Text

PENDETEKSIAN KEMUNCULAN OBJEK NYALA API BERBASISKAN CITRA DIGITAL BERGERAK

---

Penilaian

---

Object detection is required to prevent fire disaster. Object detection is a famous development in computer vision area. It’s because its ability that can differentiate between object in a natural image capture. Fire detection can be applied on a device such as home surveillance camera. The function that being utilize is the ability to detect object around it. Object detection in this research is YOLO method. YOLO or You Only Look Once is a detection method based on neural networks. YOLO does the detection process through CNN algorithm only once. This research chose YOLOv3 as the YOLO version used. This research use a primary type dataset with a total of 4 datasets. The video format is mp4. The dataset is divided by 2 parts, one 5 second video for the training process, and 3 1 second video for the testing process. This research found the result which show 48% of dataset 1 are able to achieve a satisfying result, while dataset 2 only able to achieve 3%. The system failed to detect any object in dataset 3. The failure is due to dataset lack of quantity and the data variety in training process.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207004784	T82622	T826222022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T826222022

Publisher

Inderalaya : Jurusan Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2022

Collation

xvii, 41 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

621.390 7

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Teknik Informatika
teknik elektronika komputer digital

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment