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

SALPROP: SALIENT OBJECT PROPOSALS VIA AGGREGATED EDGE CUES

Citation Author(s):
PRERANA MUKHERJEE, BREJESH LALL, SARVASWA TANDON
Submitted by:
PRERANA MUKHERJEE
Last updated:
12 September 2017 - 6:11am
Document Type:
Poster
Document Year:
2017
Event:
Presenters:
PRERANA MUKHERJEE
Paper Code:
MP-PA.8
 

In this paper, we propose a novel object proposal generation scheme by formulating a graph-based salient edge classification framework that utilizes the edge context. In the proposed method, we construct a Bayesian probabilistic edge map to assign a saliency value to the edgelets by exploiting low level edge features. A Conditional Random Field is then learned to effectively combine these features for edge classification with object/non-object label. We propose an objectness score for the generated windows by analyzing the salient edge density inside the bounding box. Extensive experiments on PASCAL VOC 2007 dataset demonstrate that the proposed method gives competitive performance against 10 popular generic object detection techniques while using fewer number of proposals.

up
0 users have voted: