scholarly journals Color-Texture Based Object Tracking Using HSV Color Space and Local Binary Pattern

Author(s):  
Priyanto Hidayatullah ◽  
◽  
Miftahuddin Zuhdi ◽  
2013 ◽  
Vol 765-767 ◽  
pp. 2403-2406
Author(s):  
Jing Du ◽  
Yun Yang Yan ◽  
Xi Yin Wu ◽  
Yian Liu

Fire detection based on images is an effective method for fire prevention, especially in big room or badly environment. It is important to extract the features of a flame image. According to the idea of visual saliency in computer vision, saliency model of brightness, color and flame texture are proposed here. The saliency of flame brightness is indicated by the V component in HSV color space. The saliency of flame color is expressed by the relation of R and B in the RGB color space. The saliency of flame texture is described by the distance between the feature vectors which are the combination of features with Local Binary Pattern. Experimental results show the saliency model is effective for flame feature extraction.


Author(s):  
Sheikh Summerah

Abstract: This study presents a strategy to automate the process to recognize and track objects using color and motion. Video Tracking is the approach to detect a moving item using a camera across the long distance. The basic goal of video tracking is in successive video frames to link target objects. When objects move quicker in proportion to frame rate, the connection might be particularly difficult. This work develops a method to follow moving objects in real-time utilizing HSV color space values and OpenCV in distinct video frames.. We start by deriving the HSV value of an object to be tracked and then in the testing stage, track the object. It was seen that the objects were tracked with 90% accuracy. Keywords: HSV, OpenCV, Object tracking,


Author(s):  
Jong Hun Park ◽  
Gang Seong Lee ◽  
Jin Soo Kim ◽  
Seuc Ho Ryu ◽  
Sang Hun Lee

Sign in / Sign up

Export Citation Format

Share Document