Object recognition in atmospheric turbulence scenes
This addresses the problem of degraded surveillance imagery for security and monitoring applications, though it is incremental as it adapts existing deep learning methods to a specific challenge.
The paper tackles object recognition in atmospheric turbulence scenes by proposing a framework that learns distorted features, achieving over 30% mAP on a synthetic VOC dataset and showing improved performance on real data.
The influence of atmospheric turbulence on acquired surveillance imagery poses significant challenges in image interpretation and scene analysis. Conventional approaches for target classification and tracking are less effective under such conditions. While deep-learning-based object detection methods have shown great success in normal conditions, they cannot be directly applied to atmospheric turbulence sequences. In this paper, we propose a novel framework that learns distorted features to detect and classify object types in turbulent environments. Specifically, we utilise deformable convolutions to handle spatial turbulent displacement. Features are extracted using a feature pyramid network, and Faster R-CNN is employed as the object detector. Experimental results on a synthetic VOC dataset demonstrate that the proposed framework outperforms the benchmark with a mean Average Precision (mAP) score exceeding 30%. Additionally, subjective results on real data show significant improvement in performance.