In this paper, we tackle the problem of temporally consistent boundary detection and hierarchical segmentation in videos. While finding the best high-level reasoning of region assignments in videos is the focus of much recent research, temporal consistency in boundary detection has so far only rarely been tackled. We argue that temporally consistent boundaries are a key component to temporally consistent region assignment. The proposed method is based on the point-wise mutual information (PMI) of spatio-temporal voxels. Temporal consistency is established by an evaluation of PMI-based point affinities in the spectral domain over space and time. Thus, the proposed method is independent of any optical flow computation or previously learned motion models. The proposed low-level video segmentation method outperforms the learning-based state of the art in terms of standard region metrics.
Deep convolutional neural networks (CNNs) have been immensely successful in many high-level computer vision tasks given large labeled datasets. However, for video semantic object segmentation, a domain where labels are scarce, effectively exploiting the representation power of CNN with limited training data remains a challenge. Simply borrowing the existing pretrained CNN image recognition model for video segmentation task can severely hurt performance. We propose a semi-supervised approach to adapting CNN image recognition model trained from labeled image data to the target domain exploiting both semantic evidence learned from CNN, and the intrinsic structures of video data. By explicitly modeling and compensating for the domain shift from the source domain to the target domain, this proposed approach underpins a robust semantic object segmentation method against the changes in appearance, shape and occlusion in natural videos. We present extensive experiments on challenging datasets that demonstrate the superior performance of our approach compared with the state-of-the-art methods.
Common users have changed from mere consumers to active producers of multimedia data content. Video editing plays an important role in this scenario, calling for simple segmentation tools that can handle fast-moving and deformable video objects with possible occlusions, color similarities with the background, among other challenges. We present an interactive video segmentation method, named FOMTrace, which addresses the problem in an effective and efficient way. From a user-provided object mask in a first frame, the method performs semi-automatic video segmentation on a spatiotemporal superpixel-graph, and then estimates a Fuzzy Object Model (FOM), which refines segmentation of the second frame by constraining delineation on a pixel-graph within a region where the object's boundary is expected to be. The user can correct/accept the refined object mask in the second frame, which is then similarly used to improve the spatiotemporal video segmentation of the remaining frames. Both steps are repeated alternately, within interactive response times, until the segmentation refinement of the final frame is accepted by the user. Extensive experiments demonstrate FOMTrace's ability for tracing objects in comparison with state-of-the-art approaches for interactive video segmentation, supervised, and unsupervised object tracking.
This paper formulates and presents a solution to the new problem of budgeted semantic video segmentation. Given a video, the goal is to accurately assign a semantic class label to every pixel in the video within a specified time budget. Typical approaches to such labeling problems, such as Conditional Random Fields (CRFs), focus on maximizing accuracy but do not provide a principled method for satisfying a time budget. For video data, the time required by CRF and related methods is often dominated by the time to compute low-level descriptors of supervoxels across the video. Our key contribution is the new budgeted inference framework for CRF models that intelligently selects the most useful subsets of descriptors to run on subsets of supervoxels within the time budget. The objective is to maintain an accuracy as close as possible to the CRF model with no time bound, while remaining within the time budget. Our second contribution is the algorithm for learning a policy for the sparse selection of supervoxels and their descriptors for budgeted CRF inference. This learning algorithm is derived by casting our problem in the framework of Markov Decision Processes, and then instantiating a state-of-the-art policy learning algorithm known as Classification-Based Approximate Policy Iteration. Our experiments on multiple video datasets show that our learning approach and framework is able to significantly reduce computation time, and maintain competitive accuracy under varying budgets.
We present an approach for object segmentation in videos that combines frame-level object detection with concepts from object tracking and motion segmentation. The approach extracts temporally consistent object tubes based on an off-the-shelf detector. Besides the class label for each tube, this provides a location prior that is independent of motion. For the final video segmentation, we combine this information with motion cues. The method overcomes the typical problems of weakly supervised/unsupervised video segmentation, such as scenes with no motion, dominant camera motion, and objects that move as a unit. In contrast to most tracking methods, it provides an accurate, temporally consistent segmentation of each object. We report results on four video segmentation datasets: YouTube Objects, SegTrackv2, egoMotion, and FBMS.
This paper presents a novel method to involve both spatial and temporal features for semantic video segmentation. Current work on convolutional neural networks(CNNs) has shown that CNNs provide advanced spatial features supporting a very good performance of solutions for both image and video analysis, especially for the semantic segmentation task. We investigate how involving temporal features also has a good effect on segmenting video data. We propose a module based on a long short-term memory (LSTM) architecture of a recurrent neural network for interpreting the temporal characteristics of video frames over time. Our system takes as input frames of a video and produces a correspondingly-sized output; for segmenting the video our method combines the use of three components: First, the regional spatial features of frames are extracted using a CNN; then, using LSTM the temporal features are added; finally, by deconvolving the spatio-temporal features we produce pixel-wise predictions. Our key insight is to build spatio-temporal convolutional networks (spatio-temporal CNNs) that have an end-to-end architecture for semantic video segmentation. We adapted fully some known convolutional network architectures (such as FCN-AlexNet and FCN-VGG16), and dilated convolution into our spatio-temporal CNNs. Our spatio-temporal CNNs achieve state-of-the-art semantic segmentation, as demonstrated for the Camvid and NYUDv2 datasets.
Are we ready to segment consumer stereo videos? The amount of this data type is rapidly increasing and encompasses rich information of appearance, motion and depth cues. However, the segmentation of such data is still largely unexplored. First, we propose therefore a new benchmark: videos, annotations and metrics to measure progress on this emerging challenge. Second, we evaluate several state of the art segmentation methods and propose a novel ensemble method based on recent spectral theory. This combines existing image and video segmentation techniques in an efficient scheme. Finally, we propose and integrate into this model a novel regressor, learnt to optimize the stereo segmentation performance directly via a differentiable proxy. The regressor makes our segmentation ensemble adaptive to each stereo video and outperforms the segmentations of the ensemble as well as a most recent RGB-D segmentation technique.
For state-of-the-art semantic segmentation task, training convolutional neural networks (CNNs) requires dense pixelwise ground truth (GT) labeling, which is expensive and involves extensive human effort. In this work, we study the possibility of using auxiliary ground truth, so-called \textit{pseudo ground truth} (PGT) to improve the performance. The PGT is obtained by propagating the labels of a GT frame to its subsequent frames in the video using a simple CRF-based, cue integration framework. Our main contribution is to demonstrate the use of noisy PGT along with GT to improve the performance of a CNN. We perform a systematic analysis to find the right kind of PGT that needs to be added along with the GT for training a CNN. In this regard, we explore three aspects of PGT which influence the learning of a CNN: i) the PGT labeling has to be of good quality; ii) the PGT images have to be different compared to the GT images; iii) the PGT has to be trusted differently than GT. We conclude that PGT which is diverse from GT images and has good quality of labeling can indeed help improve the performance of a CNN. Also, when PGT is multiple folds larger than GT, weighing down the trust on PGT helps in improving the accuracy. Finally, We show that using PGT along with GT, the performance of Fully Convolutional Network (FCN) on Camvid data is increased by $2.7\%$ on IoU accuracy. We believe such an approach can be used to train CNNs for semantic video segmentation where sequentially labeled image frames are needed. To this end, we provide recommendations for using PGT strategically for semantic segmentation and hence bypass the need for extensive human efforts in labeling.
Image segmentation is an important step in most visual tasks. While convolutional neural networks have shown to perform well on single image segmentation, to our knowledge, no study has been been done on leveraging recurrent gated architectures for video segmentation. Accordingly, we propose a novel method for online segmentation of video sequences that incorporates temporal data. The network is built from fully convolutional element and recurrent unit that works on a sliding window over the temporal data. We also introduce a novel convolutional gated recurrent unit that preserves the spatial information and reduces the parameters learned. Our method has the advantage that it can work in an online fashion instead of operating over the whole input batch of video frames. The network is tested on the change detection dataset, and proved to have 5.5\% improvement in F-measure over a plain fully convolutional network for per frame segmentation. It was also shown to have improvement of 1.4\% for the F-measure compared to our baseline network that we call FCN 12s.
