FMODetect: Robust Detection of Fast Moving Objects

TL;DR

FMODetect introduces a real-time, learning-based method for detecting fast moving objects in videos, effectively handling blurring and large displacements, outperforming existing techniques in speed and accuracy.

Contribution

The paper presents the first learning-based approach that separates deblatting into matting and deblurring, enabling real-time detection of fast moving objects.

Findings

Outperforms state-of-the-art in recall, precision, and trajectory estimation

Achieves an order of magnitude speed-up over existing methods

Enables real-time detection and retrieval in large video collections

Abstract

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.