Design of Efficient Image Fire Detection using Convolutional Neural Network
| dc.contributor.guide | Deshmukh, Maroti | |
| dc.coverage.spatial | ||
| dc.creator.researcher | Vishwakarma, Arvind Kumar | |
| dc.date.accessioned | 2025-07-10T11:43:50Z | |
| dc.date.available | 2025-07-10T11:43:50Z | |
| dc.date.awarded | 2025 | |
| dc.date.completed | 2025 | |
| dc.date.registered | 2020 | |
| dc.description.abstract | Fire detection is essential for safeguarding lives, minimizing financial loss, and preserving man-made and natural environments. An early fire detection system is designed to newlinedeliver rapid warnings, enabling prompt actions such as extinguishing the fire, evacuating occupants, or alerting emergency responders. A critical feature of early fire detection newlineis proactive monitoring, which involves continuous surveillance for fire indicators such newlineas smoke, heat, or gas emissions utilizing specialized sensors or smart systems. newlineTraditional fire detection methods rely on manually crafted features such as color, texture, and motion, combined with conventional classification algorithms. These approaches are often limited by environmental conditions, such as lighting, smoke obstructions, or similar colors, which can lead to high false positive and false negative newlinerates. Moreover, they lack adaptability and struggle with complex scenarios where fire newlinecharacteristics deviate from predefined patterns. newlineIn contrast, deep learning-based fire detection methods leverage Convolutional Neural newlineNetwork (CNN) to automatically learn hierarchical features from static images. These newlinemethods excel in recognizing fire patterns under varying conditions, including low-light newlineor smoky environments, due to their ability to process high-dimensional data and generalize from large datasets. CNN have gained prominence in image-based tasks, such newlineas fire detection, due to several advantages, including automated feature extraction, enhanced accuracy and robustness, adaptability to complex patterns, scalability with large newlinedatasets, and the ability to leverage transfer learning. These attributes make CNN more newlineeffective and preferred over traditional methods. newline newline | |
| dc.description.note | ||
| dc.format.accompanyingmaterial | DVD | |
| dc.format.dimensions | 28 cm | |
| dc.format.extent | xx,128 p. | |
| dc.identifier.researcherid | 0009-0009-0554-4473 | |
| dc.identifier.uri | http://hdl.handle.net/10603/651341 | |
| dc.language | English | |
| dc.publisher.institution | Department Computer Science and Engineering | |
| dc.publisher.place | Srinagar | |
| dc.publisher.university | National Institute of Technology Uttarakhand | |
| dc.relation | ||
| dc.rights | university | |
| dc.source.university | University | |
| dc.subject.keyword | Computer Science | |
| dc.subject.keyword | Engineering and Technology | |
| dc.subject.keyword | Telecommunications | |
| dc.title | Design of Efficient Image Fire Detection using Convolutional Neural Network | |
| dc.title.alternative | ||
| dc.type.degree | Ph.D. |
Files
Original bundle
1 - 5 of 12
Loading...
- Name:
- 01_title.pdf
- Size:
- 3.14 MB
- Format:
- Adobe Portable Document Format
- Description:
- Attached File
Loading...
- Name:
- 03_table of content.pdf
- Size:
- 3.16 MB
- Format:
- Adobe Portable Document Format
License bundle
1 - 1 of 1