Normal view MARC view ISBD view

Real-time smart reporting system via CCTV using hand gesture recognition with face detection feature / France Peter C. Ballon, Sharomae Jean B. Caag, Jessica Mae S. Cortez, John Bryan S. Gozum, Juliana Kyle C. Londonio, Maria Beatrice Maniquis, Adan Flloyd Quitol. 6

By: France Peter C. Ballon, Sharomae Jean B. Caag, Jessica Mae S. Cortez, John Bryan S. Gozum, Juliana Kyle C. Londonio, Maria Beatrice Maniquis, Adan Flloyd Quitol. 4 0 16, [, ] | [, ] |

Contributor(s): 5 6 [] |

Language: Unknown language code Summary language: Unknown language code Original language: Unknown language code Series: ; June 2023.46Edition: Description: 28 cm. xiii, 162 ppContent type: text Media type: unmediated Carrier type: volumeISBN: ISSN: 2Other title: 6 []Uniform titles: | | Related works: 1 40 6 []Subject(s): -- 2 -- 0 -- -- | -- 2 -- 0 -- 6 -- | 2 0 -- | -- -- 20 -- | | -- -- -- -- 20 -- | -- -- -- 20 -- --Genre/Form: -- 2 -- Additional physical formats: DDC classification: | LOC classification: | | 2Other classification:

Contents:

Action note: In: Summary: ABSTRACT: This study presents the development and implementation of a real-time smart reporting system via CCTV using hand gesture recognition with face detection features. The system is designed to automate the process of reporting incidents such as accidents, by detecting gestures made by individuals within the camera's field of view. The system machine learning algorithms, specifically Mediapipe's CNN and Haar Cascade, to recognize hand gestures and facial features, and can provide accurate and timely reporting of incidents to proper authorities. The assessment of the system's accuracy in hand gesture recognition across different distances from the CCTV reveals a decrease in accuracy as the subject moves farther away. The average accuracy of face detection using CCTV with an optimal distance of 0.05 is 98%. Furthermore, statistical analysis at a 5% level of significance indicates that the number of hands present in the frame does not significantly affect accuracy (p-value = 0.126). The performance assessment of the system in terms of recognition time and accuracy under various lighting conditions shows consistent recognition time, with the highest accuracy observed in morning and evening lighting conditions. However, the system struggles to identify negative hand gestures in afternoon lighting conditions. Lighting conditions account for 9.14% of the variability in face detection rate, with brighter conditions enhancing successful face extraction. Finally, there is no statistically significant difference I the reporting delay between large and small file sizex for uncidents recorded in .cvs files. Other editions:

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings ( 1 )
Title notes
Comments ( 0 )

Item type	Current location	Home library	Collection	Call number	Status	Date due	Barcode	Item holds
Book	PLM	PLM Filipiniana Section	Filipiniana-Thesis	T TK1.B34.2023 (Browse shelf)	Available		FT7713

Total holds: 0

Browsing PLM Shelves , Shelving location: Filipiniana Section , Collection code: Filipiniana-Thesis Close shelf browser

Previous	No cover image available	No cover image available	No cover image available	No cover image available	No cover image available	No cover image available	No cover image available	Next
Previous	T TK1.Ar5.2023 Long term load forecasting for Luzon, Philippines: A comparative analysis of linear support vector regression, multilayer perceptron, and linear regression with XG-Boost /	T TK1.As9.2023 Human controlled search and rescue robot with BLE-based victim localization /	T TK1.B33. 2023 Piezoelectric energy harvesting system with real-time monitoring using IoT-based technology /	T TK1.B34.2023 Real-time smart reporting system via CCTV using hand gesture recognition with face detection feature /	T TK1.B38.2023 Automated infectious waste segregation with disinfection system utilizing microcontroller for mitigation & monitoring of infectivity hazard /	T TK1.B47.2023 Development of a TEG-based household griller prototype using charcoal and charcoal briquettes as the hot source and a reusable ice pack as the cold source with charging capability /	T TK1.B58.2023 Implementation of small-scale floating drum biogas digester for pig manure as an alternative electricity source for backyard piggery in Brgy. Mangas 1, Alfonso, Cavite /	Next

Undergraduate Thesis: (Bachelor of Science in Electronics Engineering) - Pamantasan ng Lungsod ng Maynila, 2023. 56

ABSTRACT: This study presents the development and implementation of a real-time smart reporting system via CCTV using hand gesture recognition with face detection features. The system is designed to automate the process of reporting incidents such as accidents, by detecting gestures made by individuals within the camera's field of view. The system machine learning algorithms, specifically Mediapipe's CNN and Haar Cascade, to recognize hand gestures and facial features, and can provide accurate and timely reporting of incidents to proper authorities. The assessment of the system's accuracy in hand gesture recognition across different distances from the CCTV reveals a decrease in accuracy as the subject moves farther away. The average accuracy of face detection using CCTV with an optimal distance of 0.05 is 98%. Furthermore, statistical analysis at a 5% level of significance indicates that the number of hands present in the frame does not significantly affect accuracy (p-value = 0.126). The performance assessment of the system in terms of recognition time and accuracy under various lighting conditions shows consistent recognition time, with the highest accuracy observed in morning and evening lighting conditions. However, the system struggles to identify negative hand gestures in afternoon lighting conditions. Lighting conditions account for 9.14% of the variability in face detection rate, with brighter conditions enhancing successful face extraction. Finally, there is no statistically significant difference I the reporting delay between large and small file sizex for uncidents recorded in .cvs files.

There are no comments for this item.

to post a comment.