Primary Object Segmentation in Aerial Videos via Hierarchical Temporal Slicing and Co-Segmentation

by   Pengcheng Yuan, et al.

Primary object segmentation plays an important role in understanding videos generated by unmanned aerial vehicles. In this paper, we propose a large-scale dataset APD with 500 aerial videos, in which the primary objects are manually annotated on 5,014 sparsely sampled frames. To the best of our knowledge, it is the largest dataset to date for the task of primary object segmentation in aerial videos. From this dataset, we find that most aerial videos contain large-scale scenes, small sized primary objects as well as consistently varying scales and viewpoints. Inspired by that, we propose a novel hierarchical temporal slicing approach that repeatedly divides a video into two sub-videos formed by the odd and even frames, respectively. In this manner, an aerial video can be represented by a set of hierarchically organized short video clips, and the primary objects they share can be segmented by training end-to-end co-segmentation CNNs and finally refined within the neighborhood reversible flows. Experimental results show that our approach remarkably outperforms 24 state-of-the-art methods in segmenting primary objects in various types of aerial videos.


page 1

page 2

page 3

page 4

page 7


Complementary Segmentation of Primary Video Objects with Reversible Flows

Segmenting primary objects in a video is an important yet challenging pr...

FireNet: Real-time Segmentation of Fire Perimeter from Aerial Video

In this paper, we share our approach to real-time segmentation of fire p...

Foldover Features for Dynamic Object Behavior Description in Microscopic Videos

Behavior description is conducive to the analysis of tiny objects, simil...

ERA: A Dataset and Deep Learning Benchmark for Event Recognition in Aerial Videos

Along with the increasing use of unmanned aerial vehicles (UAVs), large ...

Scale-aware Insertion of Virtual Objects in Monocular Videos

In this paper, we propose a scale-aware method for inserting virtual obj...

Learning Knowledge-Rich Sequential Model for Planar Homography Estimation in Aerial Video

This paper presents an unsupervised approach that leverages raw aerial v...

Actionet: An Interactive End-To-End Platform For Task-Based Data Collection And Augmentation In 3D Environment

The problem of task planning for artificial agents remains largely unsol...

Please sign up or login with your details

Forgot password? Click here to reset