Multi-target small object identification method based on category loss and difference detection
The invention discloses a multi-target small object recognition method based on category loss and difference detection, which comprises the following steps of: acquiring a chessboard initial image, calibrating a chessboard image coordinate, and segmenting the chessboard image according to the coordi...
Gespeichert in:
Hauptverfasser: | , , , , , , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | ZHANG PEIBIAO XIA GUANGSHENG ZHANG YUE LING XU SHI MENGCHEN XIE FEI ZHENG PENGFEI LI QUNZHAO WU JIAHAO WANG FANG |
description | The invention discloses a multi-target small object recognition method based on category loss and difference detection, which comprises the following steps of: acquiring a chessboard initial image, calibrating a chessboard image coordinate, and segmenting the chessboard image according to the coordinate; preprocessing the segmented chessboard image, classifying the processed image by using the built deep learning network model, and converting a classification result into chess information; a chessboard image P1 is collected, and a chessboard image P2 is collected again after a chess player performs walking chess; according to the chessboard image P1 and the chessboard image P2, a difference value detection method is adopted for conducting reasonability judgment on the starting point and the ending point of chess moving, and chess information is updated. The method realizes detection and identification of Chinese chess from opening to each walking chess, has the advantages of high speed, high robustness and th |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN114429584A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN114429584A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN114429584A3</originalsourceid><addsrcrecordid>eNqNjDEOwjAQBNNQIOAPxwNSBIIEJYpANFDRWxd7nRg5dmQfBb_HBQ-gWu1oZ5eVur-9uFo4DRDKE3tPsX9BCzmDIM46zeJioAkyRkM9ZxgqvWAMMX3Ix5yJgyHjrEVC0CADKRdFW1cLyz5j88tVtb1ent2txhwV8swaAaK6R9O07e50OLbn_T-bL6d8PUQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Multi-target small object identification method based on category loss and difference detection</title><source>esp@cenet</source><creator>ZHANG PEIBIAO ; XIA GUANGSHENG ; ZHANG YUE ; LING XU ; SHI MENGCHEN ; XIE FEI ; ZHENG PENGFEI ; LI QUNZHAO ; WU JIAHAO ; WANG FANG</creator><creatorcontrib>ZHANG PEIBIAO ; XIA GUANGSHENG ; ZHANG YUE ; LING XU ; SHI MENGCHEN ; XIE FEI ; ZHENG PENGFEI ; LI QUNZHAO ; WU JIAHAO ; WANG FANG</creatorcontrib><description>The invention discloses a multi-target small object recognition method based on category loss and difference detection, which comprises the following steps of: acquiring a chessboard initial image, calibrating a chessboard image coordinate, and segmenting the chessboard image according to the coordinate; preprocessing the segmented chessboard image, classifying the processed image by using the built deep learning network model, and converting a classification result into chess information; a chessboard image P1 is collected, and a chessboard image P2 is collected again after a chess player performs walking chess; according to the chessboard image P1 and the chessboard image P2, a difference value detection method is adopted for conducting reasonability judgment on the starting point and the ending point of chess moving, and chess information is updated. The method realizes detection and identification of Chinese chess from opening to each walking chess, has the advantages of high speed, high robustness and th</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2022</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220503&DB=EPODOC&CC=CN&NR=114429584A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220503&DB=EPODOC&CC=CN&NR=114429584A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHANG PEIBIAO</creatorcontrib><creatorcontrib>XIA GUANGSHENG</creatorcontrib><creatorcontrib>ZHANG YUE</creatorcontrib><creatorcontrib>LING XU</creatorcontrib><creatorcontrib>SHI MENGCHEN</creatorcontrib><creatorcontrib>XIE FEI</creatorcontrib><creatorcontrib>ZHENG PENGFEI</creatorcontrib><creatorcontrib>LI QUNZHAO</creatorcontrib><creatorcontrib>WU JIAHAO</creatorcontrib><creatorcontrib>WANG FANG</creatorcontrib><title>Multi-target small object identification method based on category loss and difference detection</title><description>The invention discloses a multi-target small object recognition method based on category loss and difference detection, which comprises the following steps of: acquiring a chessboard initial image, calibrating a chessboard image coordinate, and segmenting the chessboard image according to the coordinate; preprocessing the segmented chessboard image, classifying the processed image by using the built deep learning network model, and converting a classification result into chess information; a chessboard image P1 is collected, and a chessboard image P2 is collected again after a chess player performs walking chess; according to the chessboard image P1 and the chessboard image P2, a difference value detection method is adopted for conducting reasonability judgment on the starting point and the ending point of chess moving, and chess information is updated. The method realizes detection and identification of Chinese chess from opening to each walking chess, has the advantages of high speed, high robustness and th</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjDEOwjAQBNNQIOAPxwNSBIIEJYpANFDRWxd7nRg5dmQfBb_HBQ-gWu1oZ5eVur-9uFo4DRDKE3tPsX9BCzmDIM46zeJioAkyRkM9ZxgqvWAMMX3Ix5yJgyHjrEVC0CADKRdFW1cLyz5j88tVtb1ent2txhwV8swaAaK6R9O07e50OLbn_T-bL6d8PUQ</recordid><startdate>20220503</startdate><enddate>20220503</enddate><creator>ZHANG PEIBIAO</creator><creator>XIA GUANGSHENG</creator><creator>ZHANG YUE</creator><creator>LING XU</creator><creator>SHI MENGCHEN</creator><creator>XIE FEI</creator><creator>ZHENG PENGFEI</creator><creator>LI QUNZHAO</creator><creator>WU JIAHAO</creator><creator>WANG FANG</creator><scope>EVB</scope></search><sort><creationdate>20220503</creationdate><title>Multi-target small object identification method based on category loss and difference detection</title><author>ZHANG PEIBIAO ; XIA GUANGSHENG ; ZHANG YUE ; LING XU ; SHI MENGCHEN ; XIE FEI ; ZHENG PENGFEI ; LI QUNZHAO ; WU JIAHAO ; WANG FANG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN114429584A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>ZHANG PEIBIAO</creatorcontrib><creatorcontrib>XIA GUANGSHENG</creatorcontrib><creatorcontrib>ZHANG YUE</creatorcontrib><creatorcontrib>LING XU</creatorcontrib><creatorcontrib>SHI MENGCHEN</creatorcontrib><creatorcontrib>XIE FEI</creatorcontrib><creatorcontrib>ZHENG PENGFEI</creatorcontrib><creatorcontrib>LI QUNZHAO</creatorcontrib><creatorcontrib>WU JIAHAO</creatorcontrib><creatorcontrib>WANG FANG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHANG PEIBIAO</au><au>XIA GUANGSHENG</au><au>ZHANG YUE</au><au>LING XU</au><au>SHI MENGCHEN</au><au>XIE FEI</au><au>ZHENG PENGFEI</au><au>LI QUNZHAO</au><au>WU JIAHAO</au><au>WANG FANG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Multi-target small object identification method based on category loss and difference detection</title><date>2022-05-03</date><risdate>2022</risdate><abstract>The invention discloses a multi-target small object recognition method based on category loss and difference detection, which comprises the following steps of: acquiring a chessboard initial image, calibrating a chessboard image coordinate, and segmenting the chessboard image according to the coordinate; preprocessing the segmented chessboard image, classifying the processed image by using the built deep learning network model, and converting a classification result into chess information; a chessboard image P1 is collected, and a chessboard image P2 is collected again after a chess player performs walking chess; according to the chessboard image P1 and the chessboard image P2, a difference value detection method is adopted for conducting reasonability judgment on the starting point and the ending point of chess moving, and chess information is updated. The method realizes detection and identification of Chinese chess from opening to each walking chess, has the advantages of high speed, high robustness and th</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | chi ; eng |
recordid | cdi_epo_espacenet_CN114429584A |
source | esp@cenet |
subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
title | Multi-target small object identification method based on category loss and difference detection |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T18%3A04%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=ZHANG%20PEIBIAO&rft.date=2022-05-03&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN114429584A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |