Abstract
Abstract. In this paper, we propose a new framework for segmenting feature-based moving objects under affine subspace model. Since the feature trajectories in practice are high-dimensional and contain a lot of noise, we firstly apply the sparse PCA to represent the original trajectories with a low-dimensional global subspace, which consists of the orthogonal sparse principal vectors. Subsequently, the local subspace separation will be achieved via automatically searching the sparse representation of the nearest neighbors for each projected data. In order to refine the local subspace estimation result, we propose an error estimation to encourage the projected data that span a same local subspace to be clustered together. In the end, the segmentation of different motions is achieved through the spectral clustering on an affinity matrix, which is constructed with both the error estimation and sparse neighbors optimization. We test our method extensively and compare it with state-of-the-art methods on the Hopkins 155 dataset. The results show that our method is comparable with the other motion segmentation methods, and in many cases exceed them in terms of precision and computation time.
Highlights
In the past years, dynamic scenes understanding has been receiving increasing attention especially on the moving camera or multiple moving objects
We seek a sparse representation for the nearest neighbors in the global subspace for each data point that span a same local subspace
Our proposed framework is evaluated on the Hopkins 155 dataset (Tron and Vidal, 2007) with comparing with state-of-the-art subspace clustering and affinity-based motion segmentation algorithms
Summary
Dynamic scenes understanding has been receiving increasing attention especially on the moving camera or multiple moving objects. In case of feature extraction for all the moving objects from the video, segmentation of different motions is equivalent to segment the extracted feature trajectories into different clusters. The algorithms of motion segmentation are classified into 2 categories (Dragon et al, 2012): affinity-based methods and subspace-based methods. The affinity-based methods focus on computing the correspondences of each pair of the trajectories, whereas the subspace-based approaches use multiple subspaces to model the multiple moving objects in the video and the segmentation of different motions is accomplished through subspace clustering. There is an intense demand to explore a new subspace-base algorithm that can segment multiple kinds of motions and handle the missing and corrupted trajectories from the real video
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
