Fast and Accurate Online Video Object Segmentation via Tracking Parts

@article{Cheng2018FastAA,
  title={Fast and Accurate Online Video Object Segmentation via Tracking Parts},
  author={Jingchun Cheng and Yi-Hsuan Tsai and Wei-Chih Hung and Shengjin Wang and Ming-Hsuan Yang},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={7415-7424}
}
Online video object segmentation is a challenging task as it entails to process the image sequence timely and accurately. To segment a target object through the video, numerous CNN-based methods have been developed by heavily finetuning on the object mask in the first frame, which is time-consuming for online applications. In this paper, we propose a fast and accurate video object segmentation algorithm that can immediately start the segmentation process once receiving the images. We first… 

Figures and Tables from this paper

Guided Co-Segmentation Network for Fast Video Object Segmentation
TLDR
This work proposes a GCSeg (Guided Co-Segmentation) Network which is mainly composed of a Reference Module and a Co-segmentation Module, to simultaneously incorporate the short-term, middle- term, and long-term temporal inter-frame relationships.
Video Object Segmentation Based on Location and RoIAlign in Weight Modulated Multi-Scale Network
TLDR
This work proposes a fast and effective video object segmentation method which does not rely on fine-tuning, and extracts the semantic information of the annotation object in the first frame to generate corresponding channel-wise weights so as to re-target the network to locate and segment the specific object accurately.
Td-VOS: Tracking-Driven Single-Object Video Object Segmentation
TLDR
The proposed method is a tracking-driven single-object video object segmentation, which combines an effective Box2Segmentation module with a general object tracking module, only using the first-frame bounding box (without mask) to initialize.
Discriminative Online Learning for Fast Video Object Segmentation
TLDR
This work proposes a novel approach to video object segmentation, based on a dedicated target appearance model that is exclusively learned online to discriminate between the target and background image regions, and designs a specialized loss and customized optimization techniques to enable highly efficient online training.
Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template Matching
TLDR
“tracking-by-detection” is introduced into VOS which can coherently integrates segmentation into tracking, by proposing a new temporal aggregation network and a novel dynamic time-evolving template matching mechanism to achieve significantly improved performance.
Fast Video Object Segmentation via Dynamic Targeting Network
TLDR
Experimental results on two public datasets demonstrate that the proposed model significantly outperforms existing methods without online training in both accuracy and efficiency, and is comparable to online training-based methods in accuracy with an order of magnitude faster speed.
Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation
TLDR
This work proposes a proposed unified framework consisting of object proposal, tracking and segmentation components that achieves the state-of-the-art performance on several video object segmentation benchmarks.
VideoMatch: Matching based Video Object Segmentation
TLDR
This work develops a novel matching based algorithm for video object segmentation that learns to match extracted features to a provided template without memorizing the appearance of the objects.
Fast Online Object Tracking and Segmentation: A Unifying Approach
TLDR
This method improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting their loss with a binary segmentation task, and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second.
UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking
TLDR
A novel tracklet-based Forest Path Cutting data association algorithm which builds up a decision forest of track hypotheses before cutting this forest into paths that form long-term consistent object tracks which performs competitively with many semi-supervised video object segmentation algorithms.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 47 REFERENCES
One-Shot Video Object Segmentation with Iterative Online Fine-Tuning
TLDR
This work proposes an iterative online training method whereby the model is fine-tuned on the first frame, segments several consecutive frames independently, and then gets updated on its own output segmentation until all frames of a video are segmented.
Learning Video Object Segmentation from Static Images
TLDR
It is demonstrated that highly accurate object segmentation in videos can be enabled by using a convolutional neural network (convnet) trained with static images only, and a combination of offline and online learning strategies are used.
Video Segmentation via Object Flow
TLDR
This work forms a principled, multiscale, spatio-temporal objective function that uses optical flow to propagate information between frames for video segmentation and demonstrates the effectiveness of jointly optimizing optical flow and video segmentations using an iterative scheme.
Online Adaptation of Convolutional Neural Networks for Video Object Segmentation
TLDR
Online Adaptive Video Object Segmentation (OnAVOS) is proposed which updates the network online using training examples selected based on the confidence of the network and the spatial configuration and adds a pretraining step based on objectness, which is learned on PASCAL.
One-Shot Video Object Segmentation
TLDR
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).
Online Video Object Segmentation via Convolutional Trident Network
TLDR
A semi-supervised online video object segmentation algorithm, which accepts user annotations about a target object at the first frame, is proposed in this work and significantly outperforms the state-of-the-art conventional algorithms on the DAVIS benchmark dataset.
Fully Connected Object Proposals for Video Segmentation
TLDR
A novel approach to video segmentation using multiple object proposals that combines appearance with long-range point tracks to ensure robustness with respect to fast motion and occlusions over longer video sequences is presented.
Key-segments for video object segmentation
TLDR
The method first identifies object-like regions in any frame according to both static and dynamic cues and compute a series of binary partitions among candidate “key-segments” to discover hypothesis groups with persistent appearance and motion.
Video Segmentation by Tracking Many Figure-Ground Segments
TLDR
An unsupervised video segmentation approach by simultaneously tracking multiple holistic figure-ground segments that outperforms state-of-the-art approaches in the dataset, showing its efficiency and robustness to challenges in different video sequences.
Fast Object Segmentation in Unconstrained Video
TLDR
This method is fast, fully automatic, and makes minimal assumptions about the video, which enables handling essentially unconstrained settings, including rapidly moving background, arbitrary object motion and appearance, and non-rigid deformations and articulations.
...
1
2
3
4
5
...