Multi-scale volumes for deep object detection and localization

• Published in: Pattern recognition Vol. 61; pp. 557 - 572
• Main Authors: Ohn-Bar, Eshed, Trivedi, Mohan Manubhai
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.01.2017
• Subjects: Context modeling; Efficient detection with deep features; Multi-scale reasoning; Scale variation handling; Structured prediction; Scale variation handling; Efficient detection with deep features; Structured prediction; Multi-scale reasoning; Context modeling
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2016.06.002

This study aims to analyze the benefits of improved multi-scale reasoning for object detection and localization with deep convolutional neural networks. To that end, an efficient and general object detection framework which operates on scale volumes of a deep feature pyramid is proposed. In contrast to the proposed approach, most current state-of-the-art object detectors operate on a single-scale in training, while testing involves independent evaluation across scales. One benefit of the proposed approach is in better capturing of multi-scale contextual information, resulting in significant gains in both detection performance and localization quality of objects on the PASCAL VOC dataset and a multi-view highway vehicles dataset. The joint detection and localization scale-specific models are shown to especially benefit detection of challenging object categories which exhibit large scale variation as well as detection of small objects. •Multi-scale feature reasoning for deep object detection in images is analyzed.•A multi-scale contextual reasoning approach is proposed using multi-scale volumes.•Scale-specific, joint detection and localization models increase robustness.•The approach efficiently handles challenging cases of large variation in scale.