The Proposed TechniqueWepropose technique to optimizing a real-time panic detection.
Theseoptimizations will include the reduction of the computational complexity whilemaintaining a high accuracy. Our real-time technique does not require any priorknowledge about a given video. Moreover, it will be applicable to various crowddensities (high-, moderate- and low-density). The proposed technique works in three steps:1- Different between twoconsecutive frames:The proposed technique starts dividethe video into frames. Then, two consecutive frames t and t?1 are compared pixel bypixel, to found the absolute values of the differences between twocorresponding pixels.
The absolute differential image is defined as follows: Id (t, t+1) = |It+1 – It|(1)It is supposed tobe the value of the tth frame in image sequences. It+1 isthe value of the (t+1)th frame in image sequences. The goal of thisstep to reduce the computation complexity and avoid the motion estimation. To achievethat the result is the positive number that represents the dissimilarity betweenpixels, if there is different that mean there is motion. 2- Calculate the Wavelet Transforms The result from theprevious step is a positive number used as input of Wavelet Transforms 1. A brief description of Wavelet Transforms in the following section.Images as smooth regions interrupted by edges, these edges are often the most interestingparts of the data both perceptually and in terms of the information theyprovide.
So, wavelet transform is a powerful tool for data analysis and presentthe edges. A wavelet from the name issmall waves with limited duration. The wavelets transform is set of mathematicalfunction used to decompose data into different component. The image will divideinto four different subbands as LL (Low frequency), HH (high frequencydiagonal), HL (low frequency horizontal) and LH (low frequency Vertical). Thisbreaking process can be repeated to have multi-level wavelet components like 2Level,3Level.
In our proposed technique we applied the three level 1 ,2 and 3 of wavelettransform. Coefficients matrices cH, cV, and cD(horizontal, vertical, and diagonal, respectively), obtained by waveletdecomposition of the input which is different between two consecutive frames. In principle after comparative study betweenthe results, we found the level 3 is better than other levels because it gavemore accurate result with decrease the false alarm. The goal of this step to foundhigh frequency part which mean the possibility of panic event is increase. 3- Sum of all coefficient After calculate the Wavelet Transformsin the different between two consecutive frames. We divide each subband into oneblock and four blocks to sum the coefficient cH, cD and cV on each block forall frames.
The result of this step we will have the sum of coefficient cH1 , cH2and cH3 for all frames in case one block and four blocks. The same processrepeated for the cV and cD coefficients. When the value of the sum the coefficientis high compare to the all previous frames that’s mean there is panic event.
The following equation is used for sum of coefficients:S = (2)Where S denote to sum of coefficient,n number of frames, and c is the coefficient. The goal of this step to detectthe panic event.