Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery

TL;DR

This paper introduces an evolutionary reinforcement learning approach integrated into a coarse-to-fine detection framework to optimize object scale detection in aerial drone imagery, addressing large scale variations effectively.

Contribution

It proposes a novel scale optimization method combining evolutionary strategies with reinforcement learning within a coarse-to-fine detection framework for drone imagery.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Achieves higher localization and label accuracy

Ensures scale consistency among neighboring objects

Abstract

Object detection in aerial imagery presents a significant challenge due to large scale variations among objects. This paper proposes an evolutionary reinforcement learning agent, integrated within a coarse-to-fine object detection framework, to optimize the scale for more effective detection of objects in such images. Specifically, a set of patches potentially containing objects are first generated. A set of rewards measuring the localization accuracy, the accuracy of predicted labels, and the scale consistency among nearby patches are designed in the agent to guide the scale optimization. The proposed scale-consistency reward ensures similar scales for neighboring objects of the same category. Furthermore, a spatial-semantic attention mechanism is designed to exploit the spatial semantic relations between patches. The agent employs the proximal policy optimization strategy in conjunction with the evolutionary strategy, effectively utilizing both the current patch status and historical experience embedded in the agent. The proposed model is compared with state-of-the-art methods on two benchmark datasets for object detection on drone imagery. It significantly outperforms all the compared methods.