 王堃王铭宇吴晨
Owner REDNOVA INNOVATIONS INC