Unlock instant, AI-driven research and patent intelligence for your innovation.

Target detection neural network training method and device

A neural network training and target detection technology, applied in the field of target detection neural network training, can solve the problems of heavy workload and poor neural network accuracy, and achieve the effect of improving accuracy

Pending Publication Date: 2020-06-30
HANGZHOU HIKVISION DIGITAL TECH
View PDF11 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, if fewer video frames are calibrated, the accuracy of the trained object detection neural network may be poor, and if more video frames are calibrated, the workload of calibration will be larger

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
  • Target detection neural network training method and device
  • Target detection neural network training method and device
  • Target detection neural network training method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0051] see figure 1 , figure 1 Shown is a schematic flow chart of the target detection neural network training method provided by the embodiment of the present application. The trained target detection neural network includes a feature extraction sub-network and a detection sub-network, which may include:

[0052] S101. Use the feature extraction sub-network to process the reference video frame in the sample video, so as to calculate the image features of the key video frame based ...

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

No PUM Login to View More

Abstract

The embodiment of the invention provides a target detection neural network training method and device. The method comprises the following steps: and processing a reference video frame in the sample video by using a feature extraction sub-network, calculating image features of a key video frame based on a transformation relationship between the reference video frame and the key video frame to obtain estimated image features, with the reference video frame being an uncalibrated video frame in the sample video, and the sample video being a calibrated video frame in the sample video; processing the estimated image features by using the detection sub-network to obtain a prediction result; and calculating loss based on an error between the prediction result and a calibration result of the key video frame, and adjusting network parameters of the target detection neural network. The accuracy of the trained target detection neural network can be improved under the condition that the workload caused by calibration is not increased.

Description

technical field [0001] The present application relates to the technical field of computer vision, in particular to a method and device for training a target detection neural network. Background technique [0002] The target detection neural network can include a feature extraction subnetwork and a detection subnetwork. The feature extraction subnetwork can extract the image features of the video frame, and the detection subnetwork can determine the area where the target object exists in the video frame based on the image features to obtain the detection result. In order to enable the target detection neural network to accurately identify the area where the target object is located in the video frame, that is, to improve the accuracy of the detection result of the target detection neural network, it is necessary to train the target detection neural network in advance. [0003] In the prior art, the area where the target object is located in multiple video frames of the sample...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/08G06K9/62
CPCG06N3/08G06F18/21Y02T10/40
Inventor 石大虎虞抒沁谭文明
Owner HANGZHOU HIKVISION DIGITAL TECH