Automatic Samples Selection Using Histogram of Oriented Gradients (HOG) Feature Distance for Tsunami Victims Detection
Journal Title: EMITTER International Journal of Engineering Technology - Year 2017, Vol 5, Issue 2
Abstract
Finding victims at a disaster site is the primary goal of Search-and-Rescue (SAR) operations. Many technologies created from research for searching disaster victims through aerial imaging. but, most of them are difficult to detect victims at tsunami disaster sites with victims and backgrounds which are look similar. This research collects post-tsunami aerial imaging data from the internet to builds dataset and model for detecting tsunami disaster victims. Datasets are built based on distance differences from features every sample using Histogram-of-Oriented-Gradient (HOG) method. We use the longest distance to collect samples from photo to generate victim and non-victim samples. We claim steps to collect samples by measuring HOG feature distance from all samples. the longest distance between samples will take as a candidate to build the dataset, then classify victim (positives) and non-victim (negatives) samples manually. The dataset of tsunami disaster victims was re-analyzed using cross-validation Leave-One-Out (LOO) with Support-Vector-Machine (SVM) method. The experimental results show the performance of two test photos with 74.36% precision, 81.60% accuracy, 61.70% recall and f-measure 67.44% to distinguish victim (positives) and non-victim (negatives).
Authors and Affiliations
Inzar Salfikar, Indra Adji Sulistijono, Achmad Basuki
Keywords
Related Articles
- EP ID EP314015
- DOI 10.24003/emitter.v5i2.182
- Views 106
- Downloads 0
Performance Analysis of DTN Using Level Signal Priority Epidemic Routing Protocol
A DTN architecture consists of several nodes that are connected with high dynamic topology. The routing protocol is an important part which determine the DTN performance system. Although DTN is addressed to be tolerant o...
Implementation of Energy Efficiency Based on Time Scheduling to Improve Network Lifetime in Wireless Body Area Network (WBAN)
ZigBee applications of IEEE 802.15.4 Wireless Sensor Network (WSN) with Low Rate Wireless Personal Area Network (LR-WPAN) can be integrated with e-health technology Wireless Body Area Network (WBAN). WBAN are small size...
An Augmented Reality Application for the Community Learning about the Risk of Earthquake in a Multi-storey Building Area
Area surrounding tower is a danger area when earthquake attack. It has an enermous risk. People in this area have to know the risk for their safety. Socialization, simulation, and learning media need to be provided conti...
Remo Dance Motion Estimation with Markerless Motion Capture Using The Optical Flow Method
Motion capture has been developed and applied in various fields, one of them is dancing. Remo dance is a dance from East Java that tells the struggle of a prince who fought on the battlefield. Remo dancer does not use bo...
Fuzzy Gain Scheduling of PID (FGS-PID) for Speed Control Three Phase Induction Motor Based on Indirect Field Oriented Control (IFOC)
This paper propose about using PID control system based on Kp, Ki, and Kd parameter determination with scheduling process from fuzzy logic. Control system is used to arrange speed of three phase induction motor using IFO...