Weighted Unsupervised Learning for 3D Object Detection
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2016, Vol 7, Issue 1
Abstract
This paper introduces a novel weighted unsuper-vised learning for object detection using an RGB-D camera. This technique is feasible for detecting the moving objects in the noisy environments that are captured by an RGB-D camera. The main contribution of this paper is a real-time algorithm for detecting each object using weighted clustering as a separate cluster. In a preprocessing step, the algorithm calculates the pose 3D position X, Y, Z and RGB color of each data point and then it calculates each data point’s normal vector using the point’s neighbor. After preprocessing, our algorithm calculates k-weights for each data point; each weight indicates membership. Resulting in clustered objects of the scene.
Authors and Affiliations
Kamran Kowsari, Manal Alassaf
Keywords
Related Articles
- EP ID EP133251
- DOI 10.14569/IJACSA.2016.070180
- Views 94
- Downloads 0
Development of a Mobile Phone Based e-Health Monitoring Application
The use of Electrocardiogram (ECG) system is important in primary diagnosis and survival analysis of the heart diseases. Growing portable mobile technologies have provided possibilities for medical monitoring for h...
Pedestrian Crossing Safety System at Traffic Lights based on Decision Tree Algorithm
Pedestrians are one of the street users who have the right to get priority on security. Highway users such as vehicle drivers sometimes violate the traffic lights that is endanger pedestrians and make pedestrians feel in...
An Improved Transformer for LLC Resonant Inverter for Induction Heating Applications
A new trend in power converters is to design a planar transformer that aims for low profile. However, at high frequency, the planar transformer AC losses become significant due to the proximity and skin effects. In this...
Document Similarity Detection using K-Means and Cosine Distance
A two-year study by the Ministry of Research, Technology and Education in Indonesia presented the evaluation of most universities in Indonesia. The findings of the evaluation are the peculiarities of various dissertation...
Hybrid Algorithm for the Optimization of Training Convolutional Neural Network
The training optimization processes and efficient fast classification are vital elements in the development of a convolution neural network (CNN). Although stochastic gradient descend (SGD) is a Prevalence algorithm used...