Semantic segmentation has recently witnessed major progress, where fully convolutional neural networks have shown to perform well. However, most of the previous work focused on improving single image segmentation. To our knowledge, no prior work has made use of temporal video information in a recurrent network. In this paper, we introduce a novel approach to implicitly utilize temporal data in videos for online semantic segmentation. The method relies on a fully convolutional network that is embedded into a gated recurrent architecture. This design receives a sequence of consecutive video frames and outputs the segmentation of the last frame. Convolutional gated recurrent networks are used for the recurrent part to preserve spatial connectivities in the image. Our proposed method can be applied in both online and batch segmentation. This architecture is tested for both binary and semantic video segmentation tasks. Experiments are conducted on the recent benchmarks in SegTrack V2, Davis, CityScapes, and Synthia. Using recurrent fully convolutional networks improved the baseline network performance in all of our experiments. Namely, 5% and 3% improvement of F-measure in SegTrack2 and Davis respectively, 5.7% improvement in mean IoU in Synthia and 3.5% improvement in categorical mean IoU in CityScapes. The performance of the RFCN network depends on its baseline fully convolutional network. Thus RFCN architecture can be seen as a method to improve its baseline segmentation network by exploiting spatiotemporal information in videos.
Graph-based video segmentation methods rely on superpixels as starting point. While most previous work has focused on the construction of the graph edges and weights as well as solving the graph partitioning problem, this paper focuses on better superpixels for video segmentation. We demonstrate by a comparative analysis that superpixels extracted from boundaries perform best, and show that boundary estimation can be significantly improved via image and time domain cues. With superpixels generated from our better boundaries we observe consistent improvement for two video segmentation methods in two different datasets.
Video object segmentation is challenging due to the factors like rapidly fast motion, cluttered backgrounds, arbitrary object appearance variation and shape deformation. Most existing methods only explore appearance information between two consecutive frames, which do not make full use of the usefully long-term nonlocal information that is helpful to make the learned appearance stable, and hence they tend to fail when the targets suffer from large viewpoint changes and significant non-rigid deformations. In this paper, we propose a simple yet effective approach to mine the long-term sptatio-temporally nonlocal appearance information for unsupervised video segmentation. The motivation of our algorithm comes from the spatio-temporal nonlocality of the region appearance reoccurrence in a video. Specifically, we first generate a set of superpixels to represent the foreground and background, and then update the appearance of each superpixel with its long-term sptatio-temporally nonlocal counterparts generated by the approximate nearest neighbor search method with the efficient KD-tree algorithm. Then, with the updated appearances, we formulate a spatio-temporal graphical model comprised of the superpixel label consistency potentials. Finally, we generate the segmentation by optimizing the graphical model via iteratively updating the appearance model and estimating the labels. Extensive evaluations on the SegTrack and Youtube-Objects datasets demonstrate the effectiveness of the proposed method, which performs favorably against some state-of-art methods.
Encoding time-series with Linear Dynamical Systems (LDSs) leads to rich models with applications ranging from dynamical texture recognition to video segmentation to name a few. In this paper, we propose to represent LDSs with infinite-dimensional subspaces and derive an analytic solution to obtain stable LDSs. We then devise efficient algorithms to perform sparse coding and dictionary learning on the space of infinite-dimensional subspaces. In particular, two solutions are developed to sparsely encode an LDS. In the first method, we map the subspaces into a Reproducing Kernel Hilbert Space (RKHS) and achieve our goal through kernel sparse coding. As for the second solution, we propose to embed the infinite-dimensional subspaces into the space of symmetric matrices and formulate the sparse coding accordingly in the induced space. For dictionary learning, we encode time-series by introducing a novel concept, namely the two-fold LDSs. We then make use of the two-fold LDSs to derive an analytical form for updating atoms of an LDS dictionary, i.e., each atom is an LDS itself. Compared to several baselines and state-of-the-art methods, the proposed methods yield higher accuracies in various classification tasks including video classification and tactile recognition.
