Multi-view X-ray R-CNN

10/04/2018
by   Jan-Martin O. Steitz, et al.
0

Motivated by the detection of prohibited objects in carry-on luggage as a part of avionic security screening, we develop a CNN-based object detection approach for multi-view X-ray image data. Our contributions are two-fold. First, we introduce a novel multi-view pooling layer to perform a 3D aggregation of 2D CNN-features extracted from each view. To that end, our pooling layer exploits the known geometry of the imaging system to ensure geometric consistency of the feature aggregation. Second, we introduce an end-to-end trainable multi-view detection pipeline based on Faster R-CNN, which derives the region proposals and performs the final classification in 3D using these aggregated multi-view features. Our approach shows significant accuracy gains compared to single-view detection while even being more efficient than performing single-view detection in each view.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/24/2020

Multi-view adaptive graph convolutions for graph classification

In this paper, a novel multi-view methodology for graph-based neural net...
research
06/26/2022

Multi-view Feature Augmentation with Adaptive Class Activation Mapping

We propose an end-to-end-trainable feature augmentation module built for...
research
07/25/2019

Simultaneous multi-view instance detection with learned geometric soft-constraints

We propose to jointly learn multi-view geometry and warping between view...
research
08/14/2014

2D View Aggregation for Lymph Node Detection Using a Shallow Hierarchy of Linear Classifiers

Enlarged lymph nodes (LNs) can provide important information for cancer ...
research
08/31/2022

Scatter Points in Space: 3D Detection from Multi-view Monocular Images

3D object detection from monocular image(s) is a challenging and long-st...
research
12/07/2021

Voxelized 3D Feature Aggregation for Multiview Detection

Multi-view detection incorporates multiple camera views to alleviate occ...
research
08/19/2022

Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection with Attention

Improving multi-view aggregation is integral for multi-view pedestrian d...

Please sign up or login with your details

Forgot password? Click here to reset