skip to main content


Title: An Efficient 3D CNN for Action/Object Segmentation in Video
Convolutional Neural Network (CNN) based image segmentation has made great progress in recent years. However, video object segmentation remains a challenging task due to its high computational complexity. Most of the previous methods employ a two-stream CNN framework to handle spatial and motion features separately. In this paper, we propose an end-to-end encoder-decoder style 3D CNN to aggregate spatial and temporal information simultaneously for video object segmentation. To efficiently process video, we propose 3D separable convolution for the pyramid pooling module and decoder, which dramatically reduces the number of operations while maintaining the performance. Moreover, we also extend our framework to video action segmentation by adding an extra classifier to predict the action label for actors in videos. Extensive experiments on several video datasets demonstrate the superior performance of the proposed approach for action and object segmentation compared to the state-of-the-art.  more » « less
Award ID(s):
1741431
NSF-PAR ID:
10203912
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
British Machine Vision Conference 2019
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    The task of instance segmentation in videos aims to consistently identify objects at pixel level throughout the entire video sequence. Existing state-of-the-art methods either follow the tracking-bydetection paradigm to employ multi-stage pipelines or directly train a complex deep model to process the entire video clips as 3D volumes. However, these methods are typically slow and resourceconsuming such that they are often limited to offline processing. In this paper, we propose SRNet, a simple and efficient framework for joint segmentation and tracking of object instances in videos. The key to achieving both high efficiency and accuracy in our framework is to formulate the instance segmentation and tracking problem into a unified spatial-relation learning task where each pixel in the current frame relates to its object center, and each object center relates to its location in the previous frame. This unified learning framework allows our framework to perform join instance segmentation and tracking through a single stage while maintaining low overheads among different learning tasks. Our proposed framework can handle two different task settings and demonstrates comparable performance with state-of-the-art methods on two different benchmarks while running significantly faster. 
    more » « less
  2. As one of the popular deep learning methods, deep convolutional neural networks (DCNNs) have been widely adopted in segmentation tasks and have received positive feedback. However, in segmentation tasks, DCNN-based frameworks are known for their incompetence in dealing with global relations within imaging features. Although several techniques have been proposed to enhance the global reasoning of DCNN, these models are either not able to gain satisfying performances compared with traditional fully-convolutional structures or not capable of utilizing the basic advantages of CNN-based networks (namely the ability of local reasoning). In this study, compared with current attempts to combine FCNs and global reasoning methods, we fully extracted the ability of self-attention by designing a novel attention mechanism for 3D computation and proposed a new segmentation framework (named 3DTU) for three-dimensional medical image segmentation tasks. This new framework processes images in an end-to-end manner and executes 3D computation on both the encoder side (which contains a 3D transformer) and the decoder side (which is based on a 3D DCNN). We tested our framework on two independent datasets that consist of 3D MRI and CT images. Experimental results clearly demonstrate that our method outperforms several state-of-the-art segmentation methods in various metrics. 
    more » « less
  3. null (Ed.)
    Material and biological sciences frequently generate large amounts of microscope data that require 3D object level segmentation. Often, the objects of interest have a common geometry, for example spherical, ellipsoidal, or cylindrical shapes. Neural networks have became a popular approach for object detection but they are often limited by their training dataset and have difficulties adapting to new data. In this paper, we propose a volumetric object detection approach for microscopy volumes comprised of fibrous structures by using deep centroid regression and geometric regularization. To this end, we train encoder-decoder networks for segmentation and centroid regression. We use the regression information combined with prior system knowledge to propose cylindrical objects and enforce geometric regularization in the segmentation. We train our networks on synthetic data and then test the trained networks in several experimental datasets. Our approach shows competitive results against other 3D segmentation methods when tested on the synthetic data and outperforms those other methods across different datasets. 
    more » « less
  4. null (Ed.)
    We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds. The two non-trivial challenges posed by this multi-scan multibody setting that we investigate are: (i) guaranteeing correspondence and segmentation consistency across multiple input point clouds capturing different spatial arrangements of bodies or body parts; and (ii) obtaining robust motion-based rigid body segmentation applicable to novel object categories. We propose an approach to address these issues that incorporates spectral synchronization into an iterative deep declarative network, so as to simultaneously recover consistent correspondences as well as motion segmentation. At the same time, by explicitly disentangling the correspondence and motion segmentation estimation modules, we achieve strong generalizability across different object categories. Our extensive evaluations demonstrate that our method is effective on various datasets ranging from rigid parts in articulated objects to individually moving objects in a 3D scene, be it single-view or full point clouds. 
    more » « less
  5. While recent work explored streaming volumetric content on-demand, there is little effort on live volumetric video streaming that bears the potential of bringing more exciting applications than its on-demand counterpart. To fill this critical gap, in this paper, we propose MetaStream, which is, to the best of our knowledge, the first practical live volumetric content capture, creation, delivery, and rendering system for immersive applications such as virtual, augmented, and mixed reality. To address the key challenge of the stringent latency requirement for processing and streaming a huge amount of 3D data, MetaStream integrates several innovations into a holistic system, including dynamic camera calibration, edge-assisted object segmentation, cross-camera redundant point removal, and foveated volumetric content rendering. We implement a prototype of MetaStream using commodity devices and extensively evaluate its performance. Our results demonstrate that MetaStream achieves low-latency live volumetric video streaming at close to 30 frames per second on WiFi networks. Compared to state-of-the-art systems, MetaStream reduces end-to-end latency by up to 31.7% while improving visual quality by up to 12.5%. 
    more » « less