Evaluation and Comparison of Novel Yolo V5 Algorithm in Identifying Land Cover Area of Geographical Regions over Single Shot Detector Algorithm Accuracy

The research aims to evaluate and compare the Land cover Image detection accuracy rate of Novel Yolo v5 algorithm to Single Shot Detection. The images of the land areas are sourced with a count of 5109 from the Kaggle website. Accuracy rate of the Novel Yolo v5 algorithm and Single Shot Detection is assessed in this study. The prediction of image detection is carried out with an iteration size of twenty, with ten coming from Group 1 and ten coming from Group 2. The goal is to get a higher rate of accuracy from the prediction. The Novel Yolo v5 approach has a success percentage of 96.81 percent, which is much higher than the Single shot detector (SSD) technique, which has a success rate of 91.62 percent. A statistically significant difference may be seen between these two methods, as shown by a p value of 0.00 (p<0.05, Independent sample t-test). Regarding the prediction of land cover image detection, the (V 5) model achieves a higher rate of accuracy than the Single Shot Detector (SSD) model. This is especially true when comparing the two models.