Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery
This addresses the problem of accurate object detection in aerial imagery for applications like surveillance or mapping, but it is incremental as it builds on existing coarse-to-fine and reinforcement learning approaches.
The paper tackles the challenge of large scale variations in object detection on drone imagery by proposing an evolutionary reinforcement learning agent integrated into a coarse-to-fine framework to optimize scale, resulting in significant outperformance over state-of-the-art methods on two benchmark datasets.
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.