ABSTRACT
This work presents a comparative analysis using the mAP metric
of the YOLOv7 and SSD algorithms applied to the field of computer
vision. The comparison is performed through the detection of potholes
on highways and roads. In works defended by other authors,
both techniques are considered for applications in computer vision.
In this study, both models achieved promising results in pothole
detection; however, it is observed that the YOLOv7 model reached
an mAP metric of 80%, while the SSD model obtained an mAP of
73%. Thus, the results indicate that YOLOv7 is more efficient and
accurate in pothole detection in this specific context.