Incrementally Detecting Moving Objects in Video with Sparsity and Connectivity

Moving object detection is crucial for cognitive vision-based robot tasks. However, due to noise, dynamic background, variations in illumination, and high frame rate, it is a challenging task to robustly and efficiently detect moving objects in video using the clue of motion. State-of-the-art batch-based methods view a sequence of images as a whole and then model the background and foreground together with the constraints of foreground sparsity and connectivity (smoothness) in a unified framework. But the efficiency of the batch-based methods is very low. State-of-the-art incremental methods model the background by a subspace whose bases are updated frame by frame. However, such incremental methods do not make full use of the foreground sparsity and connectivity. In this paper, we develop an incremental method for detecting moving objects in video. Compared to existing methods, the proposed method not only incrementally models the subspace for background reconstruction but also takes into account the sparsity and connectivity of the foreground. The optimization of the model is very efficient. Experimental results on nine public videos demonstrate that the proposed method is much efficient than the state-of-the-art batch methods and has higher F1-score than the state-of-the-art incremental methods.