Are all objects equal? Deep spatio-temporal importance prediction in driving videos

详细信息    查看全文

• 作者：Eshed Ohn-Bar ; ^{eohnbar@ucsd.edu}Author Vitae ; Mohan Manubhai TrivediAuthor Vitae
• 关键词：Spatio-temporal object analysis ; Vision-based behavior analysis ; Intelligent and automated vehicles ; Human-centric artificial intelligence ; Contextual robotics ; Driver perception modeling ; Object detection
• 刊名：Pattern Recognition
• 出版年：2017
• 出版时间：April 2017
• 年：2017
• 卷：64
• 期：Complete
• 页码：425-436
• 全文大小：3406 K
• 卷排序：64

文摘

We study a notion of object relevance, as measured in a spatio-temporal context of driving a vehicle. Various spatio-temporal object and scene cues are analyzed for the task of object importance classification. Human-centric metrics are employed for evaluating object detection and studying data bias. Importance-guided training of object detectors is proposed, showing significant improvement over an importance-agnostic baseline.