Target detection method and system based on heterogeneous composite trunk
A target detection and backbone technology, applied in neural learning methods, neural architectures, instruments, etc., can solve problems such as domain shift and incomplete application of detection tasks, achieve simplified network structure, enhance feature expression and target detection performance, and reduce The effect of the amount of network parameters
Active Publication Date: 2021-04-23
SUN YAT SEN UNIV
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Existing target detectors generally use networks pre-trained on classification tasks to make full use of a large number of training samples with category labels, but the network structure designed for classification tasks is not fully suitable for detection tasks. domain shift
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
[0036] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. For the step numbers in the following embodiments, it is only set for the convenience of illustration and description, and the order between the steps is not limited in any way. The execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art sexual adjustment.
[0037] Such as figure 1 with figure 2 As shown, the present invention provides a kind of target detection method based on heterogeneous compound backbone, and this method comprises the following steps:
[0038] S1. Obtain training data and preprocess the training data to obtain preprocessed data;
[0039] S2. Build a target detection network based on a heterogeneous composite backbone architecture;
[0040] S3. Train the target detection network based on the pre-processed data and the preset training strategy to ...
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 target detection method and system based on a heterogeneous composite trunk, and the method comprises the steps: obtaining training data, and carrying out the preprocessing of the training data, and obtaining preprocessed data; constructing a target detection network based on the heterogeneous composite backbone architecture; training the target detection network based on the preprocessed data and a preset training strategy to obtain a trained target detection network; and acquiring to-be-detected data, inputting the to-be-detected data into the trained target detection network, and outputting a detection result. The system comprises a preprocessing module, a network construction module, a training module and a detection module. By using the method, the complementary features learned by the two heterogeneous backbone networks are integrated, and feature redundancy is avoided, so that the overall feature expression and target detection performance of the detector are enhanced. The target detection method and system based on the heterogeneous composite backbone can be widely applied to the field of target detection networks.
Description
technical field [0001] The invention belongs to the field of target detection networks, and in particular relates to a target detection method and system based on a heterogeneous composite backbone. Background technique [0002] Object detection is a fundamental and widely used task in the field of computer vision. As a basic component of many vision systems, it plays a decisive role in the overall performance of the system. With the research and application of deep learning in the field of computer vision, the performance of current object detectors has been greatly improved. [0003] In a common deep learning-based target detection network, the backbone network is mainly responsible for the extraction of target-related features, and the output feature map is the basis for the detection head to locate and recognize targets, and is crucial to the overall performance of the network. Compared with the detection head, the parameter amount of the backbone network usually accou...
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
Inventor 郑慧诚严志伟陈蔓薇李烨
Owner SUN YAT SEN UNIV