Fig. 3

LanDet utilizes a dense detection network denoted as DN that is trained with the multi-task loss \(LanDet_{loss}\). The purpose of this network is to transform an input image represented by I into a collection of output grids denoted as \({\hat{G}}\). These grids contain the predicted landmark objects represented by \({\hat{O}}_l\). To obtain potential detection, a technique called non-maximum suppression (NMS) [19] is employed for \({\hat{O}}_l\). The geometrical constraints are applied on these candidate detections to generate the final predictions for \({\hat{O}}_l\), which then are used to calculate desired measures