This paper proposes a geodesic-distance-based feature that encodes global information for improved video segmentation algorithms. The feature is a joint histogram of intensity and geodesic distances, where the geodesic distances are computed as the shortest paths between superpixels via their boundaries. We also incorporate adaptive voting weights and spatial pyramid configurations to include spatial information into the geodesic histogram feature and show that this further improves results. The feature is generic and can be used as part of various algorithms. In experiments, we test the geodesic histogram feature by incorporating it into two existing video segmentation frameworks. This leads to significantly better performance in 3D video segmentation benchmarks on two datasets.
In this paper, we present a new method for egocentric video temporal segmentation based on integrating a statistical mean change detector and agglomerative clustering(AC) within an energy-minimization framework. Given the tendency of most AC methods to oversegment video sequences when clustering their frames, we combine the clustering with a concept drift detection technique (ADWIN) that has rigorous guarantee of performances. ADWIN serves as a statistical upper bound for the clustering-based video segmentation. We integrate both techniques in an energy-minimization framework that serves to disambiguate the decision of both techniques and to complete the segmentation taking into account the temporal continuity of video frames descriptors. We present experiments over egocentric sets of more than 13.000 images acquired with different wearable cameras, showing that our method outperforms state-of-the-art clustering methods.
We propose a technique that propagates information forward through video data. The method is conceptually simple and can be applied to tasks that require the propagation of structured information, such as semantic labels, based on video content. We propose a 'Video Propagation Network' that processes video frames in an adaptive manner. The model is applied online: it propagates information forward without the need to access future frames. In particular we combine two components, a temporal bilateral network for dense and video adaptive filtering, followed by a spatial network to refine features and increased flexibility. We present experiments on video object segmentation and semantic video segmentation and show increased performance comparing to the best previous task-specific methods, while having favorable runtime. Additionally we demonstrate our approach on an example regression task of color propagation in a grayscale video.
We propose an end-to-end learning framework for segmenting generic objects in videos. Our method learns to combine appearance and motion information to produce pixel level segmentation masks for all prominent objects in videos. We formulate this task as a structured prediction problem and design a two-stream fully convolutional neural network which fuses together motion and appearance in a unified framework. Since large-scale video datasets with pixel level segmentations are problematic, we show how to bootstrap weakly annotated videos together with existing image recognition datasets for training. Through experiments on three challenging video segmentation benchmarks, our method substantially improves the state-of-the-art for segmenting generic (unseen) objects. Code and pre-trained models are available on the project website.
This paper tackles the task of semi-supervised video object segmentation, i.e., the separation of an object from the background in a video, given the mask of the first frame. We present One-Shot Video Object Segmentation (OSVOS), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one-shot). Although all frames are processed independently, the results are temporally coherent and stable. We perform experiments on two annotated video segmentation databases, which show that OSVOS is fast and improves the state of the art by a significant margin (79.8% vs 68.0%).
We in this paper solve the problem of high-quality automatic real-time background cut for 720p portrait videos. We first handle the background ambiguity issue in semantic segmentation by proposing a global background attenuation model. A spatial-temporal refinement network is developed to further refine the segmentation errors in each frame and ensure temporal coherence in the segmentation map. We form an end-to-end network for training and testing. Each module is designed considering efficiency and accuracy. We build a portrait dataset, which includes 8,000 images with high-quality labeled map for training and testing. To further improve the performance, we build a portrait video dataset with 50 sequences to fine-tune video segmentation. Our framework benefits many video processing applications.
We introduce a novel semi-supervised video segmentation approach based on an efficient video representation, called as "super-trajectory". Each super-trajectory corresponds to a group of compact trajectories that exhibit consistent motion patterns, similar appearance and close spatiotemporal relationships. We generate trajectories using a probabilistic model, which handles occlusions and drifts in a robust and natural way. To reliably group trajectories, we adopt a modified version of the density peaks based clustering algorithm that allows capturing rich spatiotemporal relations among trajectories in the clustering process. The presented video representation is discriminative enough to accurately propagate the initial annotations in the first frame onto the remaining video frames. Extensive experimental analysis on challenging benchmarks demonstrate our method is capable of distinguishing the target objects from complex backgrounds and even reidentifying them after long-term occlusions.