Research Article
Efficient Active Sensing with Categorized Further Explorations for a Home Behavior-Monitoring Robot
Pseudocode 1: Normal_Mode_Monitoring.
| Codes | | Begin_Normal_Mode_Monitoring | | BF = recogActivity (IF[t])) BF = 1~6 | | If calAD(IT[BF], IF[t]) > ThAD | | FlagFrame[t] = 1 | | Else. | | FlagFrame[t] = 0 | | If NIR = ∑j=1~min(t,ConstBuff) FlagFrame[j] > ThNIR | | Goto Change_DepthRange | | Else | | Goto Begin_Normal_Mode_Monitoring | | End_Normal_Mode_Monitoring | | | Explanation of parameters and functions | | BF: activity recognized, IF[t]: image of frame t | | IT[BF]:the templates of BF. | | ThAD: a threshold to decide whether irregular or not | | FlagFrame[t]: flag of frame t; 1: irregular frame | | 0: normal frame | | NIR: number of irregular frames | | ThNIR: a threshold to decide irregularity occurrence | | ConstBuff: A constant denoting number of past frames for checking | | Functions called | | recogActivity(): activity recognition (ref. [10]) | | calAD():accumulated difference calculation |
|
Pseudocode 1: Normal_Mode_Monitoring. |
