Multi-level and multi-modal feature fusion for accurate 3D object detection in Connected and Automated Vehicles
Aiming at highly accurate object detection for connected and automated vehicles (CAVs), this paper presents a Deep Neural Network based 3D object detection model that leverages a three-stage feature extractor by developing a novel LIDAR-Camera fusion scheme. The proposed feature extractor extracts high-level features from two input sensory modalities and recovers the important features discarded during the convolutional process. The novel fusion scheme effectively fuses features across sensory modalities and convolutional layers to find the best representative global features. The fused features are shared by a two-stage network: the region proposal network (RPN) and the detection head (DH). The RPN generates high-recall proposals, and the DH produces final detection results. The experimental results show the proposed model outperforms more recent research on the KITTI 2D and 3D detection benchmark, particularly for distant and highly occluded instances.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Object Detectionobject-detectionObject DetectionRegion ProposalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DNN Multimodal Fusion Techniques for Predicting Video Sentiment
We present our work on sentiment prediction using the benchmark MOSI dataset from the CMU-MultimodalDataSDK. Previous work on multimodal sentiment analysis have been focused on input-level feature fusion or decision-leve…
feature selectionMultimodal Sentiment AnalysisSentiment AnalysisMulti-Level Feature Abstraction from Convolutional Neural Networks for Multimodal Biometric Identification
In this paper, we propose a deep multimodal fusion network to fuse multiple modalities (face, iris, and fingerprint) for person identification. The proposed deep multimodal fusion algorithm consists of multiple streams o…
General ClassificationPerson IdentificationPSA-MF: Personality-Sentiment Aligned Multi-Level Fusion for Multimodal Sentiment Analysis
Multimodal sentiment analysis (MSA) is a research field that recognizes human sentiments by combining textual, visual, and audio modalities. The main challenge lies in integrating sentiment-related information from diffe…
Multimodal Sentiment AnalysisHuman Action Recognition Using Deep Multilevel Multimodal (M2) Fusion of Depth and Inertial Sensors
Multimodal fusion frameworks for Human Action Recognition (HAR) using depth and inertial sensor data have been proposed over the years. In most of the existing works, fusion is performed at a single level (feature level …
Action RecognitionTemporal Action LocalizationBM-NAS: Bilevel Multimodal Neural Architecture Search
Deep neural networks (DNNs) have shown superior performances on various multimodal learning problems. However, it often requires huge efforts to adapt DNNs to individual multimodal tasks by manually engineering unimodal …
Neural Architecture Search