In today’s digital world, the growth of internet and communication technology has significantly increased the transmission of data in large amount. As a result, the secure transmission of data has become a pre-requisite. Generally, for video steganography whole frame/frames are utilized to conceal secret data which usually causes visual distortion. To overcome this problem, the paper presents a new video steganography approach based on moving object detection and tracking where the secret data is embedded in LSB (a least significant bit) of moving objects. Background subtraction using GMM (Gaussian mixture model) is used for detection in objects that possess motion. Albeit the embedding in moving objects is cumbersome, however, pixels selection of moving objects in videos provides more security than embedding in each frame considering as an individual image. Also, moving objects causes less distortion after embedding making it hard for the intruder to detect, ensuring the imperceptibility of the stego-video. Eventually, the proposed technique is compared with LSB embedding exclusively in frames of the video, and the results illustrated that the proposed scheme performed better than the simple LSB embedding technique.
CITATION STYLE
Dalal, M., Singh, M., Kumar, A., Charu, & Juneja, M. (2019). An approach of data hiding in video steganography using object detection. International Journal of Engineering and Advanced Technology, 8(5), 2460–2466.
Mendeley helps you to discover research relevant for your work.