On-the-Go Grapevine Yield Estimation Using Image Analysis and Boolean Model

Table 6

Results obtained for the estimation of the yield per segment (composed of three vines) based on images captured with an “on-the-go” platform.

Grapevine variety	Manual harvest		Naïve estimator			Boolean model
	Mean yield (g)	Number of segments	Mean yield (g)	R ^2	RMSE (g)	Mean yield (g)	R ^2	RMSE (g)
Cabernet Sauvignon	3406	8	1321	0.64	1863.7	3235	0.50	574.5
Syrah	3322	10	1598	0.87	2031.9	3115	0.86	390.6
Tempranillo	5031	10	2175	0.59	3194.1	4660	0.60	790.8
Total	3920	28	1698	0.71	2472.0	3670	0.78	610.1

These measurements were obtained when using a naïve estimator and the Boolean model on images segmented using a Mahalanobis distance classifier and a three-step filtering process. Asterisks represent statistical significance: ; ; .