P2-3-4 
-4 
-1 
-2 
.(m) 
► X 
Area within the 
1 
Area within the 
radius of 1 meter 
2 
I 
l/ 
radius of 2 meters 
i 
Horizontal steel pipe 
6 
Vertical steel pipe 
7 
/ / 
8 
/ / 
9 
- 
(m) 
Z 
2 3 4 5 6 (m) 
-r T T r-mr x 
1.5 
1 
(a) Locus of waist on X-Z 
4 Y 
(b) Locus of waist on X-Z 
1.5 
AY 
Horizontal steel pipe 
0.5 
-0.5 
-0.5 
-1.5 L 
(c) Locus of waist on X-Y 
0.5 
1.5 
/ 
Vertical steel pipe 
(m) X 
2 2.5 3 
(rri! 
(d) Locus of waist on X-Y 
Figure 7 Motion analysis 
4 CONCLUSIONS AND FURTHER WORKS 
In order to develop an ergoma system, the automated feature 
extraction methods were described, and human motion analyses 
were performed in this paper. The remarkable points of this 
paper are as follows: 
1) The feature point was extracted efficiently using opening in 
morphological image processing. 
2) 92 % for all extracting the feature area were performed 
automatically. 
3) A kind of work was distinguished automatically using the 
difference of radiation color. 
4) Work analysis for horizontal and vertical steel pipes were 
performed. 
5) Human motion analyses were performed using 3D data of the 
feature point. 
There are still, however, following issues that need to be resolved 
before this ergoma system may become operational. 
1 ) More effective feature extraction method under the insufficient 
image quality. 
2) Automated feature extraction system. 
3) Motion analysis without any marker. 
4) Rapid acceleration of system. 
5) Image processing for more 2 mans. 
6) Camera calibration with no control points. 
REFERENCES 
Yamada, N. and Chikatsu, H., 1999. Remapping of Historical 
Maps using Mathematical Morphology and Its Application. 
International Workshop on Mobile Mapping Technology.