In this paper we focus on improving object detection performance in terms of recall. We propose a post-detection stage during which we explore the image with the objective of recovering missed detections. This exploration is performed by sampling object proposals in the image. We analyze four different strategies to perform this sampling, giving special attention to strategies that exploit spatial relations between objects. In addition, we propose a novel method to discover higher-order relations between groups of objects. Experiments on the challenging KITTI dataset show that our proposed relations-based proposal generation strategies can help improving recall at the cost of a relatively low amount of object proposals.
Oramas Mogrovejo J.A., Tuytelaars T., ''Recovering hard-to-find object instances by sampling context-based object proposals'', Computer vision and image understanding, 2016 (Available online 18 August 2016) (accepted).
This is the author’s version of an article accepted for publication. Changes were made to this version by the publisher prior to publication. The final version of record is available at: http://dx.doi.org/10.1016/j.cviu.2016.08.007