Trajectory-Aware Adaptive Inference in Object Detection Models

TL;DR

This paper proposes an input-adaptive inference method for object detection in maritime navigation, using GPS trajectory data to dynamically adjust model complexity and improve efficiency.

Contribution

It introduces a novel early-exit mechanism in YOLOv8 that leverages motion cues for adaptive computation based on scene complexity.

Findings

Significant reduction in inference time and computational cost.

Maintains detection performance with adaptive inference.

Effective scene complexity evaluation using inter-object distances.

Abstract

The increasing integration of sensors in autonomous maritime navigation has led to large-scale multimodal datasets, raising challenges in achieving efficient real-time perception. In such systems, object detection and trajectory perception of nearby vessels are tightly coupled, particularly in dynamic environments such as maritime navigation. However, the efficiency of object detection models during inference remains an often-overlooked aspect. To this end, we build upon an existing object detection framework by incorporating GPS trajectory data into the inference process to enable input-adaptive computation. Specifically, we introduce an early-exit mechanism in a YOLOv8-based detector that incorporates motion cues - such as inter-vessel distances. Frames of vessels that are separated by short distances, converging with high speed, are processed using the full model, while only a subset of the network's architecture is activated otherwise. The difficulty degree (or scene complexity) of a frame or set of frames per second is evaluated by leveraging inter-object distance and the rate at which the distance between them decreases. Experimental results demonstrate that this strategy maintains satisfactory detection performance while significantly reducing inference time and computational cost, thus enabling a flexible trade-off between accuracy and efficiency compared to full-model inference.