Method for realizing tiny target detection on chip integrating distillation strategy and deconvolution

A technology of target detection and implementation method, which is applied in neural learning methods, image data processing, instruments, etc., can solve the problems of large storage capacity and long computing time, and achieve the effect of less memory, small on-chip area, and elimination of false detection

Pending Publication Date: 2020-05-19
淄博凝眸智能科技有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This architecture detects multiple target objects at the same time (multitasking), which is beneficial to improve the detection of tiny target objects, but requires larger storage capacity and longer computing time in the hardware implementation 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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for realizing tiny target detection on chip integrating distillation strategy and deconvolution
  • Method for realizing tiny target detection on chip integrating distillation strategy and deconvolution
  • Method for realizing tiny target detection on chip integrating distillation strategy and deconvolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] Such as figure 1 As shown, it is an integrated distillation strategy and deconvolution micro-target detection architecture involved in this embodiment, including: a learning network StudentNet containing a deconvolution layer for low-resolution images and a learning network for high-resolution images. The teaching network TeacherNet uses several intermediate feature maps of the teaching network to train the multi-layers in the learning network by adversarial loss learning, and improves the output accuracy of the learning network while expanding the receptive field of low-pixel images.

[0014] The learning network includes: a convolution layer 400 connected in sequence, a normalization layer 402 with an S-type rectification nonlinear activation unit, a convolution layer 404, a deconvolution layer 406, and a S-type rectification nonlinear activation unit. Unit's normalization layer 408, convolutional layer 410, normalization layer 412 with S-type rectified non-linear act...

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

A method for realizing tiny target detection on a chip integrating a distillation strategy and deconvolution trains a plurality of layers in a learning network for a low-resolution image and containing a deconvolution layer in a loss-resistant learning mode by a plurality of intermediate feature maps of a teaching network for a high-resolution image, so that the output precision of the learning network is improved and the size of the chip is reduced while the receptive field of a low-pixel image is enlarged. The method simply designs the target detection task as a classification task through the learning network, and only needs to determine whether the target exists in an area of 20*20 pixels, so that the on-chip area is small when the hardware is realized, the required memory is small, and meanwhile, the false detection of the tiny objects can be effectively eliminated.

Description

technical field [0001] The present invention relates to a technology in the field of image detection, in particular to an on-chip implementation method of tiny target detection integrating a distillation strategy and deconvolution. Background technique [0002] Although there are currently several methods for object detection using convolutional neural networks, most popular algorithms perform well when objects occupy a large portion of an image (usually their size is greater than 20 square pixels). Recently, many algorithms have emerged to detect tiny objects with low resolution (less than 20 square pixels). These methods usually rely on multi-scale resolution and detect objects of different sizes at corresponding resolutions. This architecture detects multiple target objects at the same time (multitasking), which is beneficial to improve the detection of tiny target objects, but requires larger storage capacity and longer computing time in the hardware implementation proc...

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
IPC IPC(8): G06T7/00G06N3/04G06N3/08
CPCG06T7/0002G06N3/08G06N3/045Y02D10/00
Inventor 熊伟华吴华
Owner 淄博凝眸智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap