Efficient ConvNet Feature Extraction with Multiple RoI Pooling for Landmark-Based Visual Localization of Autonomous Vehicles

Figure 2

Illustration of our proposed ConvNet feature extraction method with multiple RoI pooling (MRoI). For ease of understanding, we show in (a) the existing feature map-based methods which directly use the Fast R-CNN [20] to extract ConvNet features. In addition, we also show the principle of a RoI pooling layer in (b). Our method is illustrated in (c). Obviously, our method is very simple because it only needs to add two extra RoI pooling layers (i.e., and ) behind the Conv3 and Conv4 layers. Note that “” represents the vectorized RoI pooling features from the corresponding RoI pooling layer. For the purpose of feature fusion, is first - and then concatenated (). The final output ConvNet features of Fast R-CNN and our method are denoted as “” and “,” respectively. For clarity, we present only three of the bounding boxes (BBs) detected within an image.