Skip to content

3D Dynamic Object Detection with Multi-Modal Temporal Fusion

Sep 2026 · SAE technical paper series · 0 citations · 1 references

TL;DR

This research proposes a novel framework that enhances the BEV representation with temporal modeling, and effectively enhances 3D detection accuracy in dynamic scenarios.

Abstract

This research aims to address the critical challenge of accurately detecting and estimating the state of dynamic objects in autonomous driving. Traditional 3D object detection methods often struggle with motion perception, particularly in velocity estimation, due to the lack of information in single frame perception. We propose a novel framework that enhances the BEV representation with temporal modeling. The core of our method is a two-stage temporal fusion process. First, we align historical BEV features to the current coordinate frame to eliminate the interference of ego-motion. Subsequently, a dedicated temporal fusion encoder, architected with residual connections and a Feature Pyramid Network, refines the aligned multi-frame BEV features to capture complex motion patterns and improve multi-scale object representation. This approach directly tackles the problem of motion decoupling. By aligning features, we disentangle object motion from ego-motion. The temporal fusion encoder then mitigates the positional ambiguity of moving objects in the fused BEV space, a common issue in simple feature concatenation, leading to more robust detection. We built a dataset following the structure of the nuScenes dataset, using data collected from an autonomous driving simulation platform. The evaluation results on our simulation dataset demonstrate that the proposed temporal module achieves a 13.0% improvement in NDS score and a substantial 29.7% reduction in velocity error (mAVE). These results demonstrate that our temporal fusion strategy effectively enhances 3D detection accuracy in dynamic scenarios.

View source

Similar papers

Open access Sep 2026

Ego-Motion-Aware Temporal Fusion in BEV Space for Multi-Modal 3D Object Detection

Multi-modal 3D object detection is critical for autonomous driving perception. While Bird’s Eye View (BEV) fusion methods effectively integrate LiDAR and camera features, they primarily focus on single-frame fusion and neglect temporal context. We propose CamT-BEV, a camera-temporal-enhanced BEV fusion framework for im...

Na Zhang, Edmundo Guerra, A. Grau · 0 citations
Open access 2026

Encoder-Level Temporal Fusion Transformers for Robust Multi-Object Tracking

Experiments on three challenging benchmarks show that GTF improves identity association and overall tracking robustness, particularly under fast motion, appearance ambiguity, and frequent occlusions, and ablation studies further support the roles of encoder-level temporal fusion, adaptive gating, entropy regularization...

Jinho Kim, Kuk-Jin Yoon · 0 citations
Open access Aug 2026

TraTeTrack: historical trajectory-guided temporal modeling for visual object tracking

The core innovation of TraTeTrack is to introduce historical trajectory guidance into the conventional template-search image-pair tracking framework instead of replacing visual image pairs, and the proposed trajectory branch complements them by modeling low-dimensional historical bounding-box sequences.

Yong Tao, Haibin Wang, Jing-Lin Ma et al. · 0 citations
Conference Aug 2026

PrismTrack: Perspective-Aware Multi-Cue Association for Robust Multi-Object Tracking

Multi-Object Tracking (MOT) remains challenging due to object occlusion, complex motions, and detection unreliability in crowded scenarios. We propose an enhanced MOT framework integrating and optimizing state-of-the-art components, specifically Improved Detection Confidence Boost (IDCBoost) and Track-Perspective-Based...

Trung Nghia Huynh, Chi Nhan Huynh, Jia-Ching Wang et al. · 0 citations
Sep 2026

A multiobject tracking method based on dynamic adaptation and collaborative enhancement

A new MOT approach focused on dynamic adaptation and collaborative enhancement consisting of a nonlinear adaptive kalman filter that makes adjustments in object states for detecting anomalous motions and a multi-dimensional feature enhancement network that elaborates on appearance-enhancing exploration accumulations ac...

Yuan-Zhe Ji, Ying Guo, Ze-Yu Liu et al. · 0 citations
2026

EDAFusion: LiDAR-Guided Multilevel Depth Enhancement and Dynamic Scale Attention Fusion for Multimodal 3-D Object Detection

Three-dimensional object detection plays a critical role in intelligent robotics and autonomous driving, where accurate and robust perception remains challenging under multimodal fusion settings. Existing bird’s-eye-view (BEV)-based multimodal methods still suffer from unreliable camera depth estimation, insufficient a...

Jian-Qiang Su, Ji-Yuan Wang, Yong-Sheng Qi et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.