FMODetect: Robust Detection of Fast Moving Objects
This work addresses the problem of real-time detection of fast-moving, highly blurred objects for applications such as video surveillance and retrieval, providing significant speed improvements over existing methods.
This paper introduces the first learning-based method, FMODetect, for detecting fast-moving objects in video frames, which are typically highly blurred. By separating the deblatting problem into consecutive matting and deblurring steps, the method achieves an order of magnitude speed-up, enabling real-time performance and outperforming state-of-the-art methods in recall, precision, trajectory estimation, and sharp appearance reconstruction.
We propose the first learning-based approach for fast moving objects detection. Such objects are highly blurred and move over large distances within one video frame. Fast moving objects are associated with a deblurring and matting problem, also called deblatting. We show that the separation of deblatting into consecutive matting and deblurring allows achieving real-time performance, i.e. an order of magnitude speed-up, and thus enabling new classes of application. The proposed method detects fast moving objects as a truncated distance function to the trajectory by learning from synthetic data. For the sharp appearance estimation and accurate trajectory estimation, we propose a matting and fitting network that estimates the blurred appearance without background, followed by an energy minimization based deblurring. The state-of-the-art methods are outperformed in terms of recall, precision, trajectory estimation, and sharp appearance reconstruction. Compared to other methods, such as deblatting, the inference is of several orders of magnitude faster and allows applications such as real-time fast moving object detection and retrieval in large video collections.