Loading…
Implement tracking algorithm using CNNs
Convolutional neural networks (CNNs) is widely used as classifiers in the field of computer vision. The more complex a CNNs model is, the more accurate classification results will be. But a very deep network also requires a better GPU to train and test in a reasonable time. In this paper, we purpose...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 7141 |
| container_issue | |
| container_start_page | 7137 |
| container_title | |
| container_volume | |
| creator | Li, Chaoran Xi, Yuling Ding, Songtao |
| description | Convolutional neural networks (CNNs) is widely used as classifiers in the field of computer vision. The more complex a CNNs model is, the more accurate classification results will be. But a very deep network also requires a better GPU to train and test in a reasonable time. In this paper, we purpose a tracking algorithm using LeNet-5, and avoid computing complex handcrafted features from the raw inputs. Modifying the number of kernels improves the tracking accuracy of models, avoid over-fitting. The experiment of processing a video clip meets real-time requirement while using GPU and it shows our algorithm is more robust than traditional algorithm like particle filter to track single target under the complicated background. |
| doi_str_mv | 10.1109/ChiCC.2016.7554485 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>proquest_CHZPO</sourceid><recordid>TN_cdi_proquest_miscellaneous_1835609444</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7554485</ieee_id><sourcerecordid>1835609444</sourcerecordid><originalsourceid>FETCH-LOGICAL-i208t-6701ea903b0d0d3500088e65dafd57d37d51849cdcf3e57a5e0e645573348ff93</originalsourceid><addsrcrecordid>eNotkMtOwzAURA0SEqX0B2CTHWwSrmNfP5Yo4lGpKhtYRya-aQ15EScL_p6idjUa6ehoNIzdcMg4B_tQ7ENRZDlwlWlEKQ2esZXVxhrDUQnL4Zwtcq54mttcX7KrGL8AFFguFuxu3Q4NtdRNyTS66jt0u8Q1u34M075N5vjfi-02XrOL2jWRVqdcso_np_fiNd28vayLx00acjBTqjRwchbEJ3jwAgHAGFLoXe1Re6E9ciNt5ataEGqHBKQkohZCmrq2Ysnuj95h7H9milPZhlhR07iO-jmW3Ag8TJdSHtDbIxqIqBzG0LrxtzxdIP4ATJVOBg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype><pqid>1835609444</pqid></control><display><type>conference_proceeding</type><title>Implement tracking algorithm using CNNs</title><source>IEEE Xplore All Conference Series</source><creator>Li, Chaoran ; Xi, Yuling ; Ding, Songtao</creator><creatorcontrib>Li, Chaoran ; Xi, Yuling ; Ding, Songtao</creatorcontrib><description>Convolutional neural networks (CNNs) is widely used as classifiers in the field of computer vision. The more complex a CNNs model is, the more accurate classification results will be. But a very deep network also requires a better GPU to train and test in a reasonable time. In this paper, we purpose a tracking algorithm using LeNet-5, and avoid computing complex handcrafted features from the raw inputs. Modifying the number of kernels improves the tracking accuracy of models, avoid over-fitting. The experiment of processing a video clip meets real-time requirement while using GPU and it shows our algorithm is more robust than traditional algorithm like particle filter to track single target under the complicated background.</description><identifier>EISSN: 2161-2927</identifier><identifier>EISSN: 1934-1768</identifier><identifier>EISBN: 9789881563910</identifier><identifier>EISBN: 9881563917</identifier><identifier>DOI: 10.1109/ChiCC.2016.7554485</identifier><language>eng</language><publisher>TCCT</publisher><subject>Algorithm design and analysis ; Algorithms ; Classification ; Computational modeling ; Computer vision ; Conferences ; Convolutional Neural Networks ; Feature extraction ; Graphics processing units ; Kernels ; Neural networks ; Object Tracking ; Target tracking ; Tracking ; Visualization</subject><ispartof>2016 35th Chinese Control Conference (CCC), 2016, p.7137-7141</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/7554485$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,314,776,780,785,786,27901,27902,54530,54907</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/7554485$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Li, Chaoran</creatorcontrib><creatorcontrib>Xi, Yuling</creatorcontrib><creatorcontrib>Ding, Songtao</creatorcontrib><title>Implement tracking algorithm using CNNs</title><title>2016 35th Chinese Control Conference (CCC)</title><addtitle>ChiCC</addtitle><description>Convolutional neural networks (CNNs) is widely used as classifiers in the field of computer vision. The more complex a CNNs model is, the more accurate classification results will be. But a very deep network also requires a better GPU to train and test in a reasonable time. In this paper, we purpose a tracking algorithm using LeNet-5, and avoid computing complex handcrafted features from the raw inputs. Modifying the number of kernels improves the tracking accuracy of models, avoid over-fitting. The experiment of processing a video clip meets real-time requirement while using GPU and it shows our algorithm is more robust than traditional algorithm like particle filter to track single target under the complicated background.</description><subject>Algorithm design and analysis</subject><subject>Algorithms</subject><subject>Classification</subject><subject>Computational modeling</subject><subject>Computer vision</subject><subject>Conferences</subject><subject>Convolutional Neural Networks</subject><subject>Feature extraction</subject><subject>Graphics processing units</subject><subject>Kernels</subject><subject>Neural networks</subject><subject>Object Tracking</subject><subject>Target tracking</subject><subject>Tracking</subject><subject>Visualization</subject><issn>2161-2927</issn><issn>1934-1768</issn><isbn>9789881563910</isbn><isbn>9881563917</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2016</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotkMtOwzAURA0SEqX0B2CTHWwSrmNfP5Yo4lGpKhtYRya-aQ15EScL_p6idjUa6ehoNIzdcMg4B_tQ7ENRZDlwlWlEKQ2esZXVxhrDUQnL4Zwtcq54mttcX7KrGL8AFFguFuxu3Q4NtdRNyTS66jt0u8Q1u34M075N5vjfi-02XrOL2jWRVqdcso_np_fiNd28vayLx00acjBTqjRwchbEJ3jwAgHAGFLoXe1Re6E9ciNt5ataEGqHBKQkohZCmrq2Ysnuj95h7H9milPZhlhR07iO-jmW3Ag8TJdSHtDbIxqIqBzG0LrxtzxdIP4ATJVOBg</recordid><startdate>20160701</startdate><enddate>20160701</enddate><creator>Li, Chaoran</creator><creator>Xi, Yuling</creator><creator>Ding, Songtao</creator><general>TCCT</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope></search><sort><creationdate>20160701</creationdate><title>Implement tracking algorithm using CNNs</title><author>Li, Chaoran ; Xi, Yuling ; Ding, Songtao</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i208t-6701ea903b0d0d3500088e65dafd57d37d51849cdcf3e57a5e0e645573348ff93</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Algorithm design and analysis</topic><topic>Algorithms</topic><topic>Classification</topic><topic>Computational modeling</topic><topic>Computer vision</topic><topic>Conferences</topic><topic>Convolutional Neural Networks</topic><topic>Feature extraction</topic><topic>Graphics processing units</topic><topic>Kernels</topic><topic>Neural networks</topic><topic>Object Tracking</topic><topic>Target tracking</topic><topic>Tracking</topic><topic>Visualization</topic><toplevel>online_resources</toplevel><creatorcontrib>Li, Chaoran</creatorcontrib><creatorcontrib>Xi, Yuling</creatorcontrib><creatorcontrib>Ding, Songtao</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Li, Chaoran</au><au>Xi, Yuling</au><au>Ding, Songtao</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Implement tracking algorithm using CNNs</atitle><btitle>2016 35th Chinese Control Conference (CCC)</btitle><stitle>ChiCC</stitle><date>2016-07-01</date><risdate>2016</risdate><spage>7137</spage><epage>7141</epage><pages>7137-7141</pages><eissn>2161-2927</eissn><eissn>1934-1768</eissn><eisbn>9789881563910</eisbn><eisbn>9881563917</eisbn><abstract>Convolutional neural networks (CNNs) is widely used as classifiers in the field of computer vision. The more complex a CNNs model is, the more accurate classification results will be. But a very deep network also requires a better GPU to train and test in a reasonable time. In this paper, we purpose a tracking algorithm using LeNet-5, and avoid computing complex handcrafted features from the raw inputs. Modifying the number of kernels improves the tracking accuracy of models, avoid over-fitting. The experiment of processing a video clip meets real-time requirement while using GPU and it shows our algorithm is more robust than traditional algorithm like particle filter to track single target under the complicated background.</abstract><pub>TCCT</pub><doi>10.1109/ChiCC.2016.7554485</doi><tpages>5</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | EISSN: 2161-2927 |
| ispartof | 2016 35th Chinese Control Conference (CCC), 2016, p.7137-7141 |
| issn | 2161-2927 1934-1768 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_1835609444 |
| source | IEEE Xplore All Conference Series |
| subjects | Algorithm design and analysis Algorithms Classification Computational modeling Computer vision Conferences Convolutional Neural Networks Feature extraction Graphics processing units Kernels Neural networks Object Tracking Target tracking Tracking Visualization |
| title | Implement tracking algorithm using CNNs |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T10%3A48%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Implement%20tracking%20algorithm%20using%20CNNs&rft.btitle=2016%2035th%20Chinese%20Control%20Conference%20(CCC)&rft.au=Li,%20Chaoran&rft.date=2016-07-01&rft.spage=7137&rft.epage=7141&rft.pages=7137-7141&rft.eissn=2161-2927&rft_id=info:doi/10.1109/ChiCC.2016.7554485&rft.eisbn=9789881563910&rft.eisbn_list=9881563917&rft_dat=%3Cproquest_CHZPO%3E1835609444%3C/proquest_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i208t-6701ea903b0d0d3500088e65dafd57d37d51849cdcf3e57a5e0e645573348ff93%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1835609444&rft_id=info:pmid/&rft_ieee_id=7554485&rfr_iscdi=true |