Rapid target detection method based on multi-scale fusion
A multi-scale fusion and target detection technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve problems such as slow detection speed, achieve the effect of improving multi-feature representation ability and enhancing multi-scale detection ability
Pending Publication Date: 2020-10-02
SHANGHAI INST OF TECH
View PDF3 Cites 10 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The two-stage method generally has higher detection accuracy, but the detection speed is slower
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 Construction
[0047]The technical solutions in the embodiments of the present invention will be clearly and completely described and discussed below in conjunction with the accompanying drawings of the present invention. Obviously, what is described here is only a part of the examples of the present invention, not all examples. Based on the present invention All other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0048] like figure 1 As shown, this embodiment discloses a fast target detection method based on multi-scale fusion, including the following steps:
[0049] Step S1: Input the image to be detected into the Darknet53 feature extractor to extract the feature map of the image to be detected;
[0050] Step S2: input the feature map extracted by the Darknet53 feature extractor in step S1 to the multi-feature fusion module;
[0051] Described multi-feature fusion module comprises the fo...
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 rapid target detection method based on multi-scale fusion. The method comprises the following steps: S1, inputting a to-be-detected image into a Darknet53 feature extractor to extract a feature map of the to-be-detected image; s2, inputting the feature map extracted by the Darknet53 feature extractor into a multi-feature fusion module; s3, inputting the feature information obtained by the multi-feature fusion module into a multi-scale aggregation module; and S4, inputting the feature information obtained by the multi-scale aggregation module into a residual predictionmodule with a spatial attention mechanism, and outputting a target detection result. According to the multi-feature fusion module constructed by the invention, the learnable weighting parameters aredistributed to three different convolution integral branches in a self-adaptive manner, so that the multi-feature representation capability of the target detection model is improved. Four output branches of the detection network enhance the multi-scale detection capability of the network from top to bottom through the multi-scale aggregation module. And spatial attention is used in the predictionmodule, so that the network can better position the position information of the object.
Description
technical field [0001] The invention relates to the technical field of target detection in deep learning, in particular to a fast target detection method based on multi-scale fusion. Background technique [0002] In recent years, with the continuous development of deep learning, object detection technology based on deep learning has been widely used. In real-life scenarios, object detection is disturbed by many factors, such as: illumination, occlusion, etc. How to quickly and accurately detect and recognize objects in complex scenes has become a topic worthy of further study. Target detection technology is to use computer vision technology to judge whether there is an object of interest in a static image or a dynamic video, correctly identify the object category, and locate the location information of the object. Existing object detection methods generally fall into two categories: two-stage methods and one-stage methods. The two-stage method first uses the region recomm...
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): G06K9/62
CPCG06V2201/07G06F18/253
Inventor 杨振坤扶梅马向华朱丽
Owner SHANGHAI INST OF TECH