{"id":"https://openalex.org/W2740088230","doi":"https://doi.org/10.1109/asap.2017.7995262","title":"Real-time object detection in software with custom vector instructions and algorithm changes","display_name":"Real-time object detection in software with custom vector instructions and algorithm changes","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2740088230","doi":"https://doi.org/10.1109/asap.2017.7995262","mag":"2740088230"},"language":"en","primary_location":{"id":"doi:10.1109/asap.2017.7995262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2017.7995262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 28th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111480656","display_name":"J.R. Edwards","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Joe Edwards","raw_affiliation_strings":["University of British Columbia VectorBlox Computing Inc"],"affiliations":[{"raw_affiliation_string":"University of British Columbia VectorBlox Computing Inc","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071113717","display_name":"Guy Lemieux","orcid":"https://orcid.org/0000-0002-7924-8695"},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Guy G.F. Lemieux","raw_affiliation_strings":["University of British Columbia VectorBlox Computing Inc"],"affiliations":[{"raw_affiliation_string":"University of British Columbia VectorBlox Computing Inc","institution_ids":["https://openalex.org/I4210127509"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111480656"],"corresponding_institution_ids":["https://openalex.org/I4210127509"],"apc_list":null,"apc_paid":null,"fwci":0.182,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56164251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"75","last_page":"82"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9799000024795532,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9779999852180481,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8354254364967346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7962204217910767},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6979785561561584},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5228641033172607},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5178130269050598},{"id":"https://openalex.org/keywords/vhdl","display_name":"VHDL","score":0.49846959114074707},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4755777418613434},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4553048014640808},{"id":"https://openalex.org/keywords/arm-architecture","display_name":"ARM architecture","score":0.45056289434432983},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4373806118965149},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34049826860427856},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.33742886781692505},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11958032846450806}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8354254364967346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7962204217910767},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6979785561561584},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5228641033172607},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5178130269050598},{"id":"https://openalex.org/C36941000","wikidata":"https://www.wikidata.org/wiki/Q209455","display_name":"VHDL","level":3,"score":0.49846959114074707},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4755777418613434},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4553048014640808},{"id":"https://openalex.org/C26771161","wikidata":"https://www.wikidata.org/wiki/Q16980","display_name":"ARM architecture","level":2,"score":0.45056289434432983},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4373806118965149},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34049826860427856},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.33742886781692505},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11958032846450806}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asap.2017.7995262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2017.7995262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 28th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1480909796","https://openalex.org/W1973012690","https://openalex.org/W2023203414","https://openalex.org/W2037748535","https://openalex.org/W2067555400","https://openalex.org/W2113522228","https://openalex.org/W2119706443","https://openalex.org/W2142704643","https://openalex.org/W2152404412","https://openalex.org/W2164598857","https://openalex.org/W3210232381","https://openalex.org/W4241765343","https://openalex.org/W6678044696","https://openalex.org/W6803376173"],"related_works":["https://openalex.org/W3004362061","https://openalex.org/W4297665406","https://openalex.org/W2364622490","https://openalex.org/W2042515040","https://openalex.org/W2383986884","https://openalex.org/W2356141508","https://openalex.org/W2749962643","https://openalex.org/W2390807153","https://openalex.org/W2532502681","https://openalex.org/W2389916899"],"abstract_inverted_index":{"Real-time":[0],"vision":[1],"applications":[2],"place":[3],"stringent":[4],"performance":[5,12,171],"requirements":[6],"on":[7,68,76],"embedded":[8,14],"systems.":[9],"To":[10],"meet":[11],"requirements,":[13],"systems":[15],"often":[16,47],"require":[17,34,138],"hardware":[18,25,184],"implementations.":[19],"This":[20,37,166],"approach":[21,167],"is":[22,65,95,160],"unfavorable":[23],"as":[24],"development":[26],"can":[27,172,185],"be":[28,173],"difficult":[29],"to":[30,102,152,162],"debug,":[31],"time-consuming,":[32],"and":[33,148,178],"extensive":[35],"skill.":[36],"paper":[38],"presents":[39],"a":[40,50,56,61,69,77,83,104,179,187],"case":[41],"study":[42],"of":[43,49,143,182],"accelerating":[44],"face":[45,155],"detection,":[46],"part":[48],"complex":[51],"image":[52],"processing":[53],"pipeline,":[54],"using":[55,82,97],"software/hardware":[57],"hybrid":[58],"approach.":[59],"As":[60],"baseline,":[62],"the":[63,90,93,110,130,135],"algorithm":[64,94],"initially":[66],"run":[67],"scalar":[70],"ARM":[71],"Cortex-A9":[72,132],"application":[73],"processor":[74],"found":[75],"Xilinx":[78],"Zynq":[79],"device.":[80],"Next,":[81],"previously":[84],"designed":[85],"vector":[86,100,119],"engine":[87],"implemented":[88],"in":[89],"FPGA":[91],"fabric,":[92],"vectorized,":[96],"only":[98],"standard":[99],"instructions,":[101],"achieve":[103],"25\u00d7":[105],"speedup.":[106],"Then,":[107],"we":[108],"accelerate":[109],"critical":[111],"inner":[112],"loops":[113],"by":[114],"adding":[115],"two":[116],"hardware-assisted":[117],"custom":[118,136,183],"instructions":[120,137],"for":[121],"an":[122],"additional":[123],"10\u00d7":[124],"speedup,":[125],"yielding":[126],"248\u00d7":[127],"speedup":[128],"over":[129],"initial":[131],"baseline.":[133],"Collectively,":[134],"fewer":[139],"than":[140],"800":[141],"lines":[142],"VHDL":[144],"code,":[145],"including":[146],"comments":[147],"blank":[149],"lines.":[150],"Compared":[151],"previous":[153],"hardware-only":[154],"detection":[156],"systems,":[157],"our":[158],"work":[159],"1.5":[161],"6.8":[163],"times":[164],"faster.":[165],"demonstrates":[168],"that":[169],"good":[170],"obtained":[174],"from":[175],"software-only":[176],"vectorization,":[177],"small":[180],"amount":[181],"provide":[186],"significant":[188],"acceleration":[189],"boost.":[190]},"counts_by_year":[{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
