Sorry, you need to enable JavaScript to visit this website.

OBJECTNESS-AWARE TRACKING VIA DOUBLE-LAYER MODEL

Citation Author(s):
Jianxiang Ma, Anlong Ming, Yu Zhou
Submitted by:
Menghan Zhou
Last updated:
5 October 2018 - 4:42am
Document Type:
Poster
Document Year:
2018
Event:
Presenters:
Menghan Zhou
Paper Code:
2492
 

The prediction drifts to the non-object backgrounds is a critical issue in conversional correlation filter (CF) based trackers. The key insight of this paper is to propose a doublelayer model to address this problem. Specifically, the first layer is a CF tracker, which is employed to predict a rough position of the target, and the objectness layer, which is regarded as the second layer, is utilized to reveal the object characteristics of the predicted target. The novel objectness layer firstly constructs a set of target-related object proposals, which satisfy both the spatial and temporal constraints. And then an objectness classifier is learned upon the proposal set to best separate the target from the noise background proposals. The convincing experimental results on the challenging OTB100 and TC128 dataset demonstrate the effectiveness of the presented approach.

up
0 users have voted: