Edge Detection-Based Feature Extraction for the Systems of Activity Recognition

Table 1

Accuracy of classification for the proposed methodology against depth dataset.

Activities	BN	JC	PLJ	RNN	SIM	SKP	WLK	OW1	OW2	JP	CLP	BXG	SUD
BN	98	0	0	0	0	2	0	0	0	0	0	0	0
JC	0	97	1	0	0	2	0	0	0	0	0	0	0
PLJ	0	0	99	0	0	0	0	1	0	0	0	0	0
RNN	0	2	0	96	0	0	1	0	0	1	0	0	0
SIM	0	0	0	0	100	0	0	0	0	0	0	0	0
SKP	0	0	1	0	0	95	1	0	1	0	1	0	1
WLK	0	0	0	0	0	0	100	0	0	0	0	0	0
OW1	0	0	0	0	1	0	0	99	0	0	0	0	0
OW2	1	0	0	0	0	1	0	0	97	0	0	1	0
JP	0	0	1	0	0	0	0	1	0	98	0	0	0
CLP	0	0	0	0	0	1	0	0	0	0	99	0	0
BXG	0	2	0	1	0	0	1	0	0	0	0	96	0
SUD	0	0	0	0	1	0	0	0	0	0	0	0	99
Average	97.9%

BN for bending, JC for jacking, PLJ for place jumping, RNN for running, SIM for side movement, SKP for skipping, WLK for walking, OW1 for one-hand waving, OW2 for two-hand waving, JP for jumping, CLP for clapping, BXG for boxing, and SUD for sitting up and down