Towards Efficient 3D Object Detection for Vehicle-Infrastructure Collaboration via Risk-Intent Selection

TL;DR

RiSe addresses the bandwidth–accuracy conflict in vehicle–infrastructure collaboration by shifting from visibility-based filtering to risk-intent-based feature transmission. It combines a Potential Field-Trajectory Correlation Model (PTCM) to quantify trajectory-level interaction risk with an Intention-Driven Area Prediction Module (IDAPM) that uses ego-motion priors to predict driving-task–relevant BEV regions, enabling semantic-selective fusion. On the DeepAccident dataset, RiSe achieves a strong Pareto frontier, reducing communication to $0.71\%$ of full transmission while maintaining state-of-the-art detection for safety-critical objects, aided by a Rescale Focal Loss that improves high-risk region localization. These results highlight practical benefits for planning-oriented collaborative perception and point to future extensions in multi-modal fusion, asynchronous communication, and privacy-preserving data sharing.

Abstract

Vehicle-Infrastructure Collaborative Perception (VICP) is pivotal for resolving occlusion in autonomous driving, yet the trade-off between communication bandwidth and feature redundancy remains a critical bottleneck. While intermediate fusion mitigates data volume compared to raw sharing, existing frameworks typically rely on spatial compression or static confidence maps, which inefficiently transmit spatially redundant features from non-critical background regions. To address this, we propose Risk-intent Selective detection (RiSe), an interaction-aware framework that shifts the paradigm from identifying visible regions to prioritizing risk-critical ones. Specifically, we introduce a Potential Field-Trajectory Correlation Model (PTCM) grounded in potential field theory to quantitatively assess kinematic risks. Complementing this, an Intention-Driven Area Prediction Module (IDAPM) leverages ego-motion priors to proactively predict and filter key Bird's-Eye-View (BEV) areas essential for decision-making. By integrating these components, RiSe implements a semantic-selective fusion scheme that transmits high-fidelity features only from high-interaction regions, effectively acting as a feature denoiser. Extensive experiments on the DeepAccident dataset demonstrate that our method reduces communication volume to 0.71\% of full feature sharing while maintaining state-of-the-art detection accuracy, establishing a competitive Pareto frontier between bandwidth efficiency and perception performance.

Figures (5)

• Figure 1: The core motivation and evolution of the proposed RiSe framework. (a) Evolution of collaborative perception: moving from bandwidth-limited compression and static filtering to our proposed interaction-driven paradigm that utilizes risk fields. (b) Motivation scenario: leveraging the ego-vehicle's driving intent to identify the Critical Interaction Zone, allowing the infrastructure to prioritize high-risk targets (red) over irrelevant ones (blue) to optimize bandwidth efficiency.
• Figure 2: The Overall Architecture of RiSe Framework. Guided by the ego-vehicle's driving intent, the infrastructure utilizes the PTCM and IDAPM to collaboratively generate a correlation heatmap. This heatmap serves as a spatial filter to selectively transmit only high-relevance feature blocks, which are subsequently integrated by the Fusion Module for interaction-aware 3D object detection.
• Figure 3: Detailed Architecture of the Intention-Driven Area Prediction Module. The module encodes motion dynamics by extracting four feature components: Segmentation, Centerness, Offset, and Motion Flow. These components are processed by a CNN to generate motion features, which are subsequently fused with the original BEV features to predict the intention-driven relevance heatmap.
• Figure 4: BEV Visualization of 3D Object Detection. The first image indicates a 3D object detection result without collaborative communication. The middle shows the result from the Where2comm method. The last shows the 3D detection result with the method proposed in this paper.
• Figure 5: Visualization of Intention-Aware Correlation Prediction. The top row displays the ground truth heatmaps, while the bottom row presents the predicted results. The color spectrum represents the relevance score: warmer colors indicate high correlation and interaction risk, whereas cooler colors denote low-relevance regions. The figure demonstrates that the infrastructure system can accurately predict correlations based on vehicle intentions and interaction risks.