{"id":"https://openalex.org/W4367046546","doi":"https://doi.org/10.1145/3576842.3582366","title":"Eagle: End-to-end Deep Reinforcement Learning based Autonomous Control of PTZ Cameras","display_name":"Eagle: End-to-end Deep Reinforcement Learning based Autonomous Control of PTZ Cameras","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4367046546","doi":"https://doi.org/10.1145/3576842.3582366"},"language":"en","primary_location":{"id":"doi:10.1145/3576842.3582366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3576842.3582366","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3576842.3582366","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3576842.3582366","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069941852","display_name":"Sandeep Singh Sandha","orcid":"https://orcid.org/0000-0003-1421-1880"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandeep Singh Sandha","raw_affiliation_strings":["University of California, Los Angeles, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-1421-1880","affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, United States of America","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101689740","display_name":"Bharathan Balaji","orcid":"https://orcid.org/0000-0002-9490-2018"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bharathan Balaji","raw_affiliation_strings":["Amazon, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-9490-2018","affiliations":[{"raw_affiliation_string":"Amazon, United States of America","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050029555","display_name":"Luis Antonio Ribot Garc\u00eda","orcid":"https://orcid.org/0000-0002-5111-0694"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luis Garcia","raw_affiliation_strings":["University of Southern California, Information Sciences Institute, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-5111-0694","affiliations":[{"raw_affiliation_string":"University of Southern California, Information Sciences Institute, United States of America","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074563122","display_name":"Mani Srivastava","orcid":"https://orcid.org/0000-0002-3782-9192"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mani Srivastava","raw_affiliation_strings":["University of California, Los Angeles, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-3782-9192","affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, United States of America","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9997000098228455,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9997000098228455,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9995999932289124,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8351014852523804},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8277428150177002},{"id":"https://openalex.org/keywords/eagle","display_name":"Eagle","score":0.6350799202919006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.614257276058197},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48863106966018677},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4867081940174103},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4709915518760681},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.36807113885879517},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.13737234473228455}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8351014852523804},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8277428150177002},{"id":"https://openalex.org/C2780985876","wikidata":"https://www.wikidata.org/wiki/Q2092297","display_name":"Eagle","level":2,"score":0.6350799202919006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.614257276058197},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48863106966018677},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4867081940174103},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4709915518760681},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36807113885879517},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.13737234473228455},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3576842.3582366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3576842.3582366","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3576842.3582366","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3576842.3582366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3576842.3582366","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3576842.3582366","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G3285285838","display_name":"Collaborative Research: NCS: FO: Enhancing Episodic Memory through Real-world Integration of Brain Recording and Stimulation with Semantic Alignment of Human and IoT Perception","funder_award_id":"2124252","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3560604224","display_name":null,"funder_award_id":"FA9550-22-1-0193","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G3831091872","display_name":"Collaborative Research: CNS Core: Medium: IoCT:  System Mechanisms for Enabling an Internet of Collaborative Things","funder_award_id":"2211301","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367046546.pdf","grobid_xml":"https://content.openalex.org/works/W4367046546.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1512509126","https://openalex.org/W1989823960","https://openalex.org/W2088298109","https://openalex.org/W2114425417","https://openalex.org/W2252355370","https://openalex.org/W2618618567","https://openalex.org/W2885514323","https://openalex.org/W2944576261","https://openalex.org/W2963895973","https://openalex.org/W2995687583","https://openalex.org/W3030656010","https://openalex.org/W3067846174","https://openalex.org/W3104218139","https://openalex.org/W3159463067"],"related_works":["https://openalex.org/W647060948","https://openalex.org/W2380223122","https://openalex.org/W1491901162","https://openalex.org/W2371861705","https://openalex.org/W2949096641","https://openalex.org/W2970686063","https://openalex.org/W4320729701","https://openalex.org/W4254103348","https://openalex.org/W3210378990","https://openalex.org/W3034745255"],"abstract_inverted_index":{"Existing":[0],"approaches":[1,28],"for":[2,60,120,193],"autonomous":[3],"control":[4,22,90,127,133],"of":[5,23,45,50,124,139,145],"pan-tilt-zoom":[6],"(PTZ)":[7],"cameras":[8],"use":[9],"multiple":[10],"stages":[11],"where":[12],"object":[13,51,138],"detection":[14,52],"and":[15,32,110,122,151,171,184],"localization":[16],"are":[17,164],"performed":[18],"separately":[19],"from":[20,34],"the":[21,24,42,91,100,137,143,160],"PTZ":[25,92,125,191],"mechanisms.":[26],"These":[27],"require":[29],"manual":[30],"labels":[31],"suffer":[33],"performance":[35,134],"bottlenecks":[36],"due":[37,103],"to":[38,77,89,104,142,154,209],"error":[39],"propagation":[40],"across":[41],"multi-stage":[43],"flow":[44],"information.":[46],"The":[47],"large":[48],"size":[49],"neural":[53,80],"networks":[54],"also":[55],"makes":[56],"prior":[57],"solutions":[58],"infeasible":[59],"real-time":[61,190],"deployment":[62],"in":[63,99,202],"resource-constrained":[64,194],"devices.":[65],"We":[66,114],"present":[67],"an":[68],"end-to-end":[69],"deep":[70],"reinforcement":[71,95],"learning":[72,96],"(RL)":[73],"solution":[74],"called":[75],"Eagle1":[76],"train":[78],"a":[79,116],"network":[81],"policy":[82],"that":[83],"directly":[84,208],"takes":[85],"images":[86,147],"as":[87,179],"input":[88],"camera.":[93],"Training":[94],"is":[97],"cumbersome":[98],"real":[101],"world":[102],"labeling":[105],"effort,":[106],"runtime":[107],"environment":[108],"stochasticity,":[109],"fragile":[111],"experimental":[112],"setups.":[113],"introduce":[115],"photo-realistic":[117],"simulation":[118],"framework":[119],"training":[121],"evaluation":[123],"camera":[126,132,176],"policies.":[128],"Eagle":[129,162,199],"achieves":[130],"superior":[131],"by":[135],"maintaining":[136],"interest":[140],"close":[141],"center":[144],"captured":[146],"at":[148],"high":[149],"resolution":[150],"has":[152],"up":[153],"17%":[155],"more":[156],"tracking":[157,192],"duration":[158],"than":[159,169],"state-of-the-art.":[161],"policies":[163,200],"lightweight":[165],"(90x":[166],"fewer":[167],"parameters":[168],"Yolo5s)":[170],"can":[172,205],"run":[173],"on":[174],"embedded":[175],"platforms":[177],"such":[178],"Raspberry":[180],"PI":[181],"(33":[182],"FPS)":[183],"Jetson":[185],"Nano":[186],"(38":[187],"FPS),":[188],"facilitating":[189],"environments.":[195],"With":[196],"domain":[197],"randomization,":[198],"trained":[201],"our":[203],"simulator":[204],"be":[206],"transferred":[207],"real-world":[210],"scenarios2.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}