SalProp: Salient object proposals via aggregated edge cues
This work addresses object detection efficiency for computer vision applications, but it is incremental as it builds on existing edge-based techniques.
The paper tackled the problem of generating object proposals for detection by developing a graph-based salient edge classification framework, resulting in competitive performance on PASCAL VOC 2007 with fewer proposals compared to 10 existing methods.
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.