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

Proposal processing method and related products

A processing method and processor technology, applied in the fields of instruments, character and pattern recognition, computer components, etc., can solve problems such as time-consuming, achieve high real-time performance requirements, improve extraction processing efficiency, and reduce time complexity and consumption. Effect

Active Publication Date: 2021-10-01
HANGZHOU FABU TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the current technique, the method of finding all non-overlapping extractions using NMS usually consists of two steps: sort all extractions according to their scores, and start from the box with the highest score, and continuously remove boxes with lower scores and with the score Higher overlapping high boxes, which is time-consuming and not suitable for those environments with high real-time performance requirements

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
  • Proposal processing method and related products
  • Proposal processing method and related products
  • Proposal processing method and related products

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In the following description, reference is made to the accompanying drawings, which form a part hereof, and which show, by way of illustration, certain aspects of embodiments of the disclosure or in which embodiments of the disclosure may be used. . It should be understood that the embodiments of the present disclosure may be utilized in other aspects and include structural or logical changes not depicted in the figures. Accordingly, the following detailed description should not be taken in a limiting sense, and the scope of the present disclosure is defined by the appended claims.

[0041] figure 1 It is a schematic diagram illustrating the RPN in the prior art. RPN is used for extractive generation and is the focus in Faster R-CNN for object detection. Take faster R-CNN as an example, such as figure 1 As shown, to generate region extractions, a small network is slid over the convolutional feature maps output by the CNN, and the small network takes as input an n×n ...

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

Provided are a proposals processing method and related products for object detection, where the method comprising: determining a score threshold according to a statistics property of scores of all proposal; selecting proposals with a score higher than the score threshold from all the proposals; and suppressing to the selected proposals to get all non-overlapping proposals with high scores, as such, time complexity for selecting proposals is reduced, and efficiency for selection of the proposals to be used for suppression is improved, thereby improving proposal processing efficiency, and object detection efficiency.

Description

technical field [0001] The present disclosure relates to the technical field of target detection, in particular to an extraction and processing method for target detection and related products. Background technique [0002] The success of region extraction methods and region-based convolutional neural network (region-based convolutional neural network, R-CNN) has promoted the latest progress in object detection, R-CNN evolved into fast R-CNN, and further evolved into faster R-CNN . The faster R-CNN target detection system consists of two modules. One module is a deep fully convolutional network, which extracts regions by introducing a region proposal network (RPN). The second module is a fast R network that uses the extracted regions. -CNN detector. [0003] In faster R-CNN, an image is input into a convolutional neural network (CNN) to obtain a feature map of the image, and the RPN further uses the feature map to generate a series of rectangular region extractions. Regio...

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): G06K9/00
CPCG06V10/25G06V10/82G06F18/24133G06V10/94G06F18/2113
Inventor 何晓飞阿比纳什·莫汉蒂曹宇肖勇
Owner HANGZHOU FABU TECH CO LTD