A Large-Scale Dataset and Deep Learning Model for Detecting and Counting Olive Trees in Satellite Imagery

Table 2

A comparison of the proposed model’s results to previous research.

Technique	Dataset	Spectrum	No. of images	Performance metrics
				OA	CER (%)	OER (%)	EE (%)
Reticular matching [28]	QuickBird	Greyscale	N/A	98%	5	7	1.24
Multilevel thresholding [17]	SIGPAC viewer	Greyscale	95	96%	5	3	1.2
Detection using red bands [1]	SIGPAC viewer	Red band	60	N/A	1.2	4	1.27
Improved K-means algorithm [16]	SIGPAC viewer	RGB	110	97.5%	4	1	0.97
Proposed model	Satellites Pro	RGB	230	98.3%	0.97	1.2	0.94