BMFN3D: Bidirectional multilayer fusion network for indoor 3D object detection
Authors:
Open Access
- 11 July 2022
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 58 (18) , 696-698
Abstract
Among various indoor 3D object detection methods, one of which is based on 3D convolution. However, in current 3D convolutional method for indoor 3D object detection, feature fusion is only implemented in a single direction and adjacent layer, which leads to the feature loss during feature propagation and weakens the detection performance. To solve the above problem, a bidirectional multilayer fusion network (BMFN) is proposed to enrich features for prediction. Furthermore, we propose a new network based on BMFN for 3D object detection, BMFN3D. In BMFN3D, the channel and spatial attention mechanisms are introduced into the backbone and head of detection network, so as to enhance the selection of effective feature information. Finally, a new calculation method for regression loss is proposed with the consideration of the 3D spatial information. We validate our method with two indoor datasets of SUN RGB‐D and ScanNet, and achieve state‐of‐the‐art results.Keywords
Funding Information
- National Natural Science Foundation of China (U1713213, U1913202, U1813205)
This publication has 19 references indexed in Scilit:
- Generative Sparse Detection Networks for 3D Single-Shot Object Detection2020
- H3DNet: 3D Object Detection Using Hybrid Geometric Primitives2020
- MLCVNet: Multi-Level Context VoteNet for 3D Object Detection2020
- Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection2020
- 3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance Segmentation2020
- MMFNet: A multi-modality MRI fusion network for segmentation of nasopharyngeal carcinomaNeurocomputing, 2020
- Distance-IoU Loss: Faster and Better Learning for Bounding Box RegressionProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Deep Hough Voting for 3D Object Detection in Point Clouds2019
- IoU Loss for 2D/3D Object Detection2019
- 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks2019