Background subtraction is often the first step in many computer vision applications such as object localisation and tracking. It aims to segment out moving parts of a scene that represent object of interests. In the field of computer vision, researchers have dedicated their efforts to improve the robustness and accuracy of such segmentations but most of their methods are computationally intensive, making them nonviable options for our targeted embedded camera platform whose energy and processing power is significantly more constrained. To address this problem as well as maintain an acceptable level of performance, we introduce Compressive Sensing (CS) to the widely used Mixture of Gaussian to create a new background subtraction method. The results show that our method not only can decrease the computation significantly (a factor of 7 in a DSP setting) but remains comparably accurate.
A novel automatic target detection and tracking algorithm for tracking targets based on ship borne infrared imagery is proposed in this paper. The algorithm has two modes: detection and tracking. In detection mode, the proposed algorithm utilized difference between the consecutive frames and top-hat filter to determine the target position. In tracking mode, the Intensity Variation Function (IVF) is utilized. Before tracking and location the new position, the algorithm should determine the IVF whether reliable. If unreliable, the mode turns to detection. Experimental results by using real-life infrared image sequence are shown to validate the robustness of the proposed technique.
In this paper, a quantum color image watermarking scheme is proposed through twice-scrambling of Arnold transformations and steganography of least significant bit (LSB). Both carrier image and watermark images are represented by the novel quantum representation of color digital images model (NCQI). The image sizes for carrier and watermark are assumed to be [Formula: see text] and [Formula: see text], respectively. At first, the watermark is scrambled into a disordered form through image preprocessing technique of exchanging the image pixel position and altering the color information based on Arnold transforms, simultaneously. Then, the scrambled watermark with [Formula: see text] image size and 24-qubit grayscale is further expanded to an image with size [Formula: see text] and 6-qubit grayscale using the nearest-neighbor interpolation method. Finally, the scrambled and expanded watermark is embedded into the carrier by steganography of LSB scheme, and a key image with [Formula: see text] size and 3-qubit information is generated at the meantime, which only can use the key image to retrieve the original watermark. The extraction of watermark is the reverse process of embedding, which is achieved by applying a sequence of operations in the reverse order. Simulation-based experimental results involving different carrier and watermark images (i.e. conventional or non-quantum) are simulated based on the classical computer’s MATLAB 2014b software, which illustrates that the present method has a good performance in terms of three items: visual quality, robustness and steganography capacity.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.