Improved Handling of Motion Blur in Online Object Detection
This research provides practical improvements for online object detection systems operating in real-world scenarios, particularly for applications involving cameras in motion (e.g., cars, handheld phones), by specifically tackling motion blur.
This paper addresses the challenge of object detection in the presence of egomotion-induced motion blur, a common issue in real-world online vision systems. The authors found that custom label generation, specifically designed to resolve spatial ambiguity, significantly improved object detection performance. Additionally, conditioning the model on bespoke categories of motion blur provided a noteworthy boost, contrasting with findings in classification tasks.
We wish to detect specific categories of objects, for online vision systems that will run in the real world. Object detection is already very challenging. It is even harder when the images are blurred, from the camera being in a car or a hand-held phone. Most existing efforts either focused on sharp images, with easy to label ground truth, or they have treated motion blur as one of many generic corruptions. Instead, we focus especially on the details of egomotion induced blur. We explore five classes of remedies, where each targets different potential causes for the performance gap between sharp and blurred images. For example, first deblurring an image changes its human interpretability, but at present, only partly improves object detection. The other four classes of remedies address multi-scale texture, out-of-distribution testing, label generation, and conditioning by blur-type. Surprisingly, we discover that custom label generation aimed at resolving spatial ambiguity, ahead of all others, markedly improves object detection. Also, in contrast to findings from classification, we see a noteworthy boost by conditioning our model on bespoke categories of motion blur. We validate and cross-breed the different remedies experimentally on blurred COCO images and real-world blur datasets, producing an easy and practical favorite model with superior detection rates.