Recovering hard-to-find object instances by sampling context-based object proposals
| Autor: | M José Oramas, Tinne Tuytelaars |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2016 |
| Předmět: |
FOS: Computer and information sciences
Exploit Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Context (language use) 02 engineering and technology 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences 0202 electrical engineering electronic engineering information engineering 0105 earth and related environmental sciences Computer. Automation business.industry Sampling (statistics) Object (computer science) Object detection Spatial relation Method Signal Processing 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Data mining Artificial intelligence Focus (optics) business computer Software |
| Zdroj: | Computer vision and image understanding |
| ISSN: | 1077-3142 |
| Popis: | 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. Comment: Computer Vision and Image Understanding (CVIU) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect