In this paper, a computer vision system for counting people standing in line is presented. In this application, common techniques such as Adaptive Background Subtraction (ABS), blob tracking with Kalman filter, and occlusion resistive techniques are used to detect and track people. Additionally, a novel method using Dual Adaptive Background Subtractors (DABS) is implemented for dynamically determining the line region in a real-world crowded scene, and also as an alternative target acquisition to regular ABS. The DABS technique acts as a temporal bandpass filter for motion, helping identify people standing in line while in the presence of other moving people. This is achieved by using two ABS with different temporal adaptiveness. Unlike other computer vision papers which perform tests in highly controlled environments, the DABS technique is tested in a crowded Starbucks© at the Cal Poly student union. For any length of people standing in line, result shows that DABS has a lower mean error by one or more people when compared to ABS. Even in challenging crowded scenes where the line can reach 19 people in length, DABS achieves a Normalized RMS Error of 43%.
","abstract_html":"<p>In this paper, a computer vision system for counting people standing in line is presented. In this application, common techniques such as Adaptive Background Subtraction (ABS), blob tracking with Kalman filter, and occlusion resistive techniques are used to detect and track people. Additionally, a novel method using Dual Adaptive Background Subtractors (DABS) is implemented for dynamically determining the line region in a real-world crowded scene, and also as an alternative target acquisition to regular ABS. The DABS technique acts as a temporal bandpass filter for motion, helping identify people standing in line while in the presence of other moving people. This is achieved by using two ABS with different temporal adaptiveness. Unlike other computer vision papers which perform tests in highly controlled environments, the DABS technique is tested in a crowded Starbucks© at the Cal Poly student union. For any length of people standing in line, result shows that DABS has a lower mean error by one or more people when compared to ABS. Even in challenging crowded scenes where the line can reach 19 people in length, DABS achieves a Normalized RMS Error of 43%.</p>","abstract_has_math":false,"creators":["Gargov, George Dimitrov"],"institution":null,"degree_name":"MS in Electrical Engineering","degree_level":null,"degree_discipline":"Electrical Engineering","degree_department":null,"school":null,"contributors":["John Oliver"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2016,"date_issued":"2016-03-01T08:00:00Z","date_published":"2016-03-01T08:00:00Z","updated_at":"2026-07-24T01:31:35Z","subjects":["computer vision","adaptive background subtraction","kalman filter","line monitoring","Signal Processing"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["10.15368/theses.2016.11"],"render_values":[{"text":"10.15368/theses.2016.11","href":"https://doi.org/10.15368/theses.2016.11","code":true}]}]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/1539","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["John Oliver"]},{"key":"dc:creator","label":"Author","values":["Gargov, George Dimitrov"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2016-03-17T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Electrical Engineering"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["computer vision","adaptive background subtraction","kalman filter","line monitoring","Signal Processing"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/1539","10.15368/theses.2016.11"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In this paper, a computer vision system for counting people standing in line is presented. In this application, common techniques such as Adaptive Background Subtraction (ABS), blob tracking with Kalman filter, and occlusion resistive techniques are used to detect and track people. Additionally, a novel method using Dual Adaptive Background Subtractors (DABS) is implemented for dynamically determining the line region in a real-world crowded scene, and also as an alternative target acquisition to regular ABS. The DABS technique acts as a temporal bandpass filter for motion, helping identify people standing in line while in the presence of other moving people. This is achieved by using two ABS with different temporal adaptiveness. Unlike other computer vision papers which perform tests in highly controlled environments, the DABS technique is tested in a crowded Starbucks© at the Cal Poly student union. For any length of people standing in line, result shows that DABS has a lower mean error by one or more people when compared to ABS. Even in challenging crowded scenes where the line can reach 19 people in length, DABS achieves a Normalized RMS Error of 43%.
"]},{"key":"dc:title","label":"Title","values":["Coffee Queue Project"]}]}],"canonical_facts":{"dc:contributor":["John Oliver"],"dc:creator":["Gargov, George Dimitrov"],"dc:date.available":["2016-03-17T07:00:00Z"],"dc:description.abstract":["In this paper, a computer vision system for counting people standing in line is presented. In this application, common techniques such as Adaptive Background Subtraction (ABS), blob tracking with Kalman filter, and occlusion resistive techniques are used to detect and track people. Additionally, a novel method using Dual Adaptive Background Subtractors (DABS) is implemented for dynamically determining the line region in a real-world crowded scene, and also as an alternative target acquisition to regular ABS. The DABS technique acts as a temporal bandpass filter for motion, helping identify people standing in line while in the presence of other moving people. This is achieved by using two ABS with different temporal adaptiveness. Unlike other computer vision papers which perform tests in highly controlled environments, the DABS technique is tested in a crowded Starbucks© at the Cal Poly student union. For any length of people standing in line, result shows that DABS has a lower mean error by one or more people when compared to ABS. Even in challenging crowded scenes where the line can reach 19 people in length, DABS achieves a Normalized RMS Error of 43%.
"],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/1539","10.15368/theses.2016.11"],"dc:subject":["computer vision","adaptive background subtraction","kalman filter","line monitoring","Signal Processing"],"dc:title":["Coffee Queue Project"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_name":["MS in Electrical Engineering"]},"updated_at":"2026-07-24T01:31:35Z"}