Data set selection method for robot target detection algorithm
A target detection algorithm and target detection technology are applied in the field of data set selection for robot target detection algorithms to reduce the similarity value and improve robust performance and generalization performance.
Active Publication Date: 2021-04-30
SHANGHAI ROBOT IND TECH RES INST CO LTD
View PDF12 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003]
The existing robot target detection algorithm model data set recommendation research generally adopts the method based on human experience, and this kind of subjective selection often requires a lot of model tuning process
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
[0027] Below in conjunction with specific embodiment, further illustrate the present invention. It should be understood that these examples are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the content taught by the present invention, those skilled in the art may make various changes or modifications to the present invention, and these equivalent forms also fall within the scope defined by the appended claims of the present application.
[0028] Such as figure 1 As shown, a kind of data set selection method oriented to robot target recognition algorithm provided by the present invention comprises the following steps:
[0029] Step 1: Perform row vector encoding on the metadata features of each type of existing data set.
[0030] Metadata features include application scenarios, target detection object category, target detection object size, light and darkn...
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
Aiming at the problem of how to select a data set for a robot target detection algorithm model in various application scenes, the invention provides a data set selection method for a robot target detection algorithm. According to the invention, a data set can be automatically selected for model training and testing according to different requirements of the algorithm model by using a machine learning method, an artificial experience method can be effectively replaced, and meanwhile, the robustness and generalization performance of the algorithm model are improved. In addition, the method provided by the invention extracts data set metadata features influencing the model detection effect according to the test conclusion, and recodes the row vector, so that the similarity value of next matching can be effectively reduced. Through continuous iterative update learning, the row vector coding of the data set in the step 1 is improved, a more appropriate data set can be provided for the next new robot target recognition algorithm model, and the robustness and generalization performance of the algorithm model are improved.
Description
technical field [0001] The invention relates to the field of machine learning, in particular to a data set selection method for robot target detection algorithms. Background technique [0002] With the rapid development of artificial intelligence deep learning, object detection technology based on computer vision has been applied to various scenarios. Especially in the field of robotics, the target detection technology used in industrial robots, service robots, drones, security monitoring and other scenarios has become increasingly mature. Different application scenarios usually select corresponding data sets for model training and testing. In order to be able to select the appropriate data set for the algorithm model developers so that the algorithm model can achieve the optimal performance, it has become a research hotspot for the algorithm model developers in recent years. [0003] The existing research on robot target detection algorithm model data set recommendation g...
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): G06F17/10G06N20/00
CPCG06F17/10G06N20/00
Inventor 沈文婷陆林东郑军奇
Owner SHANGHAI ROBOT IND TECH RES INST CO LTD