Handbook of Multimedia for Digital Entertainment and Arts- P15

Handbook of Multimedia for Digital Entertainment and Arts- P15: The advances in computer entertainment, multi-player and online games,technology-enabled art, culture and performance have created a new form of entertainmentand art, which attracts and absorbs their participants. The fantastic successof this new field has influenced the development of the new digital entertainmentindustry and related products and services, which has impacted every aspect of ourlives.
Nội dung trích xuất từ tài liệu:
Handbook of Multimedia for Digital Entertainment and Arts- P15416 Y.M. Ro and S.H. Jinabove, the frames of soccer videos were categorized into four view types, i.e., V DfC; M; G; Gp g. The processing time for the view decision in soccer videos wasmeasured. Table 1 shows the time measured for the view type decision for different terminalcomputing power. As shown, the longest time is taken to detect the global view withgoal post. From the experimental results, the first condition of the soccer video, meaning itsstability in real-time for the proposed filtering system, can be found by substitutingthese results to Eq. (3). For the soccer video, the first condition can be described as, D N f P T .Gp / Ä 1; ı therefore; N f Ä 1 P T .Gp /: (6) The second condition is verified by evaluating the filtering performance of theproposed filtering algorithm. Figure 9 shows the variation of the filtering perfor-mance with respect to sampling rate. As shown, the performance (recall rate in thefigure) decreases as the sampling rate decreases. From Fig. 9, it is shown that themaximum permissible limit of sampling rate is determined by the tolerance .Tfp / offiltering performance. When the system permits about 80% filtering performance ofTfp , it is observed that the sampling rate, fs , becomes 2.5 frames per second by theexperimental result. As a result of the experiments, we obtain the system requirements for real-timefiltering of soccer videos as shown in Fig. 10. Substituting PT .Gp /s of Table 1 into Table 1 Processing time for the view type decision Terminal View T1 T2 T3 EŒPT.C / 0.170 sec. 0.037 sec. 0.025 sec. EŒPT.M / 0.270 sec. 0.075 sec. 0.045 sec. EŒPT.G/ 0.281 sec. 0.174 sec. 0.088 sec. EŒPT.Gp / 0.314 sec. 0.206 sec. 0.110 sec.Fig. 9 Variation of filtering performance according to sampling rate18 Real-Time Content Filtering for Live Broadcasts in TV Terminals 417Eq. (6), we acquire the number of input channels and frame sampling rates availablein the used filtering system. As shown, the number of input channels depends onboth sampling rate and terminal capability. By assuming the confidence limit of thefiltering performance, Tfp , we also get the minimum sampling rate from Fig. 10.Fig. 10 The number of input channels enables the real-time filtering system to satisfy the filteringrequirements in (a) Terminal 1, (b) Terminal 2, and (c) Terminal 3. 1 and 2 lines indicate theconditions of Eq. 6 and Fig. 9, respectively. 1 line shows that the number of input channels isinversely proportional to b with the processing time of Gp . 2 line is the range of sampling raterequired to maintain over 80% filtering performance. And 3 line (the dotted horizontal line),represents the minimum number of channels, i.e., one channel418 Y.M. Ro and S.H. Jin To maintain stability in the filtering system, the number of input channels and thesampling rate should be selected in the range where the three conditions by 1 , 2 ,and 3 lines meet. Supposing that the confidence limit of the filtering performanceis 80%, Figure 10 illustrates the following results: one input channel is allowablefor real-time filtering in Terminal 1 at sampling rates between 2.5 and 3 frames persecond. In Terminal 2, one or two channels are allowable at sampling rates between2.5 and 4.5 frames per second. Terminal 3 can have less than four channels at sam-pling rates between 2.5 and 9 frames per second. The results show that Terminal 3,which has the highest capability, has a higher number of input channels for real-timefiltering than the others. We implemented the real-time filtering system on our test-bed [27] as shown inFig. 11. The main screen shows a drama channel assumed to be the favorite stationof the TV viewer. And the screen box at the bottom right in the figure shows thefiltered broadcast from the channel of interest. In this case, a soccer video is selectedas the channel of interest and “Shooting” and “Goal” scenes are considered as themeaningful scenes. To perform the filtering algorithm on the soccer video, the CPU usage and mem-ory consumption of each terminal should remain stable. Each shows a memoryconsumption of between 32 and 38 Mbytes, and an average of 85% .T1 /, 56% .T2 /,and 25% .T3 / CPU usage time by a Window’s performance monitor.Fig. 11 Screen shot to run real-time content filtering service with a single channel of interest18 Real-Time Content Filtering for Live Broadcasts in TV Terminals 419DiscussionFor practical purposes, we will discuss the design, implementation and integrationof the proposed filtering system with a real set-top box. To realize the proposedsystem, computing power to calculate and perform the filtering algorithm within thelimited time is the most important element. We expect that TV terminals equippedwith STB and PVR will evolve into multimedia centers in the home with computingand home server connections [28, 29]. The terminal also requires a digital tunerenabling it to extract each broadcasting stream time-division, or multiple tuners forthe filtering of multiple channels Next, practical implementation should be basedon conditions such as buffer size, the number of channels, filtering performance,sampling rate, etc., in order to stabilize filtering performance. Finally, the terminalshould know the genre of the input broadcasting video because the applied filtering